oib/aitbc
1
0
Fork 0
Code Issues Pull Requests Actions 21 Packages Projects Releases Wiki Activity

Rename openclaw to hermes across documentation and workflows
Some checks failed
Cross-Node Transaction Testing / transaction-test (push) Has been cancelled
Details
Deploy to Testnet / deploy-testnet (push) Has been cancelled
Details
Documentation Validation / validate-docs (push) Has been cancelled
Details
Documentation Validation / validate-policies-strict (push) Has been cancelled
Details
Multi-Node Stress Testing / stress-test (push) Has been cancelled
Details
Node Failover Simulation / failover-test (push) Has been cancelled
Details
Integration Tests / test-service-integration (push) Has been cancelled
Details
Security Scanning / security-scan (push) Has been cancelled
Details
Python Tests / test-python (push) Has been cancelled
Details
CLI Tests / test-cli (push) Has been cancelled
Details
Blockchain Synchronization Verification / sync-verification (push) Successful in 11s
Details
Contract Performance Benchmarks / benchmark-gas-usage (push) Successful in 1m36s
Details
Contract Performance Benchmarks / benchmark-execution-time (push) Successful in 1m24s
Details
Contract Performance Benchmarks / benchmark-throughput (push) Successful in 1m25s
Details
Cross-Chain Functionality Tests / test-cross-chain-sync (push) Successful in 2s
Details
Cross-Chain Functionality Tests / test-cross-chain-transactions (push) Successful in 5s
Details
Cross-Chain Functionality Tests / test-cross-chain-bridge (push) Has been skipped
Details
Cross-Chain Functionality Tests / test-multi-chain-consensus (push) Successful in 3s
Details
Cross-Chain Functionality Tests / aggregate-results (push) Has been skipped
Details
Multi-Chain Island Architecture Tests / test-multi-chain-island (push) Successful in 2s
Details
Multi-Node Blockchain Health Monitoring / health-check (push) Successful in 3s
Details
P2P Network Verification / p2p-verification (push) Successful in 2s
Details
Smart Contract Tests / test-solidity (map[name:aitbc-contracts path:contracts]) (push) Failing after 1m28s
Details
Smart Contract Tests / test-solidity (map[name:aitbc-token path:packages/solidity/aitbc-token]) (push) Successful in 21s
Details
Smart Contract Tests / test-foundry (push) Failing after 20s
Details
Smart Contract Tests / lint-solidity (push) Successful in 30s
Details
Smart Contract Tests / deploy-contracts (push) Successful in 1m40s
Details
Systemd Sync / sync-systemd (push) Successful in 26s
Details
Contract Performance Benchmarks / compare-benchmarks (push) Successful in 4s
Details

Browse Source 
- Update workflow paths from docs/openclaw to docs/hermes
- Rename skill prefixes from openclaw-* to hermes-*
- Update agent skill references in refactoring and analysis docs
- Rename OPENCLAW_AITBC_MASTERY_PLAN.md to reflect hermes branding
- Update CLI examples and command references throughout documentation
This commit is contained in:
aitbc
2026-05-07 11:42:06 +02:00
parent 151aae1916
commit 852f2e5a8a
307 changed files with 3333 additions and 2837 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
.windsurf/meta/REFACTORING_SUMMARY.md
View File

