Copaw Ai Assistant
Deploy CoPaw as your own multi-channel personal assistant with custom skills, cron jobs, and local or cloud LLMs.
Overview
CoPaw AI Assistant is an agent skill for the Build phase that guides solo builders through installing CoPaw, connecting chat channels, adding Python skills, and scheduling cron jobs on a self-hosted personal AI assistant
Install
npx skills add https://github.com/aradotso/trending-skills --skill copaw-ai-assistantWhat is this skill?
- pip or curl install paths with copaw init --defaults and copaw app console on port 8088
- Multi-channel inbox: DingTalk, Feishu, QQ, Discord, Telegram, iMessage, Mattermost, Matrix, MQTT
- Extensible Python skills and cron scheduling on the same agent core
- Local and cloud LLM wiring including optional Ollama extras on install script
- Web Console at http://127.0.0.1:8088/ for configuration and troubleshooting
- Web Console served at http://127.0.0.1:8088/
- pip install path targets Python 3.10 through 3.13
Adoption & trust: 1.3k installs on skills.sh; 31 GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want one personal agent across DingTalk, Discord, or Telegram but fragmented docs make channel and LLM setup error-prone on your own machine.
Who is it for?
Indie builders who need a multi-channel personal assistant they control, especially across Asian enterprise chat apps plus Discord or Telegram.
Skip if: Teams that only need a single IDE-embedded coding agent with no chat bridge, or builders who cannot run Python 3.10+ or the install script on their host.
When should I use this skill?
Set up CoPaw, configure DingTalk/Feishu/Discord/Telegram channels, add custom skills, deploy locally, connect local LLMs, schedule cron, or troubleshoot channel configuration.
What do I get? / Deliverables
CoPaw runs locally or in your cloud with the web Console live, channels authenticated, skills loaded, and cron tasks ready for day-to-day builder workflows.
- Running copaw app with web Console reachable
- Initialized config from copaw init --defaults or interactive setup
- Channel and skill configuration verified for your messengers
Recommended Skills
Journey fit
You install and wire the assistant while assembling the product’s agent layer, before you rely on it for launch distribution or ops alerts. Agent-tooling is where you pick frameworks, channels, and skill packs that become your builder-facing copilot infrastructure.
How it compares
Framework install skill for a personal agent hub—not a drop-in Claude Code skill or an MCP server catalog entry.
Common Questions / FAQ
Who is copaw-ai-assistant for?
Solo and indie builders who want a self-hosted CoPaw instance that aggregates chat channels, custom skills, and scheduled jobs behind one agent.
When should I use copaw-ai-assistant?
Use it during Build when standing up agent-tooling: first install, wiring DingTalk or Feishu, adding skills, connecting Ollama or cloud models, or debugging channel config before you depend on it in Grow or Operate.
Is copaw-ai-assistant safe to install?
CoPaw runs with network and filesystem access on your machine; review the Security Audits panel on this page and lock down Console exposure, channel tokens, and cron payloads before production use.
SKILL.md
READMESKILL.md - Copaw Ai Assistant
# 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) ```bash pip install copaw copaw init --defaults # non-interactive setup with sensible defaults copaw app # starts the web Console + backend ``` ### Script install (no Python setup required) **macOS / Linux:** ```bash curl -fsSL https://copaw.agentscope.io/install.sh | bash # With Ollama support: curl -fsSL https://copaw.agentscope.io/install.sh | bash -s -- --extras ollama # Multiple extras: curl -fsSL https://copaw.agentscope.io/install.sh | bash -s -- --extras ollama,llamacpp ``` **Windows CMD:** ```cmd curl -fsSL https://copaw.agentscope.io/install.bat -o install.bat && install.bat ``` **Windows PowerShell:** ```powershell irm https://copaw.agentscope.io/install.ps1 | iex ``` After script install, open a new terminal: ```bash copaw init --defaults copaw app ``` ### Install from source ```bash git clone https://github.com/agentscope-ai/CoPaw.git cd CoPaw pip install -e ".[dev]" copaw init --defaults copaw app ``` --- ## CLI Reference ```bash copaw init # interactive workspace setup copaw init --defaults # non-interactive setup copaw app # start the Console (http://127.0.0.1:8088/) copaw app --port 8090 # use a custom port copaw --help # list all commands ``` --- ## Workspace Structure After `copaw init`, a workspace is created (default: `~/.copaw/workspace/`): ``` ~/.copaw/workspace/ ├── config.yaml # agent, provider, channel configuration ├── skills/ # custom skill files (auto-loaded) │ └── my_skill.py ├── memory/ # conversation memory storage └── logs/ # runtime logs ``` --- ## Configuration (`config.yaml`) `copaw init` generates this file. Edit it directly or use the Console UI. ### LLM Provider (OpenAI-compatible) ```yaml providers: - id: openai-main type: openai api_key: ${OPENAI_API_KEY} # use env var reference model: gpt-4o base_url: https://api.openai.com/v1 - id: local-ollama type: ollama model: llama3.2 base_url: http://localhost:11434 ``` ### Agent Settings ```yaml agent: name: CoPaw language: en # en, zh, ja, etc. provider_id: openai-main context_limit: 8000 ``` ### Channel: DingTalk ```yaml channels: - type: dingtalk app_key: ${DINGTALK_APP_KEY} app_secret: ${DINGTALK_APP_SECRET} agent_id: ${DINGTALK_AGENT_ID} mention_only: true # only respond when @mentioned in groups ``` ### Channel: Feishu (Lark) ```yaml channels: - type: feishu app_id: ${FEISHU_APP_ID} app_secret: ${FEISHU_APP_SECRET} mention_only: false ``` ### Channel: Discord ```yaml channels: - type: discord token: ${DISCORD_BOT_TOKEN} mention_only: true ``` ### Channel: Telegram ```yaml channels: - type: telegram token: ${TELEGRAM_BOT_TOKEN} ``` ### Channel: QQ ```yaml channels: - type: qq uin: ${QQ_U