Vibe Coding DiscoverCowAgent
View on GitHubOpen-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)
CowAgent (formerly chatgpt-on-wechat) is a Python agent harness: it plans tasks, runs tools, installs skills, and keeps long-term memory plus a personal knowledge base. Multi-agent, multi-model, and multi-channel, deployable via one-line install or Docker.
Use Cases
personal always-on AI assistant across IM appsbuilding multi-agent teams with per-agent roles and knowledgerunning an agent harness with planning and tool loopslong-term memory with vector + keyword retrievalauto-curated personal knowledge base and graphone-click skill installs from a skill hubMCP tool integration for external servicesmultimodal chat, image gen, ASR/TTS in one agentcomputer control and browser automation tasksdeploying a self-hosted assistant via Docker or web console
Built With
- Language
- Python
- Frameworks
- Electron · Vite · Tailwind CSS · Docker · aiohttp · python-telegram-bot · slack_bolt · discord.py · lark-oapi · wechatpy · dingtalk_stream
Tags
multi-agent · agent-harness · multi-model · memory · knowledge-base · skills · mcp · chatbot · wechat · telegram · self-evolution · tool-use · browser-automation · multimodal · task-planning · one-line-install