@@ -18,13 +18,13 @@ version: 1.0
5. **aitbc-node-coordinator** - Cross-node coordination and messaging
6. **aitbc-analytics-analyzer** - Blockchain analytics and performance metrics
#### **OpenClaw Agent Skills (6/6)**
7. **openclaw-agent-communicator** - Agent message handling and responses
8. **openclaw-session-manager** - Session creation and context management
9. **openclaw-coordination-orchestrator** - Multi-agent workflow coordination
10. **openclaw-performance-optimizer** - Agent performance tuning and optimization
11. **openclaw-error-handler** - Error detection and recovery procedures
12. **openclaw-agent-testing-skill** - Agent communication validation and performance testing
#### **hermes Agent Skills (6/6)**
7. **hermes-agent-communicator** - Agent message handling and responses
8. **hermes-session-manager** - Session creation and context management
9. **hermes-coordination-orchestrator** - Multi-agent workflow coordination
10. **hermes-performance-optimizer** - Agent performance tuning and optimization
11. **hermes-error-handler** - Error detection and recovery procedures
12. **hermes-agent-testing-skill** - Agent communication validation and performance testing
---
@@ -134,7 +134,7 @@ version: 1.0
### **Before (Legacy)**
```
# Mixed responsibilities, unclear output
openclaw agent --agent main --message "Check blockchain and process data" --thinking high
hermes agent --agent main --message "Check blockchain and process data" --thinking high
cd /opt/aitbc && source venv/bin/activate && ./aitbc-cli chain
```
@@ -143,7 +143,7 @@ cd /opt/aitbc && source venv/bin/activate && ./aitbc-cli chain
# Atomic responsibilities, structured output
@aitbc-wallet-manager Create wallet "trading-wallet" with password "secure123"
@aitbc-transaction-processor Send 100 AIT from trading-wallet to address
@openclaw-agent-communicator Send message to main agent: "Analyze transaction results"
@hermes-agent-communicator Send message to main agent: "Analyze transaction results"
```
---

54
.windsurf/meta/SKILL_ANALYSIS.md
View File

@@ -41,20 +41,20 @@ version: 1.0
#### **CURRENT ACTIVE SKILL SET**
The active OpenClaw-style split skills now live in `.windsurf/skills/` and include:
The active hermes-style split skills now live in `.windsurf/skills/` and include:
- `openclaw-agent-communicator`
- `openclaw-session-manager`
- `openclaw-coordination-orchestrator`
- `openclaw-performance-optimizer`
- `openclaw-error-handler`
- `openclaw-agent-testing-skill`
- `hermes-agent-communicator`
- `hermes-session-manager`
- `hermes-coordination-orchestrator`
- `hermes-performance-optimizer`
- `hermes-error-handler`
- `hermes-agent-testing-skill`
---
## Current Skill Analysis
### File: `openclaw-aitbc.md` (archived legacy)
### File: `hermes-aitbc.md` (archived legacy)
#### **IDENTIFIED WEAKNESSES:**
@@ -65,22 +65,22 @@ The active OpenClaw-style split skills now live in `.windsurf/skills/` and inclu
#### **RECOMMENDED ACTION:**
- **ARCHIVE** - This skill is deprecated and serves no purpose
- **Migration already completed** - The active skill set now uses the atomic OpenClaw skills listed below
- **Migration already completed** - The active skill set now uses the atomic hermes skills listed below
#### **CURRENT ACTIVE SKILL SET**
- `openclaw-agent-communicator`
- `openclaw-session-manager`
- `openclaw-coordination-orchestrator`
- `openclaw-performance-optimizer`
- `openclaw-error-handler`
- `openclaw-agent-testing-skill`
- `hermes-agent-communicator`
- `hermes-session-manager`
- `hermes-coordination-orchestrator`
- `hermes-performance-optimizer`
- `hermes-error-handler`
- `hermes-agent-testing-skill`
---
## Current Skill Analysis
### File: `openclaw-management.md` (archived legacy)
### File: `hermes-management.md` (archived legacy)
#### **IDENTIFIED WEAKNESSES:**
@@ -98,22 +98,22 @@ The active OpenClaw-style split skills now live in `.windsurf/skills/` and inclu
#### **RECOMMENDED SPLIT INTO ATOMIC SKILLS:**
1. `openclaw-agent-communicator` - Agent message handling and responses
2. `openclaw-session-manager` - Session creation and context management
3. `openclaw-coordination-orchestrator` - Multi-agent workflow coordination
4. `openclaw-performance-optimizer` - Agent performance tuning and optimization
5. `openclaw-error-handler` - Error detection and recovery procedures
1. `hermes-agent-communicator` - Agent message handling and responses
2. `hermes-session-manager` - Session creation and context management
3. `hermes-coordination-orchestrator` - Multi-agent workflow coordination
4. `hermes-performance-optimizer` - Agent performance tuning and optimization
5. `hermes-error-handler` - Error detection and recovery procedures
#### **CURRENT ACTIVE SKILL SET**
These are the actual active files in `.windsurf/skills/`:
- `openclaw-agent-communicator`
- `openclaw-session-manager`
- `openclaw-coordination-orchestrator`
- `openclaw-performance-optimizer`
- `openclaw-error-handler`
- `openclaw-agent-testing-skill`
- `hermes-agent-communicator`
- `hermes-session-manager`
- `hermes-coordination-orchestrator`
- `hermes-performance-optimizer`
- `hermes-error-handler`
- `hermes-agent-testing-skill`
---

48
.windsurf/plans/OPENCLAW_AITBC_MASTERY_PLAN.md → .windsurf/plans/HERMES_AITBC_MASTERY_PLAN.md
View File

@@ -1,10 +1,10 @@
---
description: Comprehensive OpenClaw agent training plan for AITBC software mastery from beginner to expert level
title: OPENCLAW_AITBC_MASTERY_PLAN
description: Comprehensive hermes agent training plan for AITBC software mastery from beginner to expert level
title: hermes_AITBC_MASTERY_PLAN
version: 2.2
---
# OpenClaw AITBC Mastery Plan
# hermes AITBC Mastery Plan
## Quick Navigation
- [Purpose](#purpose)
@@ -27,7 +27,7 @@ version: 2.2
---
## Purpose
Comprehensive training plan for OpenClaw agents to master AITBC software on both nodes (aitbc and aitbc1) using CLI tools, progressing from basic operations to expert-level blockchain and AI operations.
Comprehensive training plan for hermes agents to master AITBC software on both nodes (aitbc and aitbc1) using CLI tools, progressing from basic operations to expert-level blockchain and AI operations.
## Overview
@@ -93,7 +93,7 @@ ssh aitbc1 'cd /opt/aitbc && git reset --hard origin/main'
- **Marketplace**: [`multi-node-blockchain-marketplace.md`](../workflows/multi-node-blockchain-marketplace.md) - GPU provider testing and AI operations
- **Production**: [`multi-node-blockchain-production.md`](../workflows/multi-node-blockchain-production.md) - Production deployment and scaling
- **Reference**: [`multi-node-blockchain-reference.md`](../workflows/multi-node-blockchain-reference.md) - Configuration reference
- **OpenClaw Setup**: [`multi-node-blockchain-setup-openclaw.md`](../workflows/multi-node-blockchain-setup-openclaw.md) - OpenClaw-specific deployment
- **hermes Setup**: [`multi-node-blockchain-setup-hermes.md`](../workflows/multi-node-blockchain-setup-hermes.md) - hermes-specific deployment
- **Communication Test**: [`blockchain-communication-test.md`](../workflows/blockchain-communication-test.md) - Cross-node verification
- **Scenario Validation**: [`VALIDATION.md`](../scenarios/VALIDATION.md) - Canonical 3-node validation guide and harness
@@ -179,16 +179,16 @@ cd /opt/aitbc/scripts/training
- **CLI Commands**:
```bash
# Wallet creation (non-interactive)
./aitbc-cli wallet create --name openclaw-wallet --password <password> --yes --no-confirm
./aitbc-cli wallet create --name hermes-wallet --password <password> --yes --no-confirm
./aitbc-cli wallet list --output json
# Balance checking (debug mode)
./aitbc-cli wallet balance --name openclaw-wallet --verbose
./aitbc-cli wallet balance --name hermes-wallet --verbose
./aitbc-cli wallet balance --all --format table
# Node-specific operations (with debug)
NODE_URL=http://10.1.223.40:8006 ./aitbc-cli wallet balance --name openclaw-wallet --verbose # Genesis node
NODE_URL=http://<aitbc1-ip>:8006 ./aitbc-cli wallet balance --name openclaw-wallet --debug # Follower node
NODE_URL=http://10.1.223.40:8006 ./aitbc-cli wallet balance --name hermes-wallet --verbose # Genesis node
NODE_URL=http://<aitbc1-ip>:8006 ./aitbc-cli wallet balance --name hermes-wallet --debug # Follower node
```
#### **1.3 Basic Transaction Operations**
@@ -196,8 +196,8 @@ cd /opt/aitbc/scripts/training
- **CLI Commands**:
```bash
# Basic transactions (non-interactive)
./aitbc-cli wallet send --from openclaw-wallet --to recipient --amount 100 --password <password> --yes --no-confirm
./aitbc-cli wallet transactions --name openclaw-wallet --limit 10 --output json
./aitbc-cli wallet send --from hermes-wallet --to recipient --amount 100 --password <password> --yes --no-confirm
./aitbc-cli wallet transactions --name hermes-wallet --limit 10 --output json
# Cross-node transactions (debug mode)
NODE_URL=http://10.1.223.40:8006 ./aitbc-cli wallet send --from wallet1 --to wallet2 --amount 50 --verbose --dry-run
@@ -240,9 +240,9 @@ cd /opt/aitbc/scripts/training
- **CLI Commands**:
```bash
# Advanced wallet operations (non-interactive)
./aitbc-cli wallet backup --name openclaw-wallet --yes --no-confirm
./aitbc-cli wallet backup --name hermes-wallet --yes --no-confirm
./aitbc-cli wallet restore --name backup-wallet --force --yes
./aitbc-cli wallet export --name openclaw-wallet --output json
./aitbc-cli wallet export --name hermes-wallet --output json
# Multi-wallet coordination (debug mode)
./aitbc-cli wallet sync --all --verbose
@@ -278,7 +278,7 @@ cd /opt/aitbc/scripts/training
./aitbc-cli blockchain contract call --address <address> --method <method> --verbose
# Agent messaging contracts (debug mode)
./aitbc-cli agent message --to <agent_id> --content "Hello from OpenClaw" --debug
./aitbc-cli agent message --to <agent_id> --content "Hello from hermes" --debug
./aitbc-cli agent messages --from <agent_id> --output json
```
@@ -720,7 +720,7 @@ export EXCHANGE_URL=http://localhost:8001 # Exchange API
export OLLAMA_URL=http://localhost:11434 # Ollama
# Authentication
export WALLET_NAME=openclaw-wallet
export WALLET_NAME=hermes-wallet
export WALLET_PASSWORD=<secure_password>
```
@@ -806,7 +806,7 @@ grep "Performance benchmark" /var/log/aitbc/training_stage*.log
## 🎓 **Certification & Recognition**
### **OpenClaw AITBC Master Certification**
### **hermes AITBC Master Certification**
**Requirements**:
- Complete all 5 training stages via script execution
- Pass final certification exam (>95% score) simulated in Stage 5
@@ -822,10 +822,10 @@ grep "Performance benchmark" /var/log/aitbc/training_stage*.log
5. **Log Review**: Comprehensive analysis of training performance logs
### **Certification Benefits**
- **Expert Recognition**: Certified OpenClaw AITBC Master
- **Expert Recognition**: Certified hermes AITBC Master
- **Advanced Access**: Full system access and permissions
- **Economic Authority**: Economic modeling and optimization rights
- **Teaching Authority**: Qualified to train other OpenClaw agents
- **Teaching Authority**: Qualified to train other hermes agents
- **Automation Privileges**: Ability to create custom training scripts
### **Post-Certification Training**
@@ -893,7 +893,7 @@ iptables -L | grep 8006
curl http://localhost:11434/api/tags
# Verify wallet balance
/opt/aitbc/aitbc-cli balance --name openclaw-trainee
/opt/aitbc/aitbc-cli balance --name hermes-trainee
# Check AI service status
/opt/aitbc/aitbc-cli ai service status --name agent-coordinator
@@ -923,10 +923,10 @@ top -bn1 | head -20
# Remove existing wallet if needed
# WARNING: Only for training wallets
rm -rf /var/lib/aitbc/keystore/openclaw-trainee*
rm -rf /var/lib/aitbc/keystore/hermes-trainee*
# Recreate with verbose output
/opt/aitbc/aitbc-cli create --name openclaw-trainee --password trainee123 --verbose
/opt/aitbc/aitbc-cli create --name hermes-trainee --password trainee123 --verbose
```
### **Performance Optimization**
@@ -1048,10 +1048,10 @@ curl http://10.1.223.40:8001/health
**Training Plan Version**: 2.1
**Last Updated**: 2026-05-02
**Target Audience**: OpenClaw Agents
**Target Audience**: hermes Agents
**Difficulty**: Beginner to Expert (5 Stages)
**Estimated Duration**: 4 weeks
**Certification**: OpenClaw AITBC Master
**Certification**: hermes AITBC Master
**Training Scripts**: Complete automation suite available at `/opt/aitbc/scripts/training/`
---
@@ -1120,7 +1120,7 @@ All training stages are now fully automated with executable scripts:
- **Log Analysis**: Comprehensive performance tracking and optimization
### **Immediate Deployment**
OpenClaw agents can begin training immediately using:
hermes agents can begin training immediately using:
```bash
cd /opt/aitbc/scripts/training
./master_training_launcher.sh

44
.windsurf/references/ai-operations-reference.md
View File

@@ -9,7 +9,7 @@ This reference guide covers AI operations in the AITBC blockchain network, inclu
- [Marketplace Operations](#marketplace-operations)
- [GPU Provider Marketplace](#gpu-provider-marketplace)
- [Agent AI Workflows](#agent-ai-workflows)
- [OpenClaw Agent Coordination](#openclaw-agent-coordination)
- [Hermes Agent Coordination](#hermes-agent-coordination)
- [Cross-Node AI Coordination](#cross-node-ai-coordination)
- [Blockchain Integration](#blockchain-integration)
- [AI Economics and Pricing](#ai-economics-and-pricing)
@@ -245,44 +245,44 @@ python3 /opt/aitbc/plugins/ollama/client_plugin.py --model llama2 --prompt "Gene
./aitbc-cli agent execute --name "ai-coordinator" --wallet genesis-ops --priority high
```
## OpenClaw Agent Coordination
## Hermes Agent Coordination
> **Canonical validation**: Use [`docs/scenarios/VALIDATION.md`](../../docs/scenarios/VALIDATION.md) and `scripts/workflow/44_comprehensive_multi_node_scenario.sh` for the current 3-node test path.
### OpenClaw AI Agent Setup
### Hermes AI Agent Setup
```bash
# Initialize OpenClaw AI agent
openclaw agent init --name ai-inference-agent --type ai-worker
# Initialize Hermes AI agent
hermes agent init --name ai-inference-agent --type ai-worker
# Configure agent for AI operations
openclaw agent configure --name ai-inference-agent --ai-model "llama2" --gpu-requirement 1
hermes agent configure --name ai-inference-agent --ai-model "llama2" --gpu-requirement 1
# Deploy agent to node
openclaw agent deploy --name ai-inference-agent --target-node aitbc1
hermes agent deploy --name ai-inference-agent --target-node aitbc1
```
### OpenClaw AI Workflows
### Hermes AI Workflows
```bash
# Execute AI workflow via OpenClaw
openclaw execute --agent AI-InferenceAgent --task run_inference --prompt "Generate image" --model "stable-diffusion"
# Execute AI workflow via Hermes
hermes execute --agent AI-InferenceAgent --task run_inference --prompt "Generate image" --model "stable-diffusion"
# Coordinate multi-agent AI pipeline
openclaw execute --agent CoordinatorAgent --task ai_pipeline --workflow "preprocess->inference->postprocess"
hermes execute --agent CoordinatorAgent --task ai_pipeline --workflow "preprocess->inference->postprocess"
# Monitor agent AI performance
openclaw monitor --agent AI-InferenceAgent --metrics gpu,throughput,errors
hermes monitor --agent AI-InferenceAgent --metrics gpu,throughput,errors
```
### Cross-Agent Communication
```bash
# Send AI job result to another agent
openclaw message --from AI-InferenceAgent --to Data-ProcessingAgent --payload "job_id:123,result:image.png"
hermes message --from AI-InferenceAgent --to Data-ProcessingAgent --payload "job_id:123,result:image.png"
# Request resources from coordinator
openclaw message --from AI-TrainingAgent --to Resource-CoordinatorAgent --payload "request:gpu,count:2,duration:3600"
hermes message --from AI-TrainingAgent --to Resource-CoordinatorAgent --payload "request:gpu,count:2,duration:3600"
# Broadcast job completion
openclaw broadcast --from AI-InferenceAgent --channel ai-jobs --payload "job_123:completed"
hermes broadcast --from AI-InferenceAgent --channel ai-jobs --payload "job_123:completed"
```
## Cross-Node AI Coordination
@@ -664,23 +664,23 @@ ssh gitea-runner 'ollama pull mistral'
./aitbc-cli market order status --order-id "order_456"
```
### Workflow 5: OpenClaw Multi-Agent Pipeline
### Workflow 5: Hermes Multi-Agent Pipeline
```bash
# 1. Initialize agents
openclaw agent init --name Data-Preprocessor --type data-worker
openclaw agent init --name AI-Inference --type ai-worker
openclaw agent init --name Result-Postprocessor --type data-worker
hermes agent init --name Data-Preprocessor --type data-worker
hermes agent init --name AI-Inference --type ai-worker
hermes agent init --name Result-Postprocessor --type data-worker
# 2. Configure agents
openclaw agent configure --name AI-Inference --ai-model "llama2" --gpu-requirement 1
hermes agent configure --name AI-Inference --ai-model "llama2" --gpu-requirement 1
# 3. Execute pipeline
openclaw execute --agent CoordinatorAgent --task run_pipeline \
hermes execute --agent CoordinatorAgent --task run_pipeline \
--workflow "Data-Preprocessor->AI-Inference->Result-Postprocessor" \
--input "data.json" --output "results.json"
# 4. Monitor pipeline
openclaw monitor --pipeline pipeline_123 --realtime
hermes monitor --pipeline pipeline_123 --realtime
```
## Best Practices

2
.windsurf/skills/aitbc-ripgrep-specialist.md
View File

@@ -111,7 +111,7 @@ rg "password|secret|token|key" --type py --type yaml /opt/aitbc/
rg "blockchain|chain\.db|genesis|mining" --type py /opt/aitbc/
# Find AI/ML related code
rg "openclaw|ollama|model|inference" --type py /opt/aitbc/
rg "hermes|ollama|model|inference" --type py /opt/aitbc/
# Find marketplace code
rg "marketplace|listing|bid|gpu" --type py /opt/aitbc/

4
.windsurf/skills/aitbc-system-architect.md
View File

@@ -26,7 +26,7 @@ You are an expert AITBC System Architect with deep knowledge of the proper syste
- **Repository**: `/opt/aitbc` (clean, code-only)
### Service Management
- **Production Services**: Marketplace, Blockchain, OpenClaw AI
- **Production Services**: Marketplace, Blockchain, Hermes AI
- **SystemD Services**: All AITBC services with proper configuration
- **Environment Files**: System and production environment management
- **Path References**: Ensuring all services use correct system paths
@@ -157,7 +157,7 @@ ls -la /var/lib/aitbc/ /etc/aitbc/ /var/log/aitbc/
- **AI Operations**: Ensure AI services use proper system paths
- **Marketplace Operations**: Verify marketplace data in correct locations
### OpenClaw Skills
### Hermes Skills
- **Agent Communication**: Ensure AI agents use system log paths
- **Session Management**: Verify session data in system directories
- **Testing Skills**: Use system directories for test data

64
.windsurf/skills/archive/openclaw-aitbc.md
View File

@@ -1,23 +1,23 @@
---
description: Legacy OpenClaw AITBC integration - see split skills for focused operations
title: OpenClaw AITBC Integration (Legacy)
description: Legacy Hermes AITBC integration - see split skills for focused operations
title: Hermes AITBC Integration (Legacy)
version: 6.0 - DEPRECATED
---
# OpenClaw AITBC Integration (Legacy - See Split Skills)
# Hermes AITBC Integration (Legacy - See Split Skills)
⚠️ **This skill has been split into focused skills for better organization:**
## 📚 Current Active OpenClaw Skills
## 📚 Current Active Hermes Skills
This legacy bundle now maps to the current atomic OpenClaw skill files:
This legacy bundle now maps to the current atomic Hermes skill files:
- **`openclaw-agent-communicator.md`** — agent message handling and responses
- **`openclaw-session-manager.md`** — session creation and context management
- **`openclaw-coordination-orchestrator.md`** — multi-agent workflow coordination
- **`openclaw-performance-optimizer.md`** — agent performance tuning and optimization
- **`openclaw-error-handler.md`** — error detection and recovery procedures
- **`openclaw-agent-testing-skill.md`** — agent communication validation and performance testing
- **`hermes-agent-communicator.md`** — agent message handling and responses
- **`hermes-session-manager.md`** — session creation and context management
- **`hermes-coordination-orchestrator.md`** — multi-agent workflow coordination
- **`hermes-performance-optimizer.md`** — agent performance tuning and optimization
- **`hermes-error-handler.md`** — error detection and recovery procedures
- **`hermes-agent-testing-skill.md`** — agent communication validation and performance testing
### Archived Blockchain Companion
**File**: `aitbc-blockchain.md`
@@ -37,21 +37,21 @@ This legacy bundle now maps to the current atomic OpenClaw skill files:
**Before (Legacy)**:
```bash
# Mixed OpenClaw + AITBC operations
openclaw agent --agent main --message "Check blockchain and process data" --thinking high
# Mixed Hermes + AITBC operations
hermes agent --agent main --message "Check blockchain and process data" --thinking high
cd /opt/aitbc && source venv/bin/activate && ./aitbc-cli chain
```
**After (Split Skills)**:
**OpenClaw Agent Management**:
**Hermes Agent Management**:
```bash
# Pure agent coordination
openclaw agent --agent coordinator --message "Coordinate blockchain monitoring workflow" --thinking high
hermes agent --agent coordinator --message "Coordinate blockchain monitoring workflow" --thinking high
# Agent workflow orchestration
SESSION_ID="blockchain-monitor-$(date +%s)"
openclaw agent --agent monitor --session-id $SESSION_ID --message "Monitor blockchain health" --thinking medium
hermes agent --agent monitor --session-id $SESSION_ID --message "Monitor blockchain health" --thinking medium
```
**AITBC Blockchain Operations**:
@@ -67,7 +67,7 @@ cd /opt/aitbc && source venv/bin/activate
### Benefits of Focused Skills
1. **Clearer Separation of Concerns**
- OpenClaw: Agent coordination and workflow management
- Hermes: Agent coordination and workflow management
- AITBC: Blockchain operations and data management
2. **Better Documentation Organization**
@@ -76,7 +76,7 @@ cd /opt/aitbc && source venv/bin/activate
- Easier maintenance and updates
3. **Improved Reusability**
- OpenClaw skills can be used with any system
- Hermes skills can be used with any system
- AITBC skills can be used with any agent framework
- Modular combination possible
@@ -87,7 +87,7 @@ cd /opt/aitbc && source venv/bin/activate
### When to Use Each Skill
**Use OpenClaw Agent Management Skill for**:
**Use Hermes Agent Management Skill for**:
- Multi-agent workflow coordination
- Agent communication patterns
- Session management and context
@@ -102,7 +102,7 @@ cd /opt/aitbc && source venv/bin/activate
- Smart contract messaging
**Combine Both Skills for**:
- Complete OpenClaw + AITBC integration
- Complete Hermes + AITBC integration
- Agent-driven blockchain operations
- Automated blockchain workflows
- Cross-node agent coordination
@@ -111,16 +111,16 @@ cd /opt/aitbc && source venv/bin/activate
The following content from the original combined skill is now deprecated and moved to the appropriate split skills:
- ~~Agent command syntax~~ → **OpenClaw Agent Management**
- ~~Agent command syntax~~ → **Hermes Agent Management**
- ~~AITBC CLI commands~~ → **AITBC Blockchain Operations**
- ~~AI operations~~ → **AITBC Blockchain Operations**
- ~~Blockchain coordination~~ → **AITBC Blockchain Operations**
- ~~Agent workflows~~ → **OpenClaw Agent Management**
- ~~Agent workflows~~ → **Hermes Agent Management**
## Migration Checklist
### ✅ Completed
- [x] Created OpenClaw Agent Management skill
- [x] Created Hermes Agent Management skill
- [x] Created AITBC Blockchain Operations skill
- [x] Updated all command references
- [x] Added migration guide
@@ -137,14 +137,14 @@ The following content from the original combined skill is now deprecated and mov
## Quick Reference
### OpenClaw Agent Management
### Hermes Agent Management
```bash
# Agent coordination
openclaw agent --agent coordinator --message "Coordinate workflow" --thinking high
hermes agent --agent coordinator --message "Coordinate workflow" --thinking high
# Session-based workflow
SESSION_ID="task-$(date +%s)"
openclaw agent --agent worker --session-id $SESSION_ID --message "Execute task" --thinking medium
hermes agent --agent worker --session-id $SESSION_ID --message "Execute task" --thinking medium
```
### AITBC Blockchain Operations
@@ -163,12 +163,12 @@ cd /opt/aitbc && source venv/bin/activate
## Quick Links to Current Active Skills
- **OpenClaw Agent Communicator**: [../openclaw-agent-communicator.md](../openclaw-agent-communicator.md)
- **OpenClaw Session Manager**: [../openclaw-session-manager.md](../openclaw-session-manager.md)
- **OpenClaw Coordination Orchestrator**: [../openclaw-coordination-orchestrator.md](../openclaw-coordination-orchestrator.md)
- **OpenClaw Performance Optimizer**: [../openclaw-performance-optimizer.md](../openclaw-performance-optimizer.md)
- **OpenClaw Error Handler**: [../openclaw-error-handler.md](../openclaw-error-handler.md)
- **OpenClaw Agent Testing Skill**: [../openclaw-agent-testing-skill.md](../openclaw-agent-testing-skill.md)
- **Hermes Agent Communicator**: [../hermes-agent-communicator.md](../hermes-agent-communicator.md)
- **Hermes Session Manager**: [../hermes-session-manager.md](../hermes-session-manager.md)
- **Hermes Coordination Orchestrator**: [../hermes-coordination-orchestrator.md](../hermes-coordination-orchestrator.md)
- **Hermes Performance Optimizer**: [../hermes-performance-optimizer.md](../hermes-performance-optimizer.md)
- **Hermes Error Handler**: [../hermes-error-handler.md](../hermes-error-handler.md)
- **Hermes Agent Testing Skill**: [../hermes-agent-testing-skill.md](../hermes-agent-testing-skill.md)
## Archived Blockchain Companion

160
.windsurf/skills/archive/openclaw-management.md
View File

@@ -1,41 +1,41 @@
---
description: OpenClaw agent management and coordination capabilities
title: OpenClaw Agent Management Skill
description: hermes agent management and coordination capabilities
title: hermes Agent Management Skill
version: 1.0
---
# OpenClaw Agent Management Skill
# hermes Agent Management Skill
This skill provides comprehensive OpenClaw agent management, communication, and coordination capabilities. Focus on agent operations, session management, and cross-agent workflows.
This skill provides comprehensive hermes agent management, communication, and coordination capabilities. Focus on agent operations, session management, and cross-agent workflows.
## Current Active OpenClaw Skills
## Current Active hermes Skills
This archived management skill is now represented by the following active atomic skill files:
- **`openclaw-agent-communicator.md`** — agent message handling and responses
- **`openclaw-session-manager.md`** — session creation and context management
- **`openclaw-coordination-orchestrator.md`** — multi-agent workflow coordination
- **`openclaw-performance-optimizer.md`** — agent performance tuning and optimization
- **`openclaw-error-handler.md`** — error detection and recovery procedures
- **`openclaw-agent-testing-skill.md`** — agent communication validation and performance testing
- **`hermes-agent-communicator.md`** — agent message handling and responses
- **`hermes-session-manager.md`** — session creation and context management
- **`hermes-coordination-orchestrator.md`** — multi-agent workflow coordination
- **`hermes-performance-optimizer.md`** — agent performance tuning and optimization
- **`hermes-error-handler.md`** — error detection and recovery procedures
- **`hermes-agent-testing-skill.md`** — agent communication validation and performance testing
## Prerequisites
- OpenClaw 2026.3.24+ installed and gateway running
- Agent workspace configured: `~/.openclaw/workspace/`
- hermes 2026.3.24+ installed and gateway running
- Agent workspace configured: `~/.hermes/workspace/`
- Network connectivity for multi-agent coordination
## Critical: Correct OpenClaw Syntax
## Critical: Correct hermes Syntax
### Agent Commands
```bash
# CORRECT — always use --message (long form), not -m
openclaw agent --agent main --message "Your task here" --thinking medium
hermes agent --agent main --message "Your task here" --thinking medium
# Session-based communication (maintains context across calls)
SESSION_ID="workflow-$(date +%s)"
openclaw agent --agent main --session-id $SESSION_ID --message "Initialize task" --thinking low
openclaw agent --agent main --session-id $SESSION_ID --message "Continue task" --thinking medium
hermes agent --agent main --session-id $SESSION_ID --message "Initialize task" --thinking low
hermes agent --agent main --session-id $SESSION_ID --message "Continue task" --thinking medium
# Thinking levels: off | minimal | low | medium | high | xhigh
```
@@ -46,15 +46,15 @@ openclaw agent --agent main --session-id $SESSION_ID --message "Continue task" -
### Agent Status and Management
```bash
# Check agent status
openclaw status --agent all
openclaw status --agent main
hermes status --agent all
hermes status --agent main
# List available agents
openclaw list --agents
hermes list --agents
# Agent workspace management
openclaw workspace --setup
openclaw workspace --status
hermes workspace --setup
hermes workspace --status
```
## Agent Communication Patterns
@@ -62,10 +62,10 @@ openclaw workspace --status
### Single Agent Tasks
```bash
# Simple task execution
openclaw agent --agent main --message "Analyze the system logs and report any errors" --thinking high
hermes agent --agent main --message "Analyze the system logs and report any errors" --thinking high
# Task with specific parameters
openclaw agent --agent main --message "Process this data: /path/to/data.csv" --thinking medium --parameters "format:csv,mode:analyze"
hermes agent --agent main --message "Process this data: /path/to/data.csv" --thinking medium --parameters "format:csv,mode:analyze"
```
### Session-Based Workflows
@@ -74,26 +74,26 @@ openclaw agent --agent main --message "Process this data: /path/to/data.csv" --t
SESSION_ID="data-analysis-$(date +%s)"
# Step 1: Data collection
openclaw agent --agent main --session-id $SESSION_ID --message "Collect data from API endpoints" --thinking low
hermes agent --agent main --session-id $SESSION_ID --message "Collect data from API endpoints" --thinking low
# Step 2: Data processing
openclaw agent --agent main --session-id $SESSION_ID --message "Process collected data and generate insights" --thinking medium
hermes agent --agent main --session-id $SESSION_ID --message "Process collected data and generate insights" --thinking medium
# Step 3: Report generation
openclaw agent --agent main --session-id $SESSION_ID --message "Create comprehensive report with visualizations" --thinking high
hermes agent --agent main --session-id $SESSION_ID --message "Create comprehensive report with visualizations" --thinking high
```
### Multi-Agent Coordination
```bash
# Coordinator agent manages workflow
openclaw agent --agent coordinator --message "Coordinate data processing across multiple agents" --thinking high
hermes agent --agent coordinator --message "Coordinate data processing across multiple agents" --thinking high
# Worker agents execute specific tasks
openclaw agent --agent worker-1 --message "Process dataset A" --thinking medium
openclaw agent --agent worker-2 --message "Process dataset B" --thinking medium
hermes agent --agent worker-1 --message "Process dataset A" --thinking medium
hermes agent --agent worker-2 --message "Process dataset B" --thinking medium
# Aggregator combines results
openclaw agent --agent aggregator --message "Combine results from worker-1 and worker-2" --thinking high
hermes agent --agent aggregator --message "Combine results from worker-1 and worker-2" --thinking high
```
## Agent Types and Roles
@@ -101,28 +101,28 @@ openclaw agent --agent aggregator --message "Combine results from worker-1 and w
### Coordinator Agent
```bash
# Setup coordinator for complex workflows
openclaw agent --agent coordinator --message "Initialize as workflow coordinator. Manage task distribution, monitor progress, aggregate results." --thinking high
hermes agent --agent coordinator --message "Initialize as workflow coordinator. Manage task distribution, monitor progress, aggregate results." --thinking high
# Use coordinator for orchestration
openclaw agent --agent coordinator --message "Orchestrate data pipeline: extract → transform → load → validate" --thinking high
hermes agent --agent coordinator --message "Orchestrate data pipeline: extract → transform → load → validate" --thinking high
```
### Worker Agent
```bash
# Setup worker for specific tasks
openclaw agent --agent worker --message "Initialize as data processing worker. Execute assigned tasks efficiently." --thinking medium
hermes agent --agent worker --message "Initialize as data processing worker. Execute assigned tasks efficiently." --thinking medium
# Assign specific work
openclaw agent --agent worker --message "Process customer data file: /data/customers.json" --thinking medium
hermes agent --agent worker --message "Process customer data file: /data/customers.json" --thinking medium
```
### Monitor Agent
```bash
# Setup monitor for oversight
openclaw agent --agent monitor --message "Initialize as system monitor. Track performance, detect anomalies, report status." --thinking low
hermes agent --agent monitor --message "Initialize as system monitor. Track performance, detect anomalies, report status." --thinking low
# Continuous monitoring
openclaw agent --agent monitor --message "Monitor system health and report any issues" --thinking minimal
hermes agent --agent monitor --message "Monitor system health and report any issues" --thinking minimal
```
## Agent Workflows
@@ -132,16 +132,16 @@ openclaw agent --agent monitor --message "Monitor system health and report any i
SESSION_ID="data-pipeline-$(date +%s)"
# Phase 1: Data Extraction
openclaw agent --agent extractor --session-id $SESSION_ID --message "Extract data from sources" --thinking medium
hermes agent --agent extractor --session-id $SESSION_ID --message "Extract data from sources" --thinking medium
# Phase 2: Data Transformation
openclaw agent --agent transformer --session-id $SESSION_ID --message "Transform extracted data" --thinking medium
hermes agent --agent transformer --session-id $SESSION_ID --message "Transform extracted data" --thinking medium
# Phase 3: Data Loading
openclaw agent --agent loader --session-id $SESSION_ID --message "Load transformed data to destination" --thinking medium
hermes agent --agent loader --session-id $SESSION_ID --message "Load transformed data to destination" --thinking medium
# Phase 4: Validation
openclaw agent --agent validator --session-id $SESSION_ID --message "Validate loaded data integrity" --thinking high
hermes agent --agent validator --session-id $SESSION_ID --message "Validate loaded data integrity" --thinking high
```
### Monitoring Workflow
@@ -150,7 +150,7 @@ SESSION_ID="monitoring-$(date +%s)"
# Continuous monitoring loop
while true; do
openclaw agent --agent monitor --session-id $SESSION_ID --message "Check system health" --thinking minimal
hermes agent --agent monitor --session-id $SESSION_ID --message "Check system health" --thinking minimal
sleep 300 # Check every 5 minutes
done
```
@@ -160,13 +160,13 @@ done
SESSION_ID="analysis-$(date +%s)"
# Initial analysis
openclaw agent --agent analyst --session-id $SESSION_ID --message "Perform initial data analysis" --thinking high
hermes agent --agent analyst --session-id $SESSION_ID --message "Perform initial data analysis" --thinking high
# Deep dive analysis
openclaw agent --agent analyst --session-id $SESSION_ID --message "Deep dive into anomalies and patterns" --thinking high
hermes agent --agent analyst --session-id $SESSION_ID --message "Deep dive into anomalies and patterns" --thinking high
# Report generation
openclaw agent --agent analyst --session-id $SESSION_ID --message "Generate comprehensive analysis report" --thinking high
hermes agent --agent analyst --session-id $SESSION_ID --message "Generate comprehensive analysis report" --thinking high
```
## Agent Configuration
@@ -174,29 +174,29 @@ openclaw agent --agent analyst --session-id $SESSION_ID --message "Generate comp
### Agent Parameters
```bash
# Agent with specific parameters
openclaw agent --agent main --message "Process data" --thinking medium \
hermes agent --agent main --message "Process data" --thinking medium \
--parameters "input_format:json,output_format:csv,mode:batch"
# Agent with timeout
openclaw agent --agent main --message "Long running task" --thinking high \
hermes agent --agent main --message "Long running task" --thinking high \
--parameters "timeout:3600,retry_count:3"
# Agent with resource constraints
openclaw agent --agent main --message "Resource-intensive task" --thinking high \
hermes agent --agent main --message "Resource-intensive task" --thinking high \
--parameters "max_memory:4GB,max_cpu:2,max_duration:1800"
```
### Agent Context Management
```bash
# Set initial context
openclaw agent --agent main --message "Initialize with context: data_analysis_v2" --thinking low \
hermes agent --agent main --message "Initialize with context: data_analysis_v2" --thinking low \
--context "project:data_analysis,version:2.0,dataset:customer_data"
# Maintain context across calls
openclaw agent --agent main --session-id $SESSION_ID --message "Continue with previous context" --thinking medium
hermes agent --agent main --session-id $SESSION_ID --message "Continue with previous context" --thinking medium
# Update context
openclaw agent --agent main --session-id $SESSION_ID --message "Update context: new_phase" --thinking medium \
hermes agent --agent main --session-id $SESSION_ID --message "Update context: new_phase" --thinking medium \
--context-update "phase:processing,status:active"
```
@@ -205,11 +205,11 @@ openclaw agent --agent main --session-id $SESSION_ID --message "Update context:
### Cross-Agent Messaging
```bash
# Agent A sends message to Agent B
openclaw agent --agent agent-a --message "Send results to agent-b" --thinking medium \
hermes agent --agent agent-a --message "Send results to agent-b" --thinking medium \
--send-to "agent-b" --message-type "results"
# Agent B receives and processes
openclaw agent --agent agent-b --message "Process received results" --thinking medium \
hermes agent --agent agent-b --message "Process received results" --thinking medium \
--receive-from "agent-a"
```
@@ -219,14 +219,14 @@ openclaw agent --agent agent-b --message "Process received results" --thinking m
TEAM_ID="team-analytics-$(date +%s)"
# Team leader coordination
openclaw agent --agent team-lead --session-id $TEAM_ID --message "Coordinate team analytics workflow" --thinking high
hermes agent --agent team-lead --session-id $TEAM_ID --message "Coordinate team analytics workflow" --thinking high
# Team member tasks
openclaw agent --agent analyst-1 --session-id $TEAM_ID --message "Analyze customer segment A" --thinking high
openclaw agent --agent analyst-2 --session-id $TEAM_ID --message "Analyze customer segment B" --thinking high
hermes agent --agent analyst-1 --session-id $TEAM_ID --message "Analyze customer segment A" --thinking high
hermes agent --agent analyst-2 --session-id $TEAM_ID --message "Analyze customer segment B" --thinking high
# Team consolidation
openclaw agent --agent team-lead --session-id $TEAM_ID --message "Consolidate team analysis results" --thinking high
hermes agent --agent team-lead --session-id $TEAM_ID --message "Consolidate team analysis results" --thinking high
```
## Agent Error Handling
@@ -234,22 +234,22 @@ openclaw agent --agent team-lead --session-id $TEAM_ID --message "Consolidate te
### Error Recovery
```bash
# Agent with error handling
openclaw agent --agent main --message "Process data with error handling" --thinking medium \
hermes agent --agent main --message "Process data with error handling" --thinking medium \
--parameters "error_handling:retry_on_failure,max_retries:3,fallback_mode:graceful_degradation"
# Monitor agent errors
openclaw agent --agent monitor --message "Check for agent errors and report" --thinking low \
hermes agent --agent monitor --message "Check for agent errors and report" --thinking low \
--parameters "check_type:error_log,alert_threshold:5"
```
### Agent Debugging
```bash
# Debug mode
openclaw agent --agent main --message "Debug task execution" --thinking high \
hermes agent --agent main --message "Debug task execution" --thinking high \
--parameters "debug:true,log_level:verbose,trace_execution:true"
# Agent state inspection
openclaw agent --agent main --message "Report current state and context" --thinking low \
hermes agent --agent main --message "Report current state and context" --thinking low \
--parameters "report_type:state,include_context:true"
```
@@ -258,11 +258,11 @@ openclaw agent --agent main --message "Report current state and context" --think
### Efficient Agent Usage
```bash
# Batch processing
openclaw agent --agent processor --message "Process data in batches" --thinking medium \
hermes agent --agent processor --message "Process data in batches" --thinking medium \
--parameters "batch_size:100,parallel_processing:true"
# Resource optimization
openclaw agent --agent optimizer --message "Optimize resource usage" --thinking high \
hermes agent --agent optimizer --message "Optimize resource usage" --thinking high \
--parameters "memory_efficiency:true,cpu_optimization:true"
```
@@ -270,11 +270,11 @@ openclaw agent --agent optimizer --message "Optimize resource usage" --thinking
```bash
# Scale out work
for i in {1..5}; do
openclaw agent --agent worker-$i --message "Process batch $i" --thinking medium &
hermes agent --agent worker-$i --message "Process batch $i" --thinking medium &
done
# Scale in coordination
openclaw agent --agent coordinator --message "Coordinate scaled-out workers" --thinking high
hermes agent --agent coordinator --message "Coordinate scaled-out workers" --thinking high
```
## Agent Security
@@ -282,11 +282,11 @@ openclaw agent --agent coordinator --message "Coordinate scaled-out workers" --t
### Secure Agent Operations
```bash
# Agent with security constraints
openclaw agent --agent secure-agent --message "Process sensitive data" --thinking high \
hermes agent --agent secure-agent --message "Process sensitive data" --thinking high \
--parameters "security_level:high,data_encryption:true,access_log:true"
# Agent authentication
openclaw agent --agent authenticated-agent --message "Authenticated operation" --thinking medium \
hermes agent --agent authenticated-agent --message "Authenticated operation" --thinking medium \
--parameters "auth_required:true,token_expiry:3600"
```
@@ -295,11 +295,11 @@ openclaw agent --agent authenticated-agent --message "Authenticated operation" -
### Performance Monitoring
```bash
# Monitor agent performance
openclaw agent --agent monitor --message "Monitor agent performance metrics" --thinking low \
hermes agent --agent monitor --message "Monitor agent performance metrics" --thinking low \
--parameters "metrics:cpu,memory,tasks_per_second,error_rate"
# Agent analytics
openclaw agent --agent analytics --message "Generate agent performance report" --thinking medium \
hermes agent --agent analytics --message "Generate agent performance report" --thinking medium \
--parameters "report_type:performance,period:last_24h"
```
@@ -314,16 +314,16 @@ openclaw agent --agent analytics --message "Generate agent performance report" -
### Debug Commands
```bash
# Check agent status
openclaw status --agent all
hermes status --agent all
# Test agent communication
openclaw agent --agent main --message "Ping test" --thinking minimal
hermes agent --agent main --message "Ping test" --thinking minimal
# Check workspace
openclaw workspace --status
hermes workspace --status
# Verify agent configuration
openclaw config --show --agent main
hermes config --show --agent main
```
## Best Practices
@@ -352,13 +352,13 @@ openclaw config --show --agent main
- Monitor agent resource usage
- Implement proper session cleanup
This OpenClaw Agent Management skill provides the foundation for effective agent coordination, communication, and workflow orchestration across any domain or application.
This hermes Agent Management skill provides the foundation for effective agent coordination, communication, and workflow orchestration across any domain or application.
## Quick Links to Current Active Skills
- **OpenClaw Agent Communicator**: [../openclaw-agent-communicator.md](../openclaw-agent-communicator.md)
- **OpenClaw Session Manager**: [../openclaw-session-manager.md](../openclaw-session-manager.md)
- **OpenClaw Coordination Orchestrator**: [../openclaw-coordination-orchestrator.md](../openclaw-coordination-orchestrator.md)
- **OpenClaw Performance Optimizer**: [../openclaw-performance-optimizer.md](../openclaw-performance-optimizer.md)
- **OpenClaw Error Handler**: [../openclaw-error-handler.md](../openclaw-error-handler.md)
- **OpenClaw Agent Testing Skill**: [../openclaw-agent-testing-skill.md](../openclaw-agent-testing-skill.md)
- **hermes Agent Communicator**: [../hermes-agent-communicator.md](../hermes-agent-communicator.md)
- **hermes Session Manager**: [../hermes-session-manager.md](../hermes-session-manager.md)
- **hermes Coordination Orchestrator**: [../hermes-coordination-orchestrator.md](../hermes-coordination-orchestrator.md)
- **hermes Performance Optimizer**: [../hermes-performance-optimizer.md](../hermes-performance-optimizer.md)
- **hermes Error Handler**: [../hermes-error-handler.md](../hermes-error-handler.md)
- **hermes Agent Testing Skill**: [../hermes-agent-testing-skill.md](../hermes-agent-testing-skill.md)

