CoPaw AI Assistant Skill Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. CoPaw is a personal AI assistant framework you deploy on your own machine or in the cloud. It connects to multiple chat platforms (DingTalk, Feishu, QQ, Discord, iMessage, Telegram, Mattermost, Matrix, MQTT) through a single agent, supports custom Python skills, scheduled cron jobs, local and cloud LLMs, and provides a web Console at http://127.0.0.1:8088/ . Installation pip (recommended if Python 3.10–3.13 is available) Script install (no Python setup required) macOS / Linux: Windows CMD: Windows PowerShell: After script install, open a new terminal: Install from source CLI Reference Workspace Structure After copaw init , a workspace is created (default: ~/.copaw/workspace/ ): Configuration ( config.yaml ) copaw init generates this file. Edit it directly or use the Console UI. LLM Provider (OpenAI compatible) Agent Settings Channel: DingTalk Channel: Feishu (Lark) Channel: Discord Channel: Telegram Channel: QQ Channel: Mattermost Channel: Matrix Custom Skills Skills are Python files placed in ~/.copaw/workspace/skills/ . They are auto loaded when CoPaw starts — no registration step needed. Minimal skill structure Skill with async support Skill returning structured data Cron / Scheduled Tasks Define cron jobs in config.yaml to run skills on a schedule and push results to a channel: Local Model Setup Ollama LM Studio llama.cpp (extra required) Tool Guard (Security) Tool Guard blocks risky tool calls and requires user approval before execution. Configure in config.yaml : When a call is blocked, the Console shows an approval prompt. The user can approve or deny before the tool runs. Token Usage Tracking Token usage is tracked automatically and visible in the Console dashboard. Access programmatically: Environment Variables Set these before running copaw app , or reference them in config.yaml as ${VAR NAME} : Common Patterns Pattern: Morning briefing to DingTalk Pattern: Multi channel broadcast Pattern: File summarization skill Troubleshooting Console not accessible at port 8088 Skills not loading Confirm the skill file is in ~/.copaw/workspace/skills/ Confirm SKILL NAME , SKILL DESCRIPTION , SKILL SCHEMA , and the handler function are all defined at module level Check ~/.copaw/workspace/logs/ for import errors Restart copaw app after adding new skill files Channel not receiving messages 1. Verify credentials are set correctly (env vars or config.yaml ) 2. Check the Console → Channels page for connection status 3. For DingTalk/Feishu/Discord with mention only: true , the bot must be @mentioned 4. Discord messages over 2000 characters are split automatically — ensure the bot has Send Messages permission LLM provider connection fails For Ollama: confirm ollama serve is running and base url matches For OpenAI compatible APIs: verify base url ends with /v1 LLM calls auto retry with exponential backoff — transient failures resolve automatically Windows encoding issues Or set in environment: Workspace reset ModelScope Cloud Deployment For one click cloud deployment without local setup: 1. Visit [ModelScope CoPaw Studio](https://modelscope.cn/studios/fork?target=AgentScope/CoPaw) 2. Fork the studio to your account 3. Set environment variables in the studio settings 4. Start the studio — Console is accessible via the studio URL Key Links Documentation : https://copaw.agentscope.io/ Channel setup guides : https://copaw.agentscope.io/docs/channels Release notes : https://agentscope ai.github.io/CoPaw/release notes GitHub : https://github.com/agentscope ai/CoPaw PyPI : https://pypi.org/project/copaw/ Discord community : https://discord.gg/eYMpfnkG8h

copaw-ai-assistant