b4defab163
Infrastructure: - Created LXC 224 (openclaw-lxc) at 10.10.0.224 - 2 CPU cores, 4GB RAM, 32GB disk - Docker-in-LXC with AppArmor unconfined - OpenClaw installed via npm with MiniMax M2.1 and Discord integration Documentation: - productivity/openclaw/CONTEXT.md - Comprehensive technology overview - productivity/openclaw/troubleshooting.md - Complete troubleshooting guide - productivity/openclaw/README.md - Quick reference - productivity/openclaw/DEPLOYMENT_STATUS.md - Deployment checklist and status Configuration: - Added OpenClaw keywords to CLAUDE.md auto-loading rules - Updated server-configs/hosts.yml with openclaw host entry - Backed up LXC config to server-configs/proxmox/lxc/224.conf - Created .env.example template in server-configs/openclaw/ Status: Fully operational - Gateway accessible at http://10.10.0.224:18789 (SSH tunnel required) - Discord bot connected and online - MiniMax M2.1 model configured (200K context window) - Daemon running as systemd service Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
195 lines
6.1 KiB
Markdown
195 lines
6.1 KiB
Markdown
# OpenClaw Personal AI Assistant - Technology Context
|
|
|
|
## Overview
|
|
|
|
OpenClaw is an open-source personal AI assistant that runs locally with autonomous agent capabilities. Originally created as "Clawdbot" by Peter Steinberger, now community-maintained as OpenClaw.
|
|
|
|
**Deployment:** LXC 224 (10.10.0.224)
|
|
**Status:** Deployment in progress
|
|
**Primary Use:** Personal automation, task management, Discord integration
|
|
|
|
## Architecture
|
|
|
|
### Gateway-Centric Design
|
|
- **Gateway Daemon:** Single control plane for all operations
|
|
- **Messaging:** Handles chat platform integrations (Discord, Telegram, etc.)
|
|
- **Tool Execution:** Sandboxed code execution via nested Docker containers
|
|
- **Client Connections:** WebSocket and HTTP API for external integrations
|
|
|
|
### Key Components
|
|
1. **OpenClaw Gateway** - Node.js application, port 18789
|
|
2. **Docker-in-Docker Sandbox** - Isolated execution environment
|
|
3. **Persistent Workspace** - `/workspace` for file operations and memory
|
|
4. **Configuration Layer** - `openclaw.json` + environment variables
|
|
|
|
## AI Provider Integration
|
|
|
|
**Current Provider:** MiniMax M2.1
|
|
- **Model:** MiniMax-M2.1 (200K context window)
|
|
- **API Type:** Anthropic-compatible messages API
|
|
- **Endpoint:** https://api.minimax.io/anthropic
|
|
- **Authentication:** Bearer token via `MINIMAX_API_KEY`
|
|
|
|
**Model Selection:**
|
|
- Primary: `minimax/MiniMax-M2.1` (standard, balanced performance)
|
|
- Fast variant: `minimax/MiniMax-M2.1-lightning` (lower latency, lower cost)
|
|
|
|
**Pricing (per 1M tokens):**
|
|
- M2.1: $0.50 input / $1.50 output
|
|
- M2.1 Lightning: $0.30 input / $0.90 output
|
|
|
|
## Discord Integration
|
|
|
|
**Bot Configuration:**
|
|
- **Policy:** DM pairing (secure by default)
|
|
- **Intents Required:** Message Content + Server Members
|
|
- **Permissions:** View/Send/History + Embeds + Files + Reactions
|
|
|
|
**Access Control:**
|
|
- DMs: Pairing code required (1-hour expiry)
|
|
- Guild channels: Can be enabled per-server with allowlists
|
|
- Mention requirement: Optional gating for shared channels
|
|
|
|
**Message Handling:**
|
|
- History context: 20 messages (configurable)
|
|
- File uploads: 8MB max (configurable)
|
|
- Response format: Markdown with embeds
|
|
|
|
## Security Model
|
|
|
|
### Sandboxing
|
|
- **Docker-in-Docker:** Code execution isolated in nested containers
|
|
- **AppArmor:** Unconfined profile required for container nesting
|
|
- **UID:** Runs as non-root `node` user (UID 1000) inside container
|
|
|
|
### Secrets Management
|
|
- **Storage:** Environment variables via `.env` file
|
|
- **Interpolation:** `${VAR_NAME}` syntax in openclaw.json
|
|
- **Scope:** Secrets only accessible to gateway process
|
|
|
|
### Network Isolation
|
|
- **Bridge Network:** `openclaw-net` isolates from other services
|
|