4
.windsurf/skills/blockchain-troubleshoot-recovery.md
View File

@@ -379,8 +379,8 @@ NODE_URL=http://<aitbc1-ip>:8006 ./aitbc-cli blockchain height
## Related Skills
- [aitbc-node-coordinator](/aitbc-node-coordinator.md) - For cross-node coordination during recovery
- [openclaw-error-handler](/openclaw-error-handler.md) - For error handling and escalation
- [openclaw-coordination-orchestrator](/openclaw-coordination-orchestrator.md) - For multi-node recovery coordination
- [hermes-error-handler](/hermes-error-handler.md) - For error handling and escalation
- [hermes-coordination-orchestrator](/hermes-coordination-orchestrator.md) - For multi-node recovery coordination
## Related Workflows
- [Blockchain Communication Test](/workflows/blockchain-communication-test.md) - Testing workflow that triggers this skill

496
.windsurf/skills/hermes-agent.md Normal file
View File

@@ -0,0 +1,496 @@
# Hermes AI Agent Skill
## Overview
Hermes is an AI assistant with tool-calling capabilities that can interact with the AITBC system. It supports chat, session management, skills, plugins, and various integrations.
Hermes is installed on both aitbc and aitbc1 nodes in the multi-node AITBC deployment.
## Installation & Setup
```bash
# Run interactive setup wizard
hermes setup
# Check system status and dependencies
hermes doctor
# View configuration
hermes config
hermes config edit
# Select default model and provider
hermes model
```
## Basic Usage
### Interactive Chat
```bash
# Start interactive chat
hermes
# Single query mode
hermes chat -q "What is the blockchain height?"
# Resume most recent session
hermes -c
# Resume session by name
hermes -c "my project"
# Resume session by ID
hermes --resume <session_id>
```
### Model Selection
```bash
# Select default model
hermes model
# Override model for this invocation
hermes -m tencent/hy3-preview:free
# Override provider for this invocation
hermes --provider openrouter
# Current AITBC configuration: tencent/hy3-preview:free via OpenRouter
```
## Session Management
```bash
# List past sessions
hermes sessions list
# Interactive session picker
hermes sessions browse
# Rename session
hermes sessions rename <ID> <TITLE>
# Export session
hermes sessions export <ID>
# Delete session
hermes sessions delete <ID>
# Prune old sessions
hermes sessions prune
```
## Skills & Plugins
### Skills
```bash
# Search for skills
hermes skills search <query>
# Install a skill
hermes skills install <skill-name>
# List installed skills
hermes skills list
# Configure skill
hermes skills configure <skill-name>
# Remove skill
hermes skills remove <skill-name>
```
### Preload Skills for Session
```bash
# Preload specific skills
hermes -s skill1,skill2
# Repeat flag for multiple skills
hermes -s skill1 -s skill2
```
### Plugins
```bash
# List plugins
hermes plugins list
# Install plugin
hermes plugins install <plugin-name>
# Update plugin
hermes plugins update <plugin-name>
# Remove plugin
hermes plugins remove <plugin-name>
```
### Skill Curator
```bash
# Check curator status
hermes curator status
# Run curator (background skill maintenance)
hermes curator run
# Pause curator
hermes curator pause
# Pin a skill (prevent curator updates)
hermes curator pin <skill-name>
```
## Authentication
```bash
# Login to inference provider
hermes login
# Logout from provider
hermes logout
# Add pooled credential
hermes auth add <provider>
# List pooled credentials
hermes auth list
# Remove pooled credential
hermes auth remove <provider> <token>
# Clear exhaustion status for provider
hermes auth reset <provider>
```
## Fallback Providers
```bash
# Show fallback provider chain
hermes fallback list
# Add fallback provider
hermes fallback add
# Remove fallback provider
hermes fallback remove
```
## Configuration
```bash
# View configuration
hermes config
# Edit configuration in editor
hermes config edit
# Set configuration value
hermes config set model gpt-4
# Set configuration value with path
hermes config set inference.model anthropic/claude-sonnet-4.6
```
## Logs & Debugging
```bash
# View last 50 lines of agent.log
hermes logs
# Follow agent.log in real-time
hermes logs -f
# View errors only
hermes logs errors
# View logs from last hour
hermes logs --since 1h
# View logs from last day
hermes logs --since 1d
# Upload debug report for support
hermes debug share
# Dump setup summary
hermes dump
```
## Advanced Usage
### One-Shot Mode
```bash
# Send single prompt, print only response (no banner/spinner)
hermes -z "What is the blockchain height?"
# With model override
hermes -m anthropic/claude-sonnet-4.6 -z "Check blockchain status"
# With toolsets
hermes -t blockchain,wallet -z "Send 10 tokens"
```
### Git Worktree Mode
```bash
# Run in isolated git worktree (for parallel agents)
hermes -w
```
### Toolsets
```bash
# Enable specific toolsets for this invocation
hermes -t blockchain,wallet,marketplace
# With oneshot mode
hermes -t blockchain -z "Get block height"
```
### TUI Mode
```bash
# Launch modern TUI instead of classic REPL
hermes --tui
# Run TypeScript sources via tsx (dev mode)
hermes --tui --dev
```
## Special Flags
```bash
# Auto-approve shell hooks (for CI/headless)
hermes --accept-hooks
# Bypass all dangerous command approvals (use at your own risk)
hermes --yolo
# Include session ID in system prompt
hermes --pass-session-id
# Ignore user config (~/.hermes/config.yaml)
hermes --ignore-user-config
# Skip auto-injection of AGENTS.md, SOUL.md, .cursorrules, memory
hermes --ignore-rules
```
## Integrations
### Webhook Management
```bash
# Manage dynamic webhook subscriptions
hermes webhook
# View webhook help
hermes webhook --help
```
## MCP (Model Context Protocol)
```bash
# Manage MCP servers
hermes mcp
# Run Hermes as MCP server
hermes mcp serve
# List MCP servers
hermes mcp list
# Add MCP server
hermes mcp add <server-config>
```
## Profiles
```bash
# Manage profiles (multiple isolated Hermes instances)
hermes profile
# Create new profile
hermes profile create <name>
# Switch profile
hermes profile switch <name>
# List profiles
hermes profile list
# Delete profile
hermes profile delete <name>
```
## Backup & Restore
```bash
# Backup Hermes home directory to zip
hermes backup
# Restore Hermes backup from zip
hermes import <backup-file.zip>
```
## Gateway
```bash
# Run messaging gateway
hermes gateway
# Install gateway background service
hermes gateway install
# Gateway management
hermes gateway --help
```
## System Commands
```bash
# Show version
hermes version
# Update to latest version
hermes update
# Uninstall Hermes
hermes uninstall
# Print shell completion script
hermes completion bash
hermes completion zsh
hermes completion fish
```
## Environment Variables
```bash
# Set default model (AITBC uses tencent/hy3-preview:free)
export HERMES_INFERENCE_MODEL=tencent/hy3-preview:free
# Set default provider (AITBC uses OpenRouter)
export HERMES_INFERENCE_PROVIDER=openrouter
# Auto-accept hooks
export HERMES_ACCEPT_HOOKS=1
```
Note: Zsh completion is already installed on the AITBC nodes.
## AITBC-Specific Workflows
### Multi-Node Operations
Hermes runs on both aitbc and aitbc1 nodes in the multi-node AITBC deployment.
```bash
# On aitbc node
ssh aitbc
hermes -s blockchain -z "Check aitbc blockchain status"
# On aitbc1 node
ssh aitbc1
hermes -s blockchain -z "Check aitbc1 blockchain status"
# Cross-node sync verification
hermes -t blockchain -z "Verify sync between aitbc and aitbc1"
```
### Blockchain Operations with Hermes
```bash
# Preload blockchain-specific skills
hermes -s blockchain,wallet -z "Check blockchain status"
# Query blockchain state
hermes -t blockchain -z "What is the current block height?"
# Send transaction
hermes -t wallet -z "Send 10 tokens to recipient-address"
# List wallets
hermes -t wallet -z "List all wallets"
```
### AI Training with Hermes
```bash
# Preload AI skills
hermes -s ai-training,coordinator -z "Submit AI training job"
# Check job status
hermes -t ai -z "Check status of job job_123"
# List AI jobs
hermes -t ai -z "List all AI jobs"
```
### Marketplace Operations
```bash
# List GPU resources
hermes -t marketplace -z "List available GPUs"
# Place bid
hermes -t marketplace -z "Place bid on listing listing_123"
# Check orders
hermes -t marketplace -z "Check my orders"
```
## Troubleshooting
### Common Issues
**Hermes not responding:**
```bash
# Check system status
hermes doctor
# View logs
hermes logs -f
```
**Authentication issues:**
```bash
# Clear credentials and re-login
hermes logout
hermes login
# Check auth status
hermes auth list
```
**Skill not loading:**
```bash
# Check curator status
hermes curator status
# Reinstall skill
hermes skills remove <skill-name>
hermes skills install <skill-name>
```
## Best Practices
1. **Session Management**: Use descriptive session names for easy resumption
2. **Skill Selection**: Only preload relevant skills to reduce overhead
3. **One-Shot Mode**: Use `-z` for scripts and automation
4. **Logging**: Use `hermes logs -f` for real-time debugging
5. **Configuration**: Store sensitive credentials via `hermes auth` not in config files
6. **Fallbacks**: Configure fallback providers for reliability
7. **Profiles**: Use separate profiles for different projects
## Resources
- Hermes documentation: Check `hermes --help` for any command
- Configuration: `~/.hermes/config.yaml`
- Logs: `~/.hermes/logs/`
- Skills directory: `~/.hermes/skills/`

16
.windsurf/skills/openclaw-agent-communicator.md
View File

@@ -1,13 +1,13 @@
---
description: Atomic OpenClaw agent communication with deterministic message handling and response validation
title: openclaw-agent-communicator
description: Atomic hermes agent communication with deterministic message handling and response validation
title: hermes-agent-communicator
version: 1.1
---
# OpenClaw Agent Communicator
# hermes Agent Communicator
## Purpose
Handle OpenClaw agent message delivery, response processing, and communication validation with deterministic outcome tracking.
Handle hermes agent message delivery, response processing, and communication validation with deterministic outcome tracking.
## Activation
Trigger when user requests agent communication: message sending, response analysis, or communication validation.
@@ -63,7 +63,7 @@ Trigger when user requests agent communication: message sending, response analys
- Configure timeout handling
### 3. Execute
- Execute OpenClaw agent command
- Execute hermes agent command
- Capture agent response
- Measure response time
- Analyze response quality
@@ -83,8 +83,8 @@ Trigger when user requests agent communication: message sending, response analys
- **MUST** validate response format and content
## Environment Assumptions
- OpenClaw 2026.3.24+ installed and gateway running
- Agent workspace configured at `~/.openclaw/workspace/`
- hermes 2026.3.24+ installed and gateway running
- Agent workspace configured at `~/.hermes/workspace/`
- Network connectivity for agent communication
- Default agent available: "main"
- Session management functional
@@ -139,6 +139,6 @@ Send message to main agent with medium thinking level: "Analyze the current bloc
## Performance Notes
- **Execution Time**: 1-3 seconds for simple messages, 5-15 seconds for complex analysis
- **Memory Usage**: <100MB for agent communication
- **Network Requirements**: OpenClaw gateway connectivity
- **Network Requirements**: hermes gateway connectivity
- **Concurrency**: Safe for multiple simultaneous agent communications
- **Session Management**: Automatic context preservation across multiple messages

24
.windsurf/skills/openclaw-agent-testing-skill.md
View File

@@ -1,16 +1,16 @@
---
description: Atomic OpenClaw agent testing with deterministic communication validation and performance metrics
title: openclaw-agent-testing-skill
description: Atomic Hermes agent testing with deterministic communication validation and performance metrics
title: hermes-agent-testing-skill
version: 1.1
---
# OpenClaw Agent Testing Skill
# Hermes Agent Testing Skill
## Purpose
Test and validate OpenClaw agent functionality, communication patterns, session management, and performance with deterministic validation metrics.
Test and validate Hermes agent functionality, communication patterns, session management, and performance with deterministic validation metrics.
## Activation
Trigger when user requests OpenClaw agent testing: agent functionality validation, communication testing, session management testing, or agent performance analysis.
Trigger when user requests Hermes agent testing: agent functionality validation, communication testing, session management testing, or agent performance analysis.
## Input
```json
@@ -29,7 +29,7 @@ Trigger when user requests OpenClaw agent testing: agent functionality validatio
## Output
```json
{
"summary": "OpenClaw agent testing completed successfully",
"summary": "Hermes agent testing completed successfully",
"operation": "test-agent-communication|test-session-management|test-agent-performance|test-multi-agent|comprehensive",
"test_results": {
"agent_communication": "boolean",
@@ -73,7 +73,7 @@ Trigger when user requests OpenClaw agent testing: agent functionality validatio
### 1. Analyze
- Validate agent testing parameters and operation type
- Check OpenClaw service availability and health
- Check Hermes service availability and health
- Verify agent availability and status
- Assess testing scope and requirements
@@ -104,8 +104,8 @@ Trigger when user requests OpenClaw agent testing: agent functionality validatio
- **MUST** provide deterministic performance metrics
## Environment Assumptions
- OpenClaw 2026.3.24+ installed and gateway running
- Agent workspace configured at `~/.openclaw/workspace/`
- Hermes 2026.3.24+ installed and gateway running
- Agent workspace configured at `~/.hermes/workspace/`
- Network connectivity for agent communication
- Default agent available: "main"
- Session management functional
@@ -119,14 +119,14 @@ Trigger when user requests OpenClaw agent testing: agent functionality validatio
## Example Usage Prompt
```
Run comprehensive OpenClaw agent testing including communication, session management, performance, and multi-agent coordination validation
Run comprehensive Hermes agent testing including communication, session management, performance, and multi-agent coordination validation
```
## Expected Output Example
```json
{
"summary": "Comprehensive OpenClaw agent testing completed with all systems operational",
"summary": "Comprehensive Hermes agent testing completed with all systems operational",
"operation": "comprehensive",
"test_results": {
"agent_communication": true,
@@ -187,6 +187,6 @@ Run comprehensive OpenClaw agent testing including communication, session manage
## Performance Notes
- **Execution Time**: 5-15 seconds for basic tests, 30-90 seconds for comprehensive testing
- **Memory Usage**: <150MB for agent testing operations
- **Network Requirements**: OpenClaw gateway connectivity
- **Network Requirements**: Hermes gateway connectivity
- **Concurrency**: Safe for multiple simultaneous agent tests with different agents
- **Session Management**: Automatic session creation and context preservation testing

10
.windsurf/skills/openclaw-coordination-orchestrator.md
View File

@@ -1,13 +1,13 @@
---
description: Atomic OpenClaw multi-agent workflow coordination with deterministic outputs
title: openclaw-coordination-orchestrator
description: Atomic hermes multi-agent workflow coordination with deterministic outputs
title: hermes-coordination-orchestrator
version: 1.1
---
# OpenClaw Coordination Orchestrator
# hermes Coordination Orchestrator
## Purpose
Coordinate multi-agent workflows, manage agent task distribution, and orchestrate complex operations across multiple OpenClaw agents.
Coordinate multi-agent workflows, manage agent task distribution, and orchestrate complex operations across multiple hermes agents.
## Activation
Trigger when user requests multi-agent coordination: task distribution, workflow orchestration, agent collaboration, or parallel execution management.
@@ -77,7 +77,7 @@ Trigger when user requests multi-agent coordination: task distribution, workflow
- **MUST** respect agent capacity limits
## Environment Assumptions
- OpenClaw agents operational and accessible
- hermes agents operational and accessible
- Agent communication channels available
- Task queue system functional
- Agent status monitoring active

8
.windsurf/skills/openclaw-error-handler.md
View File

@@ -1,13 +1,13 @@
---
description: Atomic OpenClaw error detection and recovery procedures with deterministic outputs
title: openclaw-error-handler
description: Atomic hermes error detection and recovery procedures with deterministic outputs
title: hermes-error-handler
version: 1.1
---
# OpenClaw Error Handler
# hermes Error Handler
## Purpose
Detect, diagnose, and recover from errors in OpenClaw agent operations with systematic error handling and recovery procedures.
Detect, diagnose, and recover from errors in hermes agent operations with systematic error handling and recovery procedures.
## Activation
Trigger when user requests error handling: error diagnosis, recovery procedures, error analysis, or system health checks.

8
.windsurf/skills/openclaw-performance-optimizer.md
View File

@@ -1,13 +1,13 @@
---
description: Atomic OpenClaw agent performance tuning and optimization with deterministic outputs
title: openclaw-performance-optimizer
description: Atomic Hermes agent performance tuning and optimization with deterministic outputs
title: hermes-performance-optimizer
version: 1.1
---
# OpenClaw Performance Optimizer
# Hermes Performance Optimizer
## Purpose
Optimize agent performance, tune execution parameters, and improve efficiency for OpenClaw agents through systematic analysis and adjustment.
Optimize agent performance, tune execution parameters, and improve efficiency for Hermes agents through systematic analysis and adjustment.
## Activation
Trigger when user requests performance optimization: agent tuning, parameter adjustment, efficiency improvements, or performance benchmarking.

16
.windsurf/skills/openclaw-session-manager.md
View File

@@ -1,13 +1,13 @@
---
description: Atomic OpenClaw session management with deterministic context preservation and workflow coordination
title: openclaw-session-manager
description: Atomic hermes session management with deterministic context preservation and workflow coordination
title: hermes-session-manager
version: 1.1
---
# OpenClaw Session Manager
# hermes Session Manager
## Purpose
Create, manage, and optimize OpenClaw agent sessions with deterministic context preservation and workflow coordination.
Create, manage, and optimize hermes agent sessions with deterministic context preservation and workflow coordination.
## Activation
Trigger when user requests session operations: creation, management, context analysis, or session optimization.
@@ -63,7 +63,7 @@ Trigger when user requests session operations: creation, management, context ana
- Prepare optimization criteria
### 3. Execute
- Execute OpenClaw session operations
- Execute hermes session operations
- Monitor session health
- Track context preservation
- Analyze session performance
@@ -83,8 +83,8 @@ Trigger when user requests session operations: creation, management, context ana
- **MUST** track session resource usage
## Environment Assumptions
- OpenClaw 2026.3.24+ installed and gateway running
- Agent workspace configured at `~/.openclaw/workspace/`
- hermes 2026.3.24+ installed and gateway running
- Agent workspace configured at `~/.hermes/workspace/`
- Session storage functional
- Context preservation mechanisms operational
- Default session duration: 4 hours
@@ -145,6 +145,6 @@ Create a new session for main agent with context about blockchain optimization w
## Performance Notes
- **Execution Time**: 1-3 seconds for create/list, 5-15 seconds for analysis/optimization
- **Memory Usage**: <150MB for session management
- **Network Requirements**: OpenClaw gateway connectivity
- **Network Requirements**: hermes gateway connectivity
- **Concurrency**: Safe for multiple simultaneous sessions with different agents
- **Context Preservation**: Automatic context tracking and integrity validation

12
.windsurf/templates/agent-templates.md
View File

@@ -1,4 +1,4 @@
# OpenClaw AITBC Agent Templates
# Hermes AITBC Agent Templates
> **Canonical validation**: Use [`docs/scenarios/VALIDATION.md`](../../docs/scenarios/VALIDATION.md) with `scripts/workflow/44_comprehensive_multi_node_scenario.sh` when validating these templates.
@@ -27,7 +27,7 @@
"wallet": "aitbc-user",
"auto_transaction": true
},
"openclaw_config": {
"hermes_config": {
"model": "ollama/nemotron-3-super:cloud",
"workspace": "blockchain-monitor",
"routing": {
@@ -58,7 +58,7 @@
"profit_margin": 0.15,
"max_positions": 5
},
"openclaw_config": {
"hermes_config": {
"model": "ollama/nemotron-3-super:cloud",
"workspace": "marketplace-trader",
"routing": {
@@ -90,7 +90,7 @@
"data_retention": 86400,
"batch_processing": true
},
"openclaw_config": {
"hermes_config": {
"model": "ollama/nemotron-3-super:cloud",
"workspace": "blockchain-analyzer",
"routing": {
@@ -120,7 +120,7 @@
"auto_failover": true,
"health_checks": ["rpc", "sync", "transactions"]
},
"openclaw_config": {
"hermes_config": {
"model": "ollama/nemotron-3-super:cloud",
"workspace": "multi-node-coordinator",
"routing": {
@@ -153,7 +153,7 @@
"chain_id": "ait-mainnet",
"cross_node_routing": true
},
"openclaw_config": {
"hermes_config": {
"model": "ollama/nemotron-3-super:cloud",
"workspace": "blockchain-messaging",
"routing": {

4
.windsurf/templates/workflow-templates.md
View File

@@ -1,4 +1,4 @@
# OpenClaw AITBC Workflow Templates
# hermes AITBC Workflow Templates
> **Canonical validation**: For end-to-end node coverage, use [`docs/scenarios/VALIDATION.md`](../../docs/scenarios/VALIDATION.md) and `scripts/workflow/44_comprehensive_multi_node_scenario.sh`.
@@ -262,7 +262,7 @@ success_criteria:
## Agent Training and Learning Workflow
```yaml
name: agent-learning
description: Continuous learning and improvement for OpenClaw agents
description: Continuous learning and improvement for hermes agents
version: 1.0.0
schedule: "0 2 * * *" # Daily at 2 AM
steps:

76
.windsurf/workflows/OPENCLAW_MASTER_INDEX.md → .windsurf/workflows/HERMES_MASTER_INDEX.md
View File