- **Exposed Ports:** Only 18789 (gateway) accessible on host network
|
|
- **Outbound:** Requires internet access for AI API calls
|
|
|
|
## Operational Patterns
|
|
|
|
### Standard Operations
|
|
```bash
|
|
# Start OpenClaw
|
|
docker compose up -d
|
|
|
|
# View logs
|
|
docker compose logs -f openclaw-gateway
|
|
|
|
# Restart after config changes
|
|
docker compose restart openclaw-gateway
|
|
|
|
# Stop service
|
|
docker compose down
|
|
```
|
|
|
|
### Pairing Management
|
|
```bash
|
|
# List pending pairing requests
|
|
docker compose exec openclaw-gateway openclaw pairing list discord
|
|
|
|
# Approve pairing
|
|
docker compose exec openclaw-gateway openclaw pairing approve discord <code>
|
|
|
|
# Revoke access
|
|
docker compose exec openclaw-gateway openclaw pairing revoke discord <user_id>
|
|
```
|
|
|
|
### Diagnostics
|
|
```bash
|
|
# Health check
|
|
docker compose exec openclaw-gateway openclaw doctor
|
|
|
|
# Channel status
|
|
docker compose exec openclaw-gateway openclaw channels status --probe
|
|
|
|
# Model configuration
|
|
docker compose exec openclaw-gateway openclaw models list
|
|
```
|
|
|
|
### Configuration Updates
|
|
```bash
|
|
# Edit configuration
|
|
nano openclaw.json
|
|
|
|
# Restart to apply changes
|
|
docker compose restart openclaw-gateway
|
|
|
|
# Verify changes
|
|
docker compose logs openclaw-gateway | grep "Configuration loaded"
|
|
```
|
|
|
|
## Resource Usage Patterns
|
|
|
|
**Expected Baseline:**
|
|
- Idle: ~200MB RAM, <5% CPU
|
|
- Active chat: ~500MB RAM, 10-20% CPU
|
|
- Browser automation: ~1GB RAM, 30-50% CPU
|
|
- Concurrent operations: Up to 2GB RAM
|
|
|
|
**Disk Usage:**
|
|
- Application: ~500MB
|
|
- Workspace files: Variable (user-dependent)
|
|
- Logs: ~50MB/week (with rotation)
|
|
- Docker images: ~1GB
|
|
|
|
**Network:**
|
|
- AI API calls: ~10-100KB per request
|
|
- Discord: WebSocket connection (minimal bandwidth)
|
|
- File uploads: Up to 8MB per message
|
|
|
|
## Integration Points
|
|
|
|
### Current Integrations
|
|
- **Discord:** DM-based personal assistant
|
|
- **MiniMax API:** AI model provider
|
|
- **Docker:** Sandboxed execution environment
|
|
|
|
### Potential Future Integrations
|
|
- **n8n:** Workflow automation triggers (not currently configured)
|
|
- **Home Assistant:** Smart home control via API
|
|
- **Additional chat platforms:** Telegram, Signal, WhatsApp
|
|
- **Browser automation skills:** Web scraping, form filling
|
|
|
|
## Troubleshooting Quick Reference
|
|
|
|
| Issue | Solution |
|
|
|-------|----------|
|
|
| Gateway won't start | Check `docker compose logs` for errors; verify .env secrets |
|
|
| Discord not connecting | Verify `DISCORD_BOT_TOKEN` and intents enabled |
|
|
| "Used disallowed intents" error | Enable Message Content Intent in Discord portal |
|
|
| Pairing code not working | Check expiry (1 hour), regenerate if needed |
|
|
| High memory usage | Check for stuck browser automation processes |
|
|
| MiniMax API errors | Verify `MINIMAX_API_KEY`, check API quota |
|
|
|
|
## References
|
|
|
|
- **Official Docs:** https://docs.openclaw.ai/
|
|
- **GitHub:** https://github.com/openclaw/openclaw
|
|
- **Discord Setup:** https://docs.openclaw.ai/channels/discord
|
|
- **MiniMax Provider:** https://docs.openclaw.ai/providers/minimax
|
|
- **MiniMax Platform:** https://platform.minimax.io/
|
|
|
|
## Maintenance Notes
|
|
|
|
**Update Strategy:**
|
|
- Auto-updates: Gateway pulls `:latest` tag on restart
|
|
- Breaking changes: Check release notes before updating
|
|
- Rollback: Pin specific version tag if needed
|
|
|
|
**Backup Strategy:**
|
|
- Configuration: `openclaw.json` + `.env` (version controlled template)
|
|
- Workspace: `/opt/openclaw/workspace` (contains agent memory/files)
|
|
- Logs: Optional retention for debugging
|
|
|
|
**Monitoring:**
|
|
- Health check: HTTP endpoint at http://10.10.0.224:18789/health
|
|
- Discord connectivity: Verify bot status in server member list
|
|
- Resource usage: Monitor via Proxmox dashboard
|