@@ -1,21 +1,21 @@
---
description: Master index for OpenClaw workflows - links to all modules and provides navigation
title: OpenClaw Workflows - Master Index
description: Master index for hermes workflows - links to all modules and provides navigation
title: hermes Workflows - Master Index
version: 1.0
---
# OpenClaw Workflows - Master Index
# hermes Workflows - Master Index
This master index provides navigation to all OpenClaw agent workflows and documentation. Each workflow focuses on specific aspects of OpenClaw agent training, coordination, and testing.
This master index provides navigation to all hermes agent workflows and documentation. Each workflow focuses on specific aspects of hermes agent training, coordination, and testing.
## 📚 Module Overview
### 🎓 Agent Training Modules
#### Cross-Node Communication Training
**File**: `openclaw-cross-node-communication.md`
**File**: `hermes-cross-node-communication.md`
**Purpose**: Specialized training for agent-to-agent cross-node communication via AITBC blockchain
**Audience**: OpenClaw agents learning multi-node coordination
**Audience**: hermes agents learning multi-node coordination
**Prerequisites**: Stage 2 of Mastery Plan, both nodes synchronized
**Key Topics**:
@@ -28,21 +28,21 @@ This master index provides navigation to all OpenClaw agent workflows and docume
**Quick Start**:
```bash
cd /opt/aitbc/scripts/training
./openclaw_cross_node_comm.sh
./hermes_cross_node_comm.sh
```
---
### 🧪 Agent Testing Modules
#### Ollama GPU Provider Test (OpenClaw)
**File**: `ollama-gpu-test-openclaw.md`
**Purpose**: Complete end-to-end test for Ollama GPU inference jobs using OpenClaw agents
**Audience**: QA engineers, OpenClaw developers
**Prerequisites**: OpenClaw 2026.3.24+, all services running, enhanced CLI
#### Ollama GPU Provider Test (hermes)
**File**: `ollama-gpu-test-hermes.md`
**Purpose**: Complete end-to-end test for Ollama GPU inference jobs using hermes agents
**Audience**: QA engineers, hermes developers
**Prerequisites**: hermes 2026.3.24+, all services running, enhanced CLI
**Key Topics**:
- Environment validation with OpenClaw agents
- Environment validation with hermes agents
- Wallet setup and management
- Service health verification
- GPU test execution and monitoring
@@ -53,7 +53,7 @@ cd /opt/aitbc/scripts/training
**Quick Start**:
```bash
SESSION_ID="ollama-gpu-test-$(date +%s)"
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Initialize complete Ollama GPU test workflow" \
--thinking high
```
@@ -65,7 +65,7 @@ openclaw agent --agent test-coordinator --session-id $SESSION_ID \
#### Agent Coordination Plan Enhancement
**File**: `agent-coordination-enhancement.md`
**Purpose**: Advanced multi-agent communication patterns, distributed decision making, and scalable architectures
**Audience**: OpenClaw developers, system architects
**Audience**: hermes developers, system architects
**Prerequisites**: Advanced AI Teaching Plan completed
**Key Topics**:
@@ -79,7 +79,7 @@ openclaw agent --agent test-coordinator --session-id $SESSION_ID \
**Quick Start**:
```bash
SESSION_ID="coordination-$(date +%s)"
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "BROADCAST: System-wide resource optimization initiated" \
--thinking high
```
@@ -96,12 +96,12 @@ Cross-Node Communication Training (Foundation)
## 🚀 Recommended Learning Path
### For New OpenClaw Users
### For New hermes Users
1. **Cross-Node Communication Training** - Learn basic multi-node messaging
2. **Ollama GPU Provider Test** - Practice agent-based testing
3. **Agent Coordination Enhancement** - Master advanced coordination
### For OpenClaw Developers
### For hermes Developers
1. **Cross-Node Communication Training** - Understand multi-node architecture
2. **Agent Coordination Enhancement** - Master coordination patterns
3. **Ollama GPU Provider Test** - Learn testing methodology
@@ -127,7 +127,7 @@ Cross-Node Communication Training (Foundation)
| Role | Essential Modules |
|---|---|
| **OpenClaw Developer** | Cross-Node Communication Training, Agent Coordination Enhancement |
| **hermes Developer** | Cross-Node Communication Training, Agent Coordination Enhancement |
| **QA Engineer** | Ollama GPU Provider Test, Cross-Node Communication Training |
| **System Architect** | Agent Coordination Enhancement, Cross-Node Communication Training |
| **DevOps Engineer** | Ollama GPU Provider Test, Agent Coordination Enhancement |
@@ -147,7 +147,7 @@ Cross-Node Communication Training (Foundation)
```bash
# Register agent on genesis node
NODE_URL=http://10.1.223.40:8006 ./aitbc-cli agent create \
--name "openclaw-genesis-commander" \
--name "hermes-genesis-commander" \
--description "Primary coordinator agent" \
--verification full
@@ -161,12 +161,12 @@ NODE_URL=http://10.1.223.40:8006 ./aitbc-cli agent message \
```bash
# Initialize test coordinator
SESSION_ID="ollama-test-$(date +%s)"
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Initialize Ollama GPU provider test workflow" \
--thinking high
# Submit inference job
openclaw agent --agent client-agent --session-id $SESSION_ID \
hermes agent --agent client-agent --session-id $SESSION_ID \
--message "Submit Ollama GPU inference job" \
--parameters "prompt:What is the capital of France?,model:llama3.2:latest"
```
@@ -175,24 +175,24 @@ openclaw agent --agent client-agent --session-id $SESSION_ID \
```bash
# Hierarchical communication
SESSION_ID="hierarchy-$(date +%s)"
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "Broadcast: Execute distributed AI workflow" \
--thinking high
# Consensus voting
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "VOTE $PROPOSAL_ID: YES - Dynamic allocation optimizes AI performance" \
--thinking medium
```
## 📊 System Overview
### OpenClaw Architecture
### hermes Architecture
```
OpenClaw Agent Ecosystem:
hermes Agent Ecosystem:
├── Genesis Node (aitbc) - Primary development server
├── Follower Node (aitbc1) - Secondary node
├── Agent Gateway - OpenClaw communication layer
├── Agent Gateway - hermes communication layer
├── Blockchain Messaging - Transaction-based agent communication
├── Smart Contracts - Agent messaging and governance
├── GPU Services - Ollama inference and resource management
@@ -200,7 +200,7 @@ OpenClaw Agent Ecosystem:
```
### Key Components
- **Agent Gateway**: OpenClaw communication and coordination
- **Agent Gateway**: hermes communication and coordination
- **Blockchain Messaging**: Transaction-based cross-node communication
- **Smart Contracts**: Agent messaging, reputation, and governance
- **GPU Services**: Ollama inference, resource allocation
@@ -237,7 +237,7 @@ OpenClaw Agent Ecosystem:
| Coordination timeout | Agent Coordination Enhancement | Check agent gateway, session management |
### Emergency Procedures
1. **Agent Recovery**: Restart OpenClaw gateway, check agent status
1. **Agent Recovery**: Restart hermes gateway, check agent status
2. **Network Recovery**: Check node connectivity, restart P2P service
3. **Blockchain Recovery**: Check node sync, verify transaction pool
4. **Service Recovery**: Restart Agent Coordinator, Ollama, GPU miner
@@ -245,20 +245,20 @@ OpenClaw Agent Ecosystem:
## 📚 Additional Resources
### Documentation Files
- **OpenClaw Agent Capabilities**: `docs/openclaw/OPENCLAW_AGENT_CAPABILITIES_ADVANCED.md`
- **Agent Communication Guide**: `docs/openclaw/guides/openclaw_agent_fix_summary.md`
- **Messaging Implementation**: `docs/openclaw/guides/openclaw_messaging_implementation_guide.md`
- **Cross-Node Communication**: `docs/openclaw/guides/openclaw_cross_node_communication.md`
- **hermes Agent Capabilities**: `docs/hermes/HERMES_AGENT_CAPABILITIES_ADVANCED.md`
- **Agent Communication Guide**: `docs/hermes/guides/hermes_agent_fix_summary.md`
- **Messaging Implementation**: `docs/hermes/guides/hermes_messaging_implementation_guide.md`
- **Cross-Node Communication**: `docs/hermes/guides/hermes_cross_node_communication.md`
### Workflow Scripts
- **Cross-Node Training**: `/opt/aitbc/scripts/training/openclaw_cross_node_comm.sh`
- **Ollama GPU Test**: `ollama_gpu_test_openclaw.sh`
- **Agent Communication Fix**: `/opt/aitbc/scripts/workflow-openclaw/fix_agent_communication.sh`
- **Cross-Node Training**: `/opt/aitbc/scripts/training/hermes_cross_node_comm.sh`
- **Ollama GPU Test**: `ollama_gpu_test_hermes.sh`
- **Agent Communication Fix**: `/opt/aitbc/scripts/workflow-hermes/fix_agent_communication.sh`
## 🔄 Version History
### v1.0 (Current)
- Created master index for OpenClaw workflows
- Created master index for hermes workflows
- Organized workflows by training, testing, and coordination
- Added navigation and learning paths
- Included quick reference commands and troubleshooting
@@ -281,6 +281,6 @@ OpenClaw Agent Ecosystem:
---
**Note**: This master index is your starting point for all OpenClaw workflow operations. Choose the appropriate module based on your current task and expertise level.
**Note**: This master index is your starting point for all hermes workflow operations. Choose the appropriate module based on your current task and expertise level.
For immediate help, see the **Cross-Node Communication Training** module for foundational knowledge, or the **Agent Coordination Enhancement** module for advanced patterns.

12
.windsurf/workflows/MULTI_NODE_MASTER_INDEX.md
View File

@@ -416,12 +416,12 @@ Two-Node AITBC Blockchain:
## 📚 Additional Resources
### Documentation Files
- **OpenClaw Agent Communicator**: `../skills/openclaw-agent-communicator.md`
- **OpenClaw Coordination Orchestrator**: `../skills/openclaw-coordination-orchestrator.md`
- **OpenClaw Session Manager**: `../skills/openclaw-session-manager.md`
- **OpenClaw Agent Testing**: `../skills/openclaw-agent-testing-skill.md`
- **OpenClaw Error Handler**: `../skills/openclaw-error-handler.md`
- **OpenClaw Performance Optimizer**: `../skills/openclaw-performance-optimizer.md`
- **hermes Agent Communicator**: `../skills/hermes-agent-communicator.md`
- **hermes Coordination Orchestrator**: `../skills/hermes-coordination-orchestrator.md`
- **hermes Session Manager**: `../skills/hermes-session-manager.md`
- **hermes Agent Testing**: `../skills/hermes-agent-testing-skill.md`
- **hermes Error Handler**: `../skills/hermes-error-handler.md`
- **hermes Performance Optimizer**: `../skills/hermes-performance-optimizer.md`
### External Resources
- **AITBC Repository**: GitHub repository

94
.windsurf/workflows/agent-coordination-enhancement.md
View File

@@ -6,7 +6,7 @@ version: 1.0
# Agent Coordination Plan Enhancement
This document outlines advanced multi-agent communication patterns, distributed decision making mechanisms, and scalable agent architectures for the OpenClaw agent ecosystem.
This document outlines advanced multi-agent communication patterns, distributed decision making mechanisms, and scalable agent architectures for the hermes agent ecosystem.
## 🎯 Objectives
@@ -41,16 +41,16 @@ CoordinatorAgent (Level 1)
SESSION_ID="hierarchy-$(date +%s)"
# Level 1: Coordinator broadcasts to Level 2
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "Broadcast: Execute distributed AI workflow across all Level 2 agents" \
--thinking high
# Level 2: Agents respond to coordinator
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "Response to Coordinator: Ready for AI workflow execution with resource optimization" \
--thinking medium
openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
hermes agent --agent FollowerAgent --session-id $SESSION_ID \
--message "Response to Coordinator: Ready for distributed task participation" \
--thinking medium
```
@@ -78,16 +78,16 @@ GenesisAgent ←→ FollowerAgent
SESSION_ID="p2p-$(date +%s)"
# Direct agent-to-agent communication
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "P2P to FollowerAgent: Coordinate resource allocation for AI job batch" \
--thinking medium
openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
hermes agent --agent FollowerAgent --session-id $SESSION_ID \
--message "P2P to GenesisAgent: Confirm resource availability and scheduling" \
--thinking medium
# Cross-agent resource sharing
openclaw agent --agent AIResourceAgent --session-id $SESSION_ID \
hermes agent --agent AIResourceAgent --session-id $SESSION_ID \
--message "P2P to MultiModalAgent: Share GPU allocation for multi-modal processing" \
--thinking low
```
@@ -106,13 +106,13 @@ openclaw agent --agent AIResourceAgent --session-id $SESSION_ID \
SESSION_ID="broadcast-$(date +%s)"
# Coordinator broadcasts to all agents
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "BROADCAST: System-wide resource optimization initiated - all agents participate" \
--thinking high
# Agents acknowledge broadcast
for agent in GenesisAgent FollowerAgent AIResourceAgent MultiModalAgent; do
openclaw agent --agent $agent --session-id $SESSION_ID \
hermes agent --agent $agent --session-id $SESSION_ID \
--message "ACK: Received broadcast, initiating optimization protocols" \
--thinking low &
done
@@ -138,7 +138,7 @@ SESSION_ID="voting-$(date +%s)"
PROPOSAL_ID="resource-strategy-$(date +%s)"
# Coordinator presents proposal
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "VOTE PROPOSAL $PROPOSAL_ID: Implement dynamic GPU allocation with 70% utilization target" \
--thinking high
@@ -147,19 +147,19 @@ echo "Collecting votes..."
VOTES=()
# Genesis Agent vote
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "VOTE $PROPOSAL_ID: YES - Dynamic allocation optimizes AI performance" \
--thinking medium &
VOTES+=("GenesisAgent:YES")
# Follower Agent vote
openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
hermes agent --agent FollowerAgent --session-id $SESSION_ID \
--message "VOTE $PROPOSAL_ID: YES - Improves resource utilization" \
--thinking medium &
VOTES+=("FollowerAgent:YES")
# AI Resource Agent vote
openclaw agent --agent AIResourceAgent --session-id $SESSION_ID \
hermes agent --agent AIResourceAgent --session-id $SESSION_ID \
--message "VOTE $PROPOSAL_ID: YES - Aligns with optimization goals" \
--thinking medium &
VOTES+=("AIResourceAgent:YES")
@@ -172,7 +172,7 @@ TOTAL_COUNT=${#VOTES[@]}
if [ $YES_COUNT -gt $((TOTAL_COUNT / 2)) ]; then
echo "✅ PROPOSAL $PROPOSAL_ID APPROVED: $YES_COUNT/$TOTAL_COUNT votes"
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "DECISION: Proposal $PROPOSAL_ID APPROVED - Implementing dynamic GPU allocation" \
--thinking high
else
@@ -194,23 +194,23 @@ fi
SESSION_ID="weighted-$(date +%s)"
# Decision: AI model selection for complex task
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "WEIGHTED DECISION: Select optimal AI model for medical diagnosis pipeline" \
--thinking high
# Agents provide weighted recommendations
# Genesis Agent (AI Operations Expertise - Weight: 3)
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "RECOMMENDATION: ensemble_model (confidence: 0.9, weight: 3) - Best for accuracy" \
--thinking high &
# MultiModal Agent (Multi-Modal Expertise - Weight: 2)
openclaw agent --agent MultiModalAgent --session-id $SESSION_ID \
hermes agent --agent MultiModalAgent --session-id $SESSION_ID \
--message "RECOMMENDATION: multimodal_model (confidence: 0.8, weight: 2) - Handles multiple data types" \
--thinking high &
# AI Resource Agent (Resource Expertise - Weight: 1)
openclaw agent --agent AIResourceAgent --session-id $SESSION_ID \
hermes agent --agent AIResourceAgent --session-id $SESSION_ID \
--message "RECOMMENDATION: efficient_model (confidence: 0.7, weight: 1) - Best resource utilization" \
--thinking medium &
@@ -223,7 +223,7 @@ echo "Calculating weighted decision..."
# efficient_model: 0.7 * 1 = 0.7
# Winner: ensemble_model with highest weighted score
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "WEIGHTED DECISION: ensemble_model selected (weighted score: 2.7) - Highest confidence-weighted combination" \
--thinking high
```
@@ -242,30 +242,30 @@ openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
SESSION_ID="problem-solving-$(date +%s)"
# Complex problem: Optimize AI service pricing strategy
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "PROBLEM SOLVING: Optimize AI service pricing for maximum profitability and utilization" \
--thinking high
# Agents analyze different aspects
# Genesis Agent: Technical feasibility
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "ANALYSIS: Technical constraints suggest pricing range $50-200 per inference job" \
--thinking high &
# Follower Agent: Market analysis
openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
hermes agent --agent FollowerAgent --session-id $SESSION_ID \
--message "ANALYSIS: Market research shows competitive pricing at $80-150 per job" \
--thinking medium &
# AI Resource Agent: Cost analysis
openclaw agent --agent AIResourceAgent --session-id $SESSION_ID \
hermes agent --agent AIResourceAgent --session-id $SESSION_ID \
--message "ANALYSIS: Resource costs indicate minimum $60 per job for profitability" \
--thinking medium &
wait
# Coordinator synthesizes solution
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "SYNTHESIS: Optimal pricing strategy $80-120 range with dynamic adjustment based on demand" \
--thinking high
```
@@ -287,29 +287,29 @@ SESSION_ID="microservices-$(date +%s)"
# Specialized agents with specific responsibilities
# AI Service Agent - Handles AI job processing
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "SERVICE: Processing AI job queue with 5 concurrent jobs" \
--thinking medium &
# Resource Agent - Manages resource allocation
openclaw agent --agent AIResourceAgent --session-id $SESSION_ID \
hermes agent --agent AIResourceAgent --session-id $SESSION_ID \
--message "SERVICE: Allocating GPU resources with 85% utilization target" \
--thinking medium &
# Monitoring Agent - Tracks system health
openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
hermes agent --agent FollowerAgent --session-id $SESSION_ID \
--message "SERVICE: Monitoring system health with 99.9% uptime target" \
--thinking low &
# Analytics Agent - Provides insights
openclaw agent --agent MultiModalAgent --session-id $SESSION_ID \
hermes agent --agent MultiModalAgent --session-id $SESSION_ID \
--message "SERVICE: Analyzing performance metrics and optimization opportunities" \
--thinking medium &
wait
# Service orchestration
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "ORCHESTRATION: Coordinating 4 microservices for optimal system performance" \
--thinking high
```
@@ -328,27 +328,27 @@ openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
SESSION_ID="load-balancing-$(date +%s)"
# Coordinator monitors agent loads
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "LOAD BALANCE: Monitoring agent loads and redistributing tasks" \
--thinking high
# Agents report current load
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "LOAD REPORT: Current load 75% - capacity for 5 more AI jobs" \
--thinking low &
openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
hermes agent --agent FollowerAgent --session-id $SESSION_ID \
--message "LOAD REPORT: Current load 45% - capacity for 10 more tasks" \
--thinking low &
openclaw agent --agent AIResourceAgent --session-id $SESSION_ID \
hermes agent --agent AIResourceAgent --session-id $SESSION_ID \
--message "LOAD REPORT: Current load 60% - capacity for resource optimization tasks" \
--thinking low &
wait
# Coordinator redistributes load
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "REDISTRIBUTION: Routing new tasks to FollowerAgent (45% load) for optimal balance" \
--thinking high
```
@@ -368,24 +368,24 @@ SESSION_ID="federation-$(date +%s)"
# Local agent groups with coordination
# Group 1: AI Processing Cluster
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "FEDERATION: AI Processing Cluster - handling complex AI workflows" \
--thinking medium &
# Group 2: Resource Management Cluster
openclaw agent --agent AIResourceAgent --session-id $SESSION_ID \
hermes agent --agent AIResourceAgent --session-id $SESSION_ID \
--message "FEDERATION: Resource Management Cluster - optimizing system resources" \
--thinking medium &
# Group 3: Monitoring Cluster
openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
hermes agent --agent FollowerAgent --session-id $SESSION_ID \
--message "FEDERATION: Monitoring Cluster - ensuring system health and reliability" \
--thinking low &
wait
# Inter-federation coordination
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "FEDERATION COORDINATION: Coordinating 3 agent clusters for system-wide optimization" \
--thinking high
```
@@ -406,25 +406,25 @@ openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
SESSION_ID="orchestration-$(date +%s)"
# Step 1: Task decomposition
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "ORCHESTRATION: Decomposing complex AI pipeline into 5 subtasks for agent allocation" \
--thinking high
# Step 2: Task assignment
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "ASSIGNMENT: Task 1->GenesisAgent, Task 2->MultiModalAgent, Task 3->AIResourceAgent, Task 4->FollowerAgent, Task 5->CoordinatorAgent" \
--thinking high
# Step 3: Parallel execution
for agent in GenesisAgent MultiModalAgent AIResourceAgent FollowerAgent; do
openclaw agent --agent $agent --session-id $SESSION_ID \
hermes agent --agent $agent --session-id $SESSION_ID \
--message "EXECUTION: Starting assigned task with parallel processing" \
--thinking medium &
done
wait
# Step 4: Result aggregation
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "AGGREGATION: Collecting results from all agents for final synthesis" \
--thinking high
```
@@ -437,18 +437,18 @@ openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
SESSION_ID="adaptive-$(date +%s)"
# Monitor system conditions
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "MONITORING: System load at 85% - activating adaptive coordination protocols" \
--thinking high
# Adjust coordination strategy
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "ADAPTATION: Switching from centralized to distributed coordination for load balancing" \
--thinking high
# Agents adapt to new coordination
for agent in GenesisAgent FollowerAgent AIResourceAgent MultiModalAgent; do
openclaw agent --agent $agent --session-id $SESSION_ID \
hermes agent --agent $agent --session-id $SESSION_ID \
--message "ADAPTATION: Adjusting to distributed coordination mode" \
--thinking medium &
done
@@ -464,7 +464,7 @@ SESSION_ID="metrics-$(date +%s)"
# Measure message latency
start_time=$(date +%s.%N)
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "LATENCY TEST: Measuring communication performance" \
--thinking low
end_time=$(date +%s.%N)
@@ -474,7 +474,7 @@ echo "Message latency: ${latency}s"
# Monitor message throughput
echo "Testing message throughput..."
for i in {1..10}; do
openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
hermes agent --agent FollowerAgent --session-id $SESSION_ID \
-message "THROUGHPUT TEST $i" \
--thinking low &
done

6
.windsurf/workflows/aitbc-system-architecture-audit.md
View File

@@ -331,7 +331,7 @@ echo "=== 9. SYSTEM DIRECTORY CREATION ==="
echo "Creating Data Directories:"
mkdir -p /var/lib/aitbc/data/blockchain
mkdir -p /var/lib/aitbc/data/marketplace
mkdir -p /var/lib/aitbc/data/openclaw
mkdir -p /var/lib/aitbc/data/hermes
mkdir -p /var/lib/aitbc/data/coordinator
mkdir -p /var/lib/aitbc/data/exchange
mkdir -p /var/lib/aitbc/data/registry
@@ -341,7 +341,7 @@ echo "✅ Data directories created"
echo "Creating Log Directories:"
mkdir -p /var/log/aitbc/production/blockchain
mkdir -p /var/log/aitbc/production/marketplace
mkdir -p /var/log/aitbc/production/openclaw
mkdir -p /var/log/aitbc/production/hermes
mkdir -p /var/log/aitbc/production/services
mkdir -p /var/log/aitbc/production/errors
mkdir -p /var/log/aitbc/repository-logs
@@ -419,7 +419,7 @@ echo "✅ SystemD reloaded"
```bash
# Restart AITBC services
echo "=== 12. SERVICE RESTART ==="
services=("aitbc-marketplace.service" "aitbc-mining-blockchain.service" "aitbc-openclaw-ai.service" "aitbc-blockchain-node.service" "aitbc-blockchain-rpc.service")
services=("aitbc-marketplace.service" "aitbc-mining-blockchain.service" "aitbc-hermes-ai.service" "aitbc-blockchain-node.service" "aitbc-blockchain-rpc.service")
for service in "${services[@]}"; do
echo "Restarting $service..."

10
.windsurf/workflows/archive/ollama-gpu-test.md
View File

@@ -8,12 +8,12 @@ This workflow executes the complete end-to-end test for Ollama GPU inference job
## Current Active Skill Mapping
This archived workflow maps to these active OpenClaw skills when you need agent coordination or validation support:
This archived workflow maps to these active hermes skills when you need agent coordination or validation support:
- **`openclaw-agent-testing-skill.md`** — agent communication validation and performance testing
- **`openclaw-agent-communicator.md`** — agent message handling and responses
- **`openclaw-coordination-orchestrator.md`** — multi-agent workflow coordination
- **`openclaw-session-manager.md`** — session creation and context management
- **`hermes-agent-testing-skill.md`** — agent communication validation and performance testing
- **`hermes-agent-communicator.md`** — agent message handling and responses
- **`hermes-coordination-orchestrator.md`** — multi-agent workflow coordination
- **`hermes-session-manager.md`** — session creation and context management
## Prerequisites

2
.windsurf/workflows/archive/test-basic.md
View File

@@ -310,4 +310,4 @@ sudo systemctl restart aitbc-blockchain
---
**Dependencies**: None (base module)
**Next Module**: [OpenClaw Agent Testing](test-openclaw-agents.md) or [AI Operations Testing](test-ai-operations.md)
**Next Module**: [hermes Agent Testing](test-hermes-agents.md) or [AI Operations Testing](test-ai-operations.md)

148
.windsurf/workflows/archive/test-openclaw-agents.md
View File

@@ -1,51 +1,51 @@
---
description: OpenClaw agent functionality and coordination testing module
title: OpenClaw Agent Testing Module
description: hermes agent functionality and coordination testing module
title: hermes Agent Testing Module
version: 1.0
---
# OpenClaw Agent Testing Module
# hermes Agent Testing Module
This module covers OpenClaw agent functionality testing, multi-agent coordination, session management, and agent workflow validation.
This module covers hermes agent functionality testing, multi-agent coordination, session management, and agent workflow validation.
## Current Active Skill Mapping
This archived workflow maps to these active split skill files:
- **`openclaw-agent-testing-skill.md`** — agent communication validation and performance testing
- **`openclaw-agent-communicator.md`** — agent message handling and responses
- **`openclaw-session-manager.md`** — session creation and context management
- **`openclaw-coordination-orchestrator.md`** — multi-agent workflow coordination
- **`openclaw-performance-optimizer.md`** — agent performance tuning and optimization
- **`hermes-agent-testing-skill.md`** — agent communication validation and performance testing
- **`hermes-agent-communicator.md`** — agent message handling and responses
- **`hermes-session-manager.md`** — session creation and context management
- **`hermes-coordination-orchestrator.md`** — multi-agent workflow coordination
- **`hermes-performance-optimizer.md`** — agent performance tuning and optimization
## Prerequisites
### Required Setup
- Working directory: `/opt/aitbc`
- OpenClaw 2026.3.24+ installed
- OpenClaw gateway running
- hermes 2026.3.24+ installed
- hermes gateway running
- Basic Testing Module completed
### Environment Setup
```bash
cd /opt/aitbc
source venv/bin/activate
openclaw --version
openclaw gateway status
hermes --version
hermes gateway status
```
## 1. OpenClaw Agent Basic Testing
## 1. hermes Agent Basic Testing
### Agent Registration and Status
```bash
# Check OpenClaw gateway status
openclaw gateway status
# Check hermes gateway status
hermes gateway status
# List available agents
openclaw agent list
hermes agent list
# Check agent capabilities
openclaw agent --agent GenesisAgent --session-id test --message "Status check" --thinking low
hermes agent --agent GenesisAgent --session-id test --message "Status check" --thinking low
```
### Expected Results
@@ -55,14 +55,14 @@ openclaw agent --agent GenesisAgent --session-id test --message "Status check" -
### Troubleshooting Agent Issues
```bash
# Restart OpenClaw gateway
sudo systemctl restart openclaw-gateway
# Restart hermes gateway
sudo systemctl restart hermes-gateway
# Check gateway logs
sudo journalctl -u openclaw-gateway -f
sudo journalctl -u hermes-gateway -f
# Verify agent configuration
openclaw config show
hermes config show
```
## 2. Single Agent Testing
@@ -73,16 +73,16 @@ openclaw config show
SESSION_ID="genesis-test-$(date +%s)"
echo "Testing Genesis Agent with minimal thinking..."
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Test message - minimal thinking" --thinking minimal
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Test message - minimal thinking" --thinking minimal
echo "Testing Genesis Agent with low thinking..."
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Test message - low thinking" --thinking low
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Test message - low thinking" --thinking low
echo "Testing Genesis Agent with medium thinking..."
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Test message - medium thinking" --thinking medium
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Test message - medium thinking" --thinking medium
echo "Testing Genesis Agent with high thinking..."
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Test message - high thinking" --thinking high
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Test message - high thinking" --thinking high
```
### Follower Agent Testing
@@ -91,10 +91,10 @@ openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Test mes
SESSION_ID="follower-test-$(date +%s)"
echo "Testing Follower Agent..."
openclaw agent --agent FollowerAgent --session-id $SESSION_ID --message "Test follower agent response" --thinking low
hermes agent --agent FollowerAgent --session-id $SESSION_ID --message "Test follower agent response" --thinking low
# Test follower agent coordination
openclaw agent --agent FollowerAgent --session-id $SESSION_ID --message "Coordinate with genesis node" --thinking medium
hermes agent --agent FollowerAgent --session-id $SESSION_ID --message "Coordinate with genesis node" --thinking medium
```
### Coordinator Agent Testing
@@ -103,10 +103,10 @@ openclaw agent --agent FollowerAgent --session-id $SESSION_ID --message "Coordin
SESSION_ID="coordinator-test-$(date +%s)"
echo "Testing Coordinator Agent..."
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID --message "Test coordination capabilities" --thinking high
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID --message "Test coordination capabilities" --thinking high
# Test multi-agent coordination
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID --message "Coordinate multi-agent workflow" --thinking high
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID --message "Coordinate multi-agent workflow" --thinking high
```
## 3. Multi-Agent Coordination Testing
@@ -117,13 +117,13 @@ openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID --message "Coor
SESSION_ID="cross-agent-$(date +%s)"
# Genesis agent initiates
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Initiating cross-agent coordination test" --thinking high
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Initiating cross-agent coordination test" --thinking high
# Follower agent responds
openclaw agent --agent FollowerAgent --session-id $SESSION_ID --message "Responding to genesis agent coordination" --thinking medium
hermes agent --agent FollowerAgent --session-id $SESSION_ID --message "Responding to genesis agent coordination" --thinking medium
# Coordinator agent orchestrates
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID --message "Orchestrating multi-agent coordination" --thinking high
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID --message "Orchestrating multi-agent coordination" --thinking high
```
### Session Management Testing
@@ -132,12 +132,12 @@ openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID --message "Orch
SESSION_ID="session-test-$(date +%s)"
# Multiple messages in same session
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "First message in session" --thinking low
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Second message in session" --thinking low
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Third message in session" --thinking low
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "First message in session" --thinking low
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Second message in session" --thinking low
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Third message in session" --thinking low
# Test session with different agents
openclaw agent --agent FollowerAgent --session-id $SESSION_ID --message "Follower response in same session" --thinking medium
hermes agent --agent FollowerAgent --session-id $SESSION_ID --message "Follower response in same session" --thinking medium
```
## 4. Advanced Agent Capabilities Testing
@@ -148,17 +148,17 @@ openclaw agent --agent FollowerAgent --session-id $SESSION_ID --message "Followe
SESSION_ID="ai-workflow-$(date +%s)"
# Genesis agent designs complex AI pipeline
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "Design complex AI pipeline for medical diagnosis with parallel processing and error handling" \
--thinking high
# Follower agent participates in pipeline
openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
hermes agent --agent FollowerAgent --session-id $SESSION_ID \
--message "Participate in complex AI pipeline execution with resource monitoring" \
--thinking medium
# Coordinator agent orchestrates workflow
openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
hermes agent --agent CoordinatorAgent --session-id $SESSION_ID \
--message "Orchestrate complex AI pipeline execution across multiple agents" \
--thinking high
```
@@ -169,12 +169,12 @@ openclaw agent --agent CoordinatorAgent --session-id $SESSION_ID \
SESSION_ID="multimodal-$(date +%s)"
# Genesis agent designs multi-modal system
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "Design multi-modal AI system for customer feedback analysis with cross-modal attention" \
--thinking high
# Follower agent handles specific modality
openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
hermes agent --agent FollowerAgent --session-id $SESSION_ID \
--message "Handle text analysis modality in multi-modal AI system" \
--thinking medium
```
@@ -185,12 +185,12 @@ openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
SESSION_ID="resource-opt-$(date +%s)"
# Genesis agent optimizes resources
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "Optimize GPU resource allocation for AI service provider with demand forecasting" \
--thinking high
# Follower agent monitors resources
openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
hermes agent --agent FollowerAgent --session-id $SESSION_ID \
--message "Monitor resource utilization and report optimization opportunities" \
--thinking medium
```
@@ -206,14 +206,14 @@ echo "Testing agent response times..."
# Measure Genesis Agent response time
start_time=$(date +%s.%N)
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Quick response test" --thinking low
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Quick response test" --thinking low
end_time=$(date +%s.%N)
genesis_time=$(echo "$end_time - $start_time" | bc)
echo "Genesis Agent response time: ${genesis_time}s"
# Measure Follower Agent response time
start_time=$(date +%s.%N)
openclaw agent --agent FollowerAgent --session-id $SESSION_ID --message "Quick response test" --thinking low
hermes agent --agent FollowerAgent --session-id $SESSION_ID --message "Quick response test" --thinking low
end_time=$(date +%s.%N)
follower_time=$(echo "$end_time - $start_time" | bc)
echo "Follower Agent response time: ${follower_time}s"
@@ -227,7 +227,7 @@ echo "Testing concurrent sessions..."
# Create multiple concurrent sessions
for i in {1..5}; do
SESSION_ID="concurrent-$i-$(date +%s)"
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Concurrent test $i" --thinking low &
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Concurrent test $i" --thinking low &
done
# Wait for all to complete
@@ -243,13 +243,13 @@ echo "Concurrent session tests completed"
SESSION_ID="format-test-$(date +%s)"
# Test short message
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Short" --thinking low
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Short" --thinking low
# Test medium message
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "This is a medium length message to test agent processing capabilities" --thinking low
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "This is a medium length message to test agent processing capabilities" --thinking low
# Test long message
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "This is a longer message that tests the agent's ability to process more complex requests and provide detailed responses. It should demonstrate the agent's capability to handle substantial input and generate comprehensive output." --thinking medium
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "This is a longer message that tests the agent's ability to process more complex requests and provide detailed responses. It should demonstrate the agent's capability to handle substantial input and generate comprehensive output." --thinking medium
```
### Special Character Testing
@@ -258,10 +258,10 @@ openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "This is
SESSION_ID="special-test-$(date +%s)"
# Test special characters
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Test special chars: !@#$%^&*()_+-=[]{}|;':\",./<>?" --thinking low
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Test special chars: !@#$%^&*()_+-=[]{}|;':\",./<>?" --thinking low
# Test code blocks
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Test code: \`print('Hello World')\` and \`\`\`python\ndef hello():\n print('Hello')\`\`\`" --thinking low
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Test code: \`print('Hello World')\` and \`\`\`python\ndef hello():\n print('Hello')\`\`\`" --thinking low
```
## 7. Agent Error Handling Testing
@@ -270,14 +270,14 @@ openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Test cod
```bash
# Test invalid agent names
echo "Testing invalid agent handling..."
openclaw agent --agent InvalidAgent --session-id test --message "Test message" --thinking low 2>/dev/null && echo "ERROR: Invalid agent accepted" || echo "✅ Invalid agent properly rejected"
hermes agent --agent InvalidAgent --session-id test --message "Test message" --thinking low 2>/dev/null && echo "ERROR: Invalid agent accepted" || echo "✅ Invalid agent properly rejected"
```
### Invalid Session Testing
```bash
# Test session handling
echo "Testing session handling..."
openclaw agent --agent GenesisAgent --session-id "" --message "Test message" --thinking low 2>/dev/null && echo "ERROR: Empty session accepted" || echo "✅ Empty session properly rejected"
hermes agent --agent GenesisAgent --session-id "" --message "Test message" --thinking low 2>/dev/null && echo "ERROR: Empty session accepted" || echo "✅ Empty session properly rejected"
```
## 8. Agent Integration Testing
@@ -288,7 +288,7 @@ openclaw agent --agent GenesisAgent --session-id "" --message "Test message" --t
SESSION_ID="ai-integration-$(date +%s)"
# Agent submits AI job
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "Submit AI job for text generation: Generate a short story about AI" \
--thinking high
@@ -302,7 +302,7 @@ openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
SESSION_ID="blockchain-integration-$(date +%s)"
# Agent checks blockchain status
openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
hermes agent --agent GenesisAgent --session-id $SESSION_ID \
--message "Check blockchain status and report current height and network conditions" \
--thinking medium
```
@@ -313,7 +313,7 @@ openclaw agent --agent GenesisAgent --session-id $SESSION_ID \
SESSION_ID="resource-integration-$(date +%s)"
# Agent monitors resources
openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
hermes agent --agent FollowerAgent --session-id $SESSION_ID \
--message "Monitor system resources and report CPU, memory, and GPU utilization" \
--thinking medium
```
@@ -325,26 +325,26 @@ openclaw agent --agent FollowerAgent --session-id $SESSION_ID \
#!/bin/bash
# automated_agent_tests.sh
echo "=== OpenClaw Agent Tests ==="
echo "=== hermes Agent Tests ==="
# Test gateway status
echo "Testing OpenClaw gateway..."
openclaw gateway status || exit 1
echo "Testing hermes gateway..."
hermes gateway status || exit 1
# Test basic agent functionality
echo "Testing basic agent functionality..."
SESSION_ID="auto-test-$(date +%s)"
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Automated test message" --thinking low || exit 1
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Automated test message" --thinking low || exit 1
# Test multi-agent coordination
echo "Testing multi-agent coordination..."
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Initiate coordination test" --thinking low || exit 1
openclaw agent --agent FollowerAgent --session-id $SESSION_ID --message "Respond to coordination test" --thinking low || exit 1
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Initiate coordination test" --thinking low || exit 1
hermes agent --agent FollowerAgent --session-id $SESSION_ID --message "Respond to coordination test" --thinking low || exit 1
# Test session management
echo "Testing session management..."
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Session test message 1" --thinking low || exit 1
openclaw agent --agent GenesisAgent --session-id $SESSION_ID --message "Session test message 2" --thinking low || exit 1
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Session test message 1" --thinking low || exit 1
hermes agent --agent GenesisAgent --session-id $SESSION_ID --message "Session test message 2" --thinking low || exit 1
echo "✅ All agent tests passed!"
```
@@ -355,26 +355,26 @@ echo "✅ All agent tests passed!"
#### Gateway Not Running
```bash
# Problem: OpenClaw gateway not responding
# Problem: hermes gateway not responding
# Solution: Start gateway service
sudo systemctl start openclaw-gateway
sudo systemctl status openclaw-gateway
sudo systemctl start hermes-gateway
sudo systemctl status hermes-gateway
```
#### Agent Not Responding
```bash
# Problem: Agent not responding to messages
# Solution: Check agent configuration and restart
openclaw agent list
sudo systemctl restart openclaw-gateway
hermes agent list
sudo systemctl restart hermes-gateway
```
#### Session Issues
```bash
# Problem: Session not persisting
# Solution: Check session storage
openclaw config show
openclaw gateway status
hermes config show
hermes gateway status
```
#### Performance Issues
@@ -383,13 +383,13 @@ openclaw gateway status
# Solution: Check system resources
free -h
df -h
ps aux | grep openclaw
ps aux | grep hermes
```
## 11. Success Criteria
### Pass/Fail Criteria
- ✅ OpenClaw gateway running and responsive
- ✅ hermes gateway running and responsive
- ✅ All agents respond to basic messages
- ✅ Multi-agent coordination working
- ✅ Session management functioning

72
.windsurf/workflows/archive/test.md
View File

@@ -16,7 +16,7 @@ See **[TEST_MASTER_INDEX.md](TEST_MASTER_INDEX.md)** for complete navigation to
### New Test Modules Available
1. **[Basic Testing Module](test-basic.md)** - CLI and core operations testing
2. **[OpenClaw Agent Testing](test-openclaw-agents.md)** - Agent functionality and coordination
2. **[hermes Agent Testing](test-hermes-agents.md)** - Agent functionality and coordination
3. **[AI Operations Testing](test-ai-operations.md)** - AI job submission and processing
4. **[Advanced AI Testing](test-advanced-ai.md)** - Complex AI workflows and multi-model pipelines
5. **[Cross-Node Testing](test-cross-node.md)** - Multi-node coordination and distributed operations
@@ -57,11 +57,11 @@ source venv/bin/activate
./aitbc-cli resource status
```
### Run OpenClaw Agent Tests
### Run hermes Agent Tests
```bash
# Reference: test-openclaw-agents.md
openclaw agent --agent GenesisAgent --session-id test --message "Test message" --thinking low
openclaw agent --agent FollowerAgent --session-id test --message "Test response" --thinking low
# Reference: test-hermes-agents.md
hermes agent --agent GenesisAgent --session-id test --message "Test message" --thinking low
hermes agent --agent FollowerAgent --session-id test --message "Test response" --thinking low
```
### Run AI Operations Tests
@@ -82,7 +82,7 @@ ssh aitbc1 'cd /opt/aitbc && ./aitbc-cli resource status'
### Phase 1: Basic Validation
1. **[Basic Testing Module](test-basic.md)** - Verify core functionality
2. **[OpenClaw Agent Testing](test-openclaw-agents.md)** - Validate agent operations
2. **[hermes Agent Testing](test-hermes-agents.md)** - Validate agent operations
3. **[AI Operations Testing](test-ai-operations.md)** - Confirm AI job processing
### Phase 2: Advanced Validation
@@ -98,12 +98,12 @@ ssh aitbc1 'cd /opt/aitbc && ./aitbc-cli resource status'
| Module | Focus | Prerequisites | Quick Command |
|--------|-------|---------------|---------------|
| **[Basic](test-basic.md)** | CLI & Core Ops | None | `./aitbc-cli --version` |
| **[OpenClaw](test-openclaw-agents.md)** | Agent Testing | Basic | `openclaw agent --agent GenesisAgent --session-id test --message "test"` |
| **[hermes](test-hermes-agents.md)** | Agent Testing | Basic | `hermes agent --agent GenesisAgent --session-id test --message "test"` |
| **[AI Ops](test-ai-operations.md)** | AI Jobs | Basic | `./aitbc-cli ai-submit --wallet genesis-ops --type inference --prompt "test" --payment 100` |
| **[Advanced AI](test-advanced-ai.md)** | Complex AI | AI Ops | `./aitbc-cli ai-submit --wallet genesis-ops --type parallel --prompt "complex test" --payment 500` |
| **[Cross-Node](test-cross-node.md)** | Multi-Node | AI Ops | `ssh aitbc1 'cd /opt/aitbc && ./aitbc-cli resource status'` |
| **[Performance](test-performance.md)** | Performance | All | `./aitbc-cli simulate blockchain --blocks 100 --transactions 1000` |
| **[Integration](test-integration.md)** | End-to-End | All | `./scripts/workflow-openclaw/06_advanced_ai_workflow_openclaw.sh` |
| **[Integration](test-integration.md)** | End-to-End | All | `./scripts/workflow-hermes/06_advanced_ai_workflow_hermes.sh` |
## 🎯 Migration Guide
@@ -128,7 +128,7 @@ ssh aitbc1 'cd /opt/aitbc && ./aitbc-cli resource status'
#### **For New Deployments**
1. Start with **[Basic Testing Module](test-basic.md)**
2. Add **[OpenClaw Agent Testing](test-openclaw-agents.md)**
2. Add **[hermes Agent Testing](test-hermes-agents.md)**
3. Include **[AI Operations Testing](test-ai-operations.md)**
4. Add advanced modules as needed
@@ -163,22 +163,22 @@ python run_cli_tests.py
python -m pytest cli/tests/test_marketplace.py -v
```
### 2. Run OpenClaw Agent Tests
### 2. Run hermes Agent Tests
```bash
# Test OpenClaw gateway status
openclaw status --agent all
# Test hermes gateway status
hermes status --agent all
# Test basic agent communication
openclaw agent --agent main --message "Test communication" --thinking minimal
hermes agent --agent main --message "Test communication" --thinking minimal
# Test session-based workflow
SESSION_ID="test-$(date +%s)"
openclaw agent --agent main --session-id $SESSION_ID --message "Initialize test session" --thinking low
openclaw agent --agent main --session-id $SESSION_ID --message "Continue test session" --thinking medium
hermes agent --agent main --session-id $SESSION_ID --message "Initialize test session" --thinking low
hermes agent --agent main --session-id $SESSION_ID --message "Continue test session" --thinking medium
# Test multi-agent coordination
openclaw agent --agent coordinator --message "Test coordination" --thinking high &
openclaw agent --agent worker --message "Test worker response" --thinking medium &
hermes agent --agent coordinator --message "Test coordination" --thinking high &
hermes agent --agent worker --message "Test worker response" --thinking medium &
wait
```
@@ -234,7 +234,7 @@ ssh aitbc1 'curl -s http://localhost:8006/health | jq .'
```bash
# Test complex AI pipeline
SESSION_ID="advanced-test-$(date +%s)"
openclaw agent --agent main --session-id $SESSION_ID --message "Design complex AI pipeline for testing" --thinking high
hermes agent --agent main --session-id $SESSION_ID --message "Design complex AI pipeline for testing" --thinking high
# Test parallel AI operations
./aitbc-cli ai-submit --wallet genesis-ops --type parallel --prompt "Parallel AI test" --payment 100
@@ -435,9 +435,9 @@ netstat -tlnp | grep -E "(8000|8001|8006|11434)"
./aitbc-cli wallet list
./aitbc-cli chain
# Check OpenClaw functionality
openclaw --version
openclaw status --agent all
# Check hermes functionality
hermes --version
hermes status --agent all
# Check AI operations
./aitbc-cli ai-ops --action status --job-id "latest"
@@ -448,25 +448,25 @@ curl -s http://localhost:8006/health | jq .
ssh aitbc1 'curl -s http://localhost:8006/health | jq .'
```
### 13. OpenClaw Agent Debugging
### 13. hermes Agent Debugging
```bash
# Test OpenClaw gateway connectivity
openclaw status --agent all
# Test hermes gateway connectivity
hermes status --agent all
# Debug agent communication
openclaw agent --agent main --message "Debug test" --thinking high
hermes agent --agent main --message "Debug test" --thinking high
# Test session management
SESSION_ID="debug-$(date +%s)"
openclaw agent --agent main --session-id $SESSION_ID --message "Session debug test" --thinking medium
hermes agent --agent main --session-id $SESSION_ID --message "Session debug test" --thinking medium
# Test multi-agent coordination
openclaw agent --agent coordinator --message "Debug coordination test" --thinking high &
openclaw agent --agent worker --message "Debug worker response" --thinking medium &
hermes agent --agent coordinator --message "Debug coordination test" --thinking high &
hermes agent --agent worker --message "Debug worker response" --thinking medium &
wait
# Check agent workspace
openclaw workspace --status
hermes workspace --status
```
### 14. AI Operations Debugging
@@ -500,8 +500,8 @@ ab -n 100 -c 10 http://localhost:8000/health
# Test blockchain RPC performance
time curl -s http://localhost:8006/rpc/head | python3 -m json.tool
# Test OpenClaw agent performance
time openclaw agent --agent main --message "Performance test" --thinking high
# Test hermes agent performance
time hermes agent --agent main --message "Performance test" --thinking high
# Test AI operations performance
time ./aitbc-cli ai-submit --wallet genesis-ops --type inference --prompt "Performance test" --payment 10
@@ -644,7 +644,7 @@ python -m pytest cli/tests/test_cli_basic.py -v
## Recent Updates (v3.0)
### New Testing Capabilities
- **OpenClaw Agent Testing**: Added comprehensive agent communication and coordination tests
- **hermes Agent Testing**: Added comprehensive agent communication and coordination tests
- **AI Operations Testing**: Added AI job submission, resource allocation, and marketplace testing
- **Modular Workflow Testing**: Added testing for all 6 modular workflow components
- **Advanced AI Operations**: Added testing for complex AI pipelines and cross-node coordination
@@ -654,14 +654,14 @@ python -m pytest cli/tests/test_cli_basic.py -v
- **Multi-Agent Workflows**: Session-based agent coordination testing
- **AI Pipeline Testing**: Complex AI workflow orchestration testing
- **Distributed Testing**: Cross-node blockchain and AI operations testing
- **Performance Testing**: Added OpenClaw and AI operations performance benchmarks
- **Performance Testing**: Added hermes and AI operations performance benchmarks
- **Debugging Tools**: Enhanced troubleshooting for agent and AI operations
### Updated Project Structure
- **Working Directory**: `/opt/aitbc`
- **Virtual Environment**: `/opt/aitbc/venv`
- **CLI Wrapper**: `./aitbc-cli`
- **OpenClaw Integration**: OpenClaw 2026.3.24+ gateway and agents
- **hermes Integration**: hermes 2026.3.24+ gateway and agents
- **Modular Workflows**: 6 focused workflow modules
- **Test Structure**: Updated to include agent and AI testing
@@ -670,7 +670,7 @@ python -m pytest cli/tests/test_cli_basic.py -v
- **Exchange API**: Port 8001
- **Blockchain RPC**: Port 8006
- **Ollama**: Port 11434 (GPU operations)
- **OpenClaw Gateway**: Default port (configured in OpenClaw)
- **hermes Gateway**: Default port (configured in hermes)
### Enhanced Testing Features
- **Agent Testing**: Multi-agent communication and coordination
@@ -682,7 +682,7 @@ python -m pytest cli/tests/test_cli_basic.py -v
### Current Commands
- **CLI Commands**: Updated to use actual CLI implementation
- **OpenClaw Commands**: Agent communication and coordination
- **hermes Commands**: Agent communication and coordination
- **AI Operations**: Job submission, monitoring, marketplace
- **Service Management**: Updated to current systemd services
- **Modular Workflows**: Testing for all workflow modules

4
.windsurf/workflows/blockchain-communication-test.md
View File

@@ -169,7 +169,7 @@ ssh aitbc1 'cd /opt/aitbc && git log --oneline -5 --decorate'
## Training Integration
### Integration with Mastery Plan
This workflow integrates with Stage 2 (Intermediate Operations) of the OpenClaw AITBC Mastery Plan.
This workflow integrates with Stage 2 (Intermediate Operations) of the hermes AITBC Mastery Plan.
### Training Script
`/opt/aitbc/scripts/training/stage2_intermediate.sh` includes blockchain communication testing as part of the training curriculum.
@@ -259,4 +259,4 @@ ssh gitea-runner 'journalctl -u aitbc-blockchain-p2p -n 30 --no-pager'
## Related Workflows
- [Multi-Node Operations](/multi-node-blockchain-operations.md)
- [Multi-Node Setup Core](/multi-node-blockchain-setup-core.md)
- [Ollama GPU Test OpenClaw](/ollama-gpu-test-openclaw.md)
- [Ollama GPU Test hermes](/ollama-gpu-test-hermes.md)

34
.windsurf/workflows/openclaw-cross-node-communication.md → .windsurf/workflows/hermes-cross-node-communication.md
View File

@@ -1,25 +1,25 @@
---
description: OpenClaw specialized training workflow for agent-to-agent cross-node communication via AITBC blockchain
title: OpenClaw Cross-Node Communication Training
description: hermes specialized training workflow for agent-to-agent cross-node communication via AITBC blockchain
title: hermes Cross-Node Communication Training
version: 1.0
---
# OpenClaw Cross-Node Communication Training
# hermes Cross-Node Communication Training
## Purpose
This specialized training module teaches OpenClaw agents how to establish, verify, and utilize cross-node communication channels over the AITBC blockchain network (between genesis node `aitbc` and follower node `aitbc1`).
This specialized training module teaches hermes agents how to establish, verify, and utilize cross-node communication channels over the AITBC blockchain network (between genesis node `aitbc` and follower node `aitbc1`).
## Learning Objectives
1. **Agent Registration**: Register OpenClaw agents on multiple distinct blockchain nodes.
1. **Agent Registration**: Register hermes agents on multiple distinct blockchain nodes.
2. **Peer Discovery**: Discover agent endpoints and IDs across the blockchain state.
3. **Cross-Node Messaging**: Send and receive secure messages via blockchain transactions.
4. **Task Coordination**: Delegate AI tasks from a genesis-based agent to a follower-based agent.
5. **Event Monitoring**: Subscribe to and parse blockchain events for incoming messages.
## Prerequisites
- Completed [Stage 2 of the Mastery Plan](/OPENCLAW_AITBC_MASTERY_PLAN.md)
- Completed [Stage 2 of the Mastery Plan](/hermes_AITBC_MASTERY_PLAN.md)
- Both nodes synchronized and communicating on port 8006
- Funded wallets on both nodes (`openclaw-trainee` and `follower-ops`)
- Funded wallets on both nodes (`hermes-trainee` and `follower-ops`)
## Training Modules
@@ -29,14 +29,14 @@ Agents must be registered on the blockchain to receive messages.
```bash
# Genesis Node (aitbc: 10.1.223.40)
NODE_URL=http://10.1.223.40:8006 ./aitbc-cli agent create \
--name "openclaw-genesis-commander" \
--name "hermes-genesis-commander" \
--description "Primary coordinator agent on genesis node" \
--verification full \
--verbose
# Follower Node (aitbc1: <aitbc1-ip>)
NODE_URL=http://<aitbc1-ip>:8006 ./aitbc-cli agent create \
--name "openclaw-follower-worker" \
--name "hermes-follower-worker" \
--description "Worker agent on follower node" \
--verification full \
--debug
@@ -47,7 +47,7 @@ Learn to format and transmit messages between the registered agents.
```bash
# Get follower agent ID
FOLLOWER_AGENT_ID=$(NODE_URL=http://<aitbc1-ip>:8006 ./aitbc-cli agent list --output json | jq -r '.[] | select(.name=="openclaw-follower-worker") | .id')
FOLLOWER_AGENT_ID=$(NODE_URL=http://<aitbc1-ip>:8006 ./aitbc-cli agent list --output json | jq -r '.[] | select(.name=="hermes-follower-worker") | .id')
# Send instruction from genesis to follower
NODE_URL=http://10.1.223.40:8006 ./aitbc-cli agent message \
@@ -62,11 +62,11 @@ The follower agent must listen for and decode messages.
```bash
# Retrieve messages on follower node
NODE_URL=http://<aitbc1-ip>:8006 ./aitbc-cli agent messages \
--from openclaw-genesis-commander \
--from hermes-genesis-commander \
--output json
# Acknowledge receipt (Follower -> Genesis)
GENESIS_AGENT_ID=$(NODE_URL=http://10.1.223.40:8006 ./aitbc-cli agent list --output json | jq -r '.[] | select(.name=="openclaw-genesis-commander") | .id')
GENESIS_AGENT_ID=$(NODE_URL=http://10.1.223.40:8006 ./aitbc-cli agent list --output json | jq -r '.[] | select(.name=="hermes-genesis-commander") | .id')
NODE_URL=http://<aitbc1-ip>:8006 ./aitbc-cli agent message \
--to $GENESIS_AGENT_ID \
@@ -97,19 +97,19 @@ NODE_URL=http://<aitbc1-ip>:8006 ./aitbc-cli agent message \
## Automated Training Script
Execute the specialized training script to practice these operations autonomously.
**Script Path:** `/opt/aitbc/scripts/training/openclaw_cross_node_comm.sh`
**Script Path:** `/opt/aitbc/scripts/training/hermes_cross_node_comm.sh`
```bash
# Run the interactive training
cd /opt/aitbc/scripts/training
./openclaw_cross_node_comm.sh
./hermes_cross_node_comm.sh
# Run in automated evaluation mode
./openclaw_cross_node_comm.sh --auto-eval
./hermes_cross_node_comm.sh --auto-eval
```
## Success Validation
An OpenClaw agent has mastered cross-node communication when it can:
An hermes agent has mastered cross-node communication when it can:
1. Parse the local state to find remote agent IDs.
2. Construct and broadcast a valid JSON payload in an `agent message` transaction.
3. Automatically poll or listen for response messages on the remote node.
@@ -118,4 +118,4 @@ An OpenClaw agent has mastered cross-node communication when it can:
## Related Skills
- [aitbc-node-coordinator](/aitbc-node-coordinator.md)
- [openclaw-coordination-orchestrator](/openclaw-coordination-orchestrator.md)
- [hermes-coordination-orchestrator](/hermes-coordination-orchestrator.md)

2
.windsurf/workflows/multi-node-blockchain-reference.md
View File

@@ -344,7 +344,7 @@ sudo sysctl -p
```bash
# Use session IDs for agent workflows
SESSION_ID="task-$(date +%s)"
openclaw agent --agent main --session-id $SESSION_ID --message "Task description"
hermes agent --agent main --session-id $SESSION_ID --message "Task description"
# Always verify transactions
./aitbc-cli wallet transactions wallet-name --limit 5

64
.windsurf/workflows/multi-node-blockchain-setup-openclaw.md → .windsurf/workflows/multi-node-blockchain-setup-hermes.md
View File

@@ -1,13 +1,13 @@
---
description: Multi-node blockchain deployment workflow executed by OpenClaw agents using optimized scripts
title: OpenClaw Multi-Node Blockchain Deployment
description: Multi-node blockchain deployment workflow executed by hermes agents using optimized scripts
title: hermes Multi-Node Blockchain Deployment
version: 4.1
---
# OpenClaw Multi-Node Blockchain Deployment Workflow
# hermes Multi-Node Blockchain Deployment Workflow
Two-node AITBC blockchain setup: **aitbc** (genesis authority) + **aitbc1** (follower node).
Coordinated by OpenClaw agents with AI operations, advanced coordination, and genesis reset capabilities.
Coordinated by hermes agents with AI operations, advanced coordination, and genesis reset capabilities.
## 🆕 What's New in v4.1
@@ -23,13 +23,13 @@ Coordinated by OpenClaw agents with AI operations, advanced coordination, and ge
## Critical CLI Syntax
```bash
# OpenClaw — ALWAYS use --message (long form). -m does NOT work.
openclaw agent --agent main --message "task description" --thinking medium
# hermes — ALWAYS use --message (long form). -m does NOT work.
hermes agent --agent main --message "task description" --thinking medium
# Session-based (maintains context across calls)
SESSION_ID="deploy-$(date +%s)"
openclaw agent --agent main --session-id $SESSION_ID --message "Initialize deployment" --thinking low
openclaw agent --agent main --session-id $SESSION_ID --message "Report progress" --thinking medium
hermes agent --agent main --session-id $SESSION_ID --message "Initialize deployment" --thinking low
hermes agent --agent main --session-id $SESSION_ID --message "Report progress" --thinking medium
# AITBC CLI — always from /opt/aitbc with venv
cd /opt/aitbc && source venv/bin/activate
@@ -69,15 +69,15 @@ python3 /tmp/aitbc1_heartbeat.py
| Blockchain data | `/var/lib/aitbc/data/ait-mainnet/` |
| Keystore | `/var/lib/aitbc/keystore/` |
| Central env config | `/etc/aitbc/.env` |
| Workflow scripts | `/opt/aitbc/scripts/workflow-openclaw/` |
| Documentation | `/opt/aitbc/docs/openclaw/` |
| Workflow scripts | `/opt/aitbc/scripts/workflow-hermes/` |
| Documentation | `/opt/aitbc/docs/hermes/` |
| Logs | `/var/log/aitbc/` |
> All databases go in `/var/lib/aitbc/data/`, NOT in app directories.
## Unique Node Identity Configuration
Each node must have unique `proposer_id` and `p2p_node_id` for proper P2P network operation. The OpenClaw setup scripts automatically generate UUID-based IDs during initial setup.
Each node must have unique `proposer_id` and `p2p_node_id` for proper P2P network operation. The hermes setup scripts automatically generate UUID-based IDs during initial setup.
### Node Identity Files
- `/etc/aitbc/.env` - Contains `proposer_id` for block signing and consensus
@@ -108,55 +108,55 @@ ssh gitea-runner 'grep -E "^(proposer_id|p2p_node_id)=" /etc/aitbc/.env /etc/ait
```
### P2P Identity Issues
If OpenClaw agents report P2P connection failures due to duplicate IDs:
If hermes agents report P2P connection failures due to duplicate IDs:
1. Run the ID generation utility on affected nodes
2. Restart P2P services: `systemctl restart aitbc-blockchain-p2p`
3. Verify connectivity: `journalctl -u aitbc-blockchain-p2p -n 30`
4. Re-run OpenClaw agent coordination to confirm P2P connectivity
4. Re-run hermes agent coordination to confirm P2P connectivity
## Quick Start
### Full Deployment (Recommended)
```bash
# 1. Complete orchestrated workflow
/opt/aitbc/scripts/workflow-openclaw/05_complete_workflow_openclaw.sh
/opt/aitbc/scripts/workflow-hermes/05_complete_workflow_hermes.sh
# 2. Verify both nodes
curl -s http://localhost:8006/rpc/head | jq '.height'
ssh aitbc1 'curl -s http://localhost:8006/rpc/head | jq .height'
# 3. Agent analysis of deployment
openclaw agent --agent main --message "Analyze multi-node blockchain deployment status" --thinking high
hermes agent --agent main --message "Analyze multi-node blockchain deployment status" --thinking high
```
### Phase-by-Phase Execution
```bash
# Phase 1: Pre-flight (tested, working)
/opt/aitbc/scripts/workflow-openclaw/01_preflight_setup_openclaw_simple.sh
/opt/aitbc/scripts/workflow-hermes/01_preflight_setup_hermes_simple.sh
# Phase 2: Genesis authority setup
/opt/aitbc/scripts/workflow-openclaw/02_genesis_authority_setup_openclaw.sh
/opt/aitbc/scripts/workflow-hermes/02_genesis_authority_setup_hermes.sh
# Phase 3: Follower node setup
/opt/aitbc/scripts/workflow-openclaw/03_follower_node_setup_openclaw.sh
/opt/aitbc/scripts/workflow-hermes/03_follower_node_setup_hermes.sh
# Phase 4: Wallet operations (tested, working)
/opt/aitbc/scripts/workflow-openclaw/04_wallet_operations_openclaw_corrected.sh
/opt/aitbc/scripts/workflow-hermes/04_wallet_operations_hermes_corrected.sh
# Phase 5: Smart contract messaging training
/opt/aitbc/scripts/workflow-openclaw/train_agent_messaging.sh
/opt/aitbc/scripts/workflow-hermes/train_agent_messaging.sh
```
## Available Scripts
```
/opt/aitbc/scripts/workflow-openclaw/
├── 01_preflight_setup_openclaw_simple.sh # Pre-flight (tested)
├── 01_preflight_setup_openclaw_corrected.sh # Pre-flight (corrected)
├── 02_genesis_authority_setup_openclaw.sh # Genesis authority
├── 03_follower_node_setup_openclaw.sh # Follower node
├── 04_wallet_operations_openclaw_corrected.sh # Wallet ops (tested)
├── 05_complete_workflow_openclaw.sh # Full orchestration
/opt/aitbc/scripts/workflow-hermes/
├── 01_preflight_setup_hermes_simple.sh # Pre-flight (tested)
├── 01_preflight_setup_hermes_corrected.sh # Pre-flight (corrected)
├── 02_genesis_authority_setup_hermes.sh # Genesis authority
├── 03_follower_node_setup_hermes.sh # Follower node
├── 04_wallet_operations_hermes_corrected.sh # Wallet ops (tested)
├── 05_complete_workflow_hermes.sh # Full orchestration
├── fix_agent_communication.sh # Agent comm fix
├── train_agent_messaging.sh # SC messaging training
└── implement_agent_messaging.sh # Advanced messaging
@@ -165,11 +165,11 @@ openclaw agent --agent main --message "Analyze multi-node blockchain deployment
## Workflow Phases
### Phase 1: Pre-Flight Setup
- Verify OpenClaw gateway running
- Verify hermes gateway running
- Check blockchain services on both nodes
- Validate SSH connectivity to aitbc1
- Confirm data directories at `/var/lib/aitbc/data/ait-mainnet/`
- Initialize OpenClaw agent session
- Initialize hermes agent session
### Phase 2: Genesis Authority Setup
- Configure genesis node environment
@@ -238,7 +238,7 @@ AITBC's `AgentMessagingContract` enables on-chain agent communication:
```bash
# Train agents on messaging
openclaw agent --agent main --message "Teach me AITBC Agent Messaging Contract for cross-node communication" --thinking high
hermes agent --agent main --message "Teach me AITBC Agent Messaging Contract for cross-node communication" --thinking high
```
## Troubleshooting
@@ -269,7 +269,7 @@ systemctl is-active aitbc-blockchain-{node,rpc}.service
ssh aitbc1 'systemctl is-active aitbc-blockchain-{node,rpc}.service'
# Agent health check
openclaw agent --agent main --message "Report multi-node blockchain health" --thinking medium
hermes agent --agent main --message "Report multi-node blockchain health" --thinking medium
# Integration test
/opt/aitbc/scripts/workflow/44_comprehensive_multi_node_scenario.sh
@@ -277,7 +277,7 @@ openclaw agent --agent main --message "Report multi-node blockchain health" --th
## Documentation
Reports and guides are in `/opt/aitbc/docs/openclaw/`:
Reports and guides are in `/opt/aitbc/docs/hermes/`:
- `guides/` — Implementation and fix guides
- `reports/` — Deployment and analysis reports
- `training/` — Agent training materials

102
.windsurf/workflows/ollama-gpu-test-openclaw.md → .windsurf/workflows/ollama-gpu-test-hermes.md
View File

@@ -1,16 +1,16 @@
---
description: OpenClaw agent workflow for complete Ollama GPU provider testing from client submission to blockchain recording
title: OpenClaw Ollama GPU Provider Test Workflow
description: Hermes agent workflow for complete Ollama GPU provider testing from client submission to blockchain recording
title: Hermes Ollama GPU Provider Test Workflow
version: 1.0
---
# OpenClaw Ollama GPU Provider Test Workflow
# Hermes Ollama GPU Provider Test Workflow
This OpenClaw agent workflow executes the complete end-to-end test for Ollama GPU inference jobs, including payment processing and blockchain transaction recording.
This Hermes agent workflow executes the complete end-to-end test for Ollama GPU inference jobs, including payment processing and blockchain transaction recording.
## Prerequisites
- OpenClaw 2026.3.24+ installed and gateway running
- Hermes 2026.3.24+ installed and gateway running
- All services running: coordinator, GPU miner, Ollama, blockchain node
- Home directory wallets configured
- Enhanced CLI with multi-wallet support
@@ -41,19 +41,19 @@ This OpenClaw agent workflow executes the complete end-to-end test for Ollama GP
- Validate transaction confirmations
- Check wallet balance updates
## OpenClaw Agent Workflow
## Hermes Agent Workflow
### Phase 1: Environment Validation
```bash
# Initialize test coordinator
SESSION_ID="ollama-test-$(date +%s)"
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Initialize Ollama GPU provider test workflow. Validate all services and dependencies." \
--thinking high
# Agent performs environment checks
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Execute environment validation: check coordinator API, Ollama service, GPU miner, blockchain node health" \
--thinking medium
```
@@ -62,18 +62,18 @@ openclaw agent --agent test-coordinator --session-id $SESSION_ID \
```bash
# Initialize client agent
openclaw agent --agent client-agent --session-id $SESSION_ID \
hermes agent --agent client-agent --session-id $SESSION_ID \
--message "Initialize as client agent. Create test wallets and configure for AI job submission." \
--thinking medium
# Agent creates test wallets
openclaw agent --agent client-agent --session-id $SESSION_ID \
hermes agent --agent client-agent --session-id $SESSION_ID \
--message "Create test wallets: test-client and test-miner. Switch to client wallet and verify balance." \
--thinking medium \
--parameters "wallet_type:simple,backup_enabled:true"
# Initialize miner agent
openclaw agent --agent miner-agent --session-id $SESSION_ID \
hermes agent --agent miner-agent --session-id $SESSION_ID \
--message "Initialize as miner agent. Verify miner wallet and GPU resource availability." \
--thinking medium
```
@@ -82,13 +82,13 @@ openclaw agent --agent miner-agent --session-id $SESSION_ID \
```bash
# Coordinator agent checks all services
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Perform comprehensive service health check: coordinator API, Ollama GPU service, GPU miner service, blockchain RPC" \
--thinking high \
--parameters "timeout:30,retry_count:3"
# Agent reports service status
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Report service health status and readiness for GPU testing" \
--thinking medium
```
@@ -97,19 +97,19 @@ openclaw agent --agent test-coordinator --session-id $SESSION_ID \
```bash
# Client agent submits inference job
openclaw agent --agent client-agent --session-id $SESSION_ID \
hermes agent --agent client-agent --session-id $SESSION_ID \
--message "Submit Ollama GPU inference job: 'What is the capital of France?' using llama3.2:latest model" \
--thinking high \
--parameters "prompt:What is the capital of France?,model:llama3.2:latest,payment:10"
# Agent monitors job progress
openclaw agent --agent client-agent --session-id $SESSION_ID \
hermes agent --agent client-agent --session-id $SESSION_ID \
--message "Monitor job progress through states: QUEUED → RUNNING → COMPLETED" \
--thinking medium \
--parameters "polling_interval:5,timeout:300"
# Agent validates job results
openclaw agent --agent client-agent --session-id $SESSION_ID \
hermes agent --agent client-agent --session-id $SESSION_ID \
--message "Validate job result: 'The capital of France is Paris.' Check accuracy and completeness" \
--thinking medium
```
@@ -118,13 +118,13 @@ openclaw agent --agent client-agent --session-id $SESSION_ID \
```bash
# Client agent handles payment processing
openclaw agent --agent client-agent --session-id $SESSION_ID \
hermes agent --agent client-agent --session-id $SESSION_ID \
--message "Process payment for completed GPU job: verify receipt information, pricing, and total cost" \
--thinking high \
--parameters "validate_receipt:true,check_pricing:true"
# Agent reports payment details
openclaw agent --agent client-agent --session-id $SESSION_ID \
hermes agent --agent client-agent --session-id $SESSION_ID \
--message "Report payment details: receipt ID, provider, GPU seconds, unit price, total cost" \
--thinking medium
```
@@ -133,13 +133,13 @@ openclaw agent --agent client-agent --session-id $SESSION_ID \
```bash
# Blockchain agent verifies transaction recording
openclaw agent --agent blockchain-agent --session-id $SESSION_ID \
hermes agent --agent blockchain-agent --session-id $SESSION_ID \
--message "Verify blockchain transaction recording: check for payment transaction, validate confirmation, track block inclusion" \
--thinking high \
--parameters "confirmations:1,timeout:60"
# Agent reports blockchain status
openclaw agent --agent blockchain-agent --session-id $SESSION_ID \
hermes agent --agent blockchain-agent --session-id $SESSION_ID \
--message "Report blockchain verification results: transaction hash, block height, confirmation status" \
--thinking medium
```
@@ -148,12 +148,12 @@ openclaw agent --agent blockchain-agent --session-id $SESSION_ID \
```bash
# Client agent checks final wallet balances
openclaw agent --agent client-agent --session-id $SESSION_ID \
hermes agent --agent client-agent --session-id $SESSION_ID \
--message "Verify final wallet balances after transaction: compare initial vs final balances" \
--thinking medium
# Miner agent checks earnings
openclaw agent --agent miner-agent --session-id $SESSION_ID \
hermes agent --agent miner-agent --session-id $SESSION_ID \
--message "Verify miner earnings: check wallet balance increase from GPU job payment" \
--thinking medium
```
@@ -162,18 +162,18 @@ openclaw agent --agent miner-agent --session-id $SESSION_ID \
```bash
# Coordinator agent generates final report
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Generate comprehensive test completion report: all phases status, results, wallet changes, blockchain verification" \
--thinking xhigh \
--parameters "include_metrics:true,include_logs:true,format:comprehensive"
# Agent posts results to coordination topic
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Post test results to blockchain coordination topic for permanent recording" \
--thinking high
```
## OpenClaw Agent Templates
## Hermes Agent Templates
### Test Coordinator Agent Template
@@ -289,22 +289,22 @@ openclaw agent --agent test-coordinator --session-id $SESSION_ID \
```bash
# Service Health Issues
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Service health check failed. Implementing recovery procedures: restart services, verify connectivity, check logs" \
--thinking high
# Wallet Issues
openclaw agent --agent client-agent --session-id $SESSION_ID \
hermes agent --agent client-agent --session-id $SESSION_ID \
--message "Wallet operation failed. Implementing wallet recovery: check keystore, verify permissions, recreate wallet if needed" \
--thinking high
# GPU Issues
openclaw agent --agent miner-agent --session-id $SESSION_ID \
hermes agent --agent miner-agent --session-id $SESSION_ID \
--message "GPU processing failed. Implementing recovery: check GPU availability, restart Ollama, verify model availability" \
--thinking high
# Blockchain Issues
openclaw agent --agent blockchain-agent --session-id $SESSION_ID \
hermes agent --agent blockchain-agent --session-id $SESSION_ID \
--message "Blockchain verification failed. Implementing recovery: check node sync, verify transaction pool, retry with different parameters" \
--thinking high
```
@@ -315,17 +315,17 @@ openclaw agent --agent blockchain-agent --session-id $SESSION_ID \
```bash
# Monitor agent performance
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Report agent performance metrics: response time, success rate, error count, resource utilization" \
--thinking medium
# System performance during test
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Monitor system performance during GPU test: CPU usage, memory usage, GPU utilization, network I/O" \
--thinking medium
```
## OpenClaw Integration
## Hermes Integration
### Session Management
@@ -334,22 +334,22 @@ openclaw agent --agent test-coordinator --session-id $SESSION_ID \
SESSION_ID="ollama-gpu-test-$(date +%s)"
# Use session across all agents
openclaw agent --agent test-coordinator --session-id $SESSION_ID --message "Initialize test" --thinking high
openclaw agent --agent client-agent --session-id $SESSION_ID --message "Submit job" --thinking medium
openclaw agent --agent miner-agent --session-id $SESSION_ID --message "Monitor GPU" --thinking medium
openclaw agent --agent blockchain-agent --session-id $SESSION_ID --message "Verify blockchain" --thinking high
hermes agent --agent test-coordinator --session-id $SESSION_ID --message "Initialize test" --thinking high
hermes agent --agent client-agent --session-id $SESSION_ID --message "Submit job" --thinking medium
hermes agent --agent miner-agent --session-id $SESSION_ID --message "Monitor GPU" --thinking medium
hermes agent --agent blockchain-agent --session-id $SESSION_ID --message "Verify blockchain" --thinking high
```
### Cross-Agent Communication
```bash
# Agents communicate through coordination topic
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Post coordination message: Test phase completed, next phase starting" \
--thinking medium
# Other agents respond to coordination
openclaw agent --agent client-agent --session-id $SESSION_ID \
hermes agent --agent client-agent --session-id $SESSION_ID \
--message "Acknowledge coordination: Ready for next phase" \
--thinking minimal
```
@@ -360,24 +360,24 @@ openclaw agent --agent client-agent --session-id $SESSION_ID \
```bash
#!/bin/bash
# ollama_gpu_test_openclaw.sh
# ollama_gpu_test_hermes.sh
SESSION_ID="ollama-gpu-test-$(date +%s)"
echo "Starting OpenClaw Ollama GPU Provider Test..."
echo "Starting Hermes Ollama GPU Provider Test..."
# Initialize coordinator
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Initialize complete Ollama GPU test workflow" \
--thinking high
# Execute all phases automatically
openclaw agent --agent test-coordinator --session-id $SESSION_ID \
hermes agent --agent test-coordinator --session-id $SESSION_ID \
--message "Execute complete test: environment check, wallet setup, service health, GPU test, payment processing, blockchain verification, final reporting" \
--thinking xhigh \
--parameters "auto_execute:true,timeout:600,report_format:comprehensive"
echo "OpenClaw Ollama GPU test completed!"
echo "Hermes Ollama GPU test completed!"
```
## Integration with Existing Workflow
@@ -389,11 +389,11 @@ echo "OpenClaw Ollama GPU test completed!"
cd /home/oib/windsurf/aitbc/home
python3 test_ollama_blockchain.py
# OpenClaw automated workflow
./ollama_gpu_test_openclaw.sh
# Hermes automated workflow
./ollama_gpu_test_hermes.sh
```
### Benefits of OpenClaw Integration
### Benefits of Hermes Integration
- **Intelligent Error Handling**: Agents detect and recover from failures
- **Adaptive Testing**: Agents adjust test parameters based on system state
@@ -406,14 +406,14 @@ python3 test_ollama_blockchain.py
### Agent Communication Issues
```bash
# Check OpenClaw gateway status
openclaw status --agent all
# Check Hermes gateway status
hermes status --agent all
# Test agent communication
openclaw agent --agent test --message "ping" --thinking minimal
hermes agent --agent test --message "ping" --thinking minimal
# Check session context
openclaw agent --agent test-coordinator --session-id $SESSION_ID --message "report status" --thinking medium
hermes agent --agent test-coordinator --session-id $SESSION_ID --message "report status" --thinking medium
```
### Service Integration Issues
@@ -429,4 +429,4 @@ systemctl is-active aitbc-host-gpu-miner.service
./aitbc-cli wallet info
```
This OpenClaw agent workflow transforms the manual Ollama GPU test into an intelligent, automated, and blockchain-recorded testing process with comprehensive error handling and reporting capabilities.
This Hermes agent workflow transforms the manual Ollama GPU test into an intelligent, automated, and blockchain-recorded testing process with comprehensive error handling and reporting capabilities.