Skip to main content
CowAgent
CowAgent is your own open-source personal AI agent. It plans tasks proactively, uses tools, skills and MCP, and gets to know you over time through long-term memory, a knowledge base and self-evolution. CowAgent is multi-model, multi-channel and multi-agent. Plug in any major LLM provider, assemble a team of agents, and reach it from the Web and major IM platforms, running 24/7 on your computer or server. It’s a ready-to-use assistant and an open, extensible Agent Harness.

GitHub

Open-source repository — Star and contribute

Try Online

Dedicated cloud instance with built-in models — no setup

Core Capabilities

Autonomous Task Planning

Decomposes complex tasks and executes them step by step, looping over tools and skills until the goal is reached.

Long-term Memory

Three-tier architecture (context → daily → core), automatic Deep Dream distillation, hybrid keyword + vector retrieval.

Personal Knowledge Base

Auto-curates structured knowledge into a Markdown wiki, builds an evolving knowledge graph with visual browsing.

Self-Evolution

Reviews conversations automatically to improve skills, follow up on unfinished tasks, and consolidate memory and knowledge, growing through everyday use.

Skills System

A complete skill creation and execution engine. Install from Skill Hub or generate custom skills via natural-language conversation.

Tool System

Built-in file I/O, terminal, browser, scheduler, memory retrieval, web search, and more — with native MCP integration.

Command System

Terminal CLI and in-chat commands for process management, skill installation, configuration, and context inspection.

Pluggable Models

Claude, GPT, Gemini, DeepSeek, Qwen, GLM, Kimi, MiniMax, Doubao, and more — swap providers from the Web console with one click, or cover every capability with one key from the CowAgent model service.

Multi-channel Integration

A single Agent simultaneously serves Web, WeChat, Feishu, DingTalk, WeCom, QQ, and Official Accounts.

Multi-Agent Teams

Create multiple Agents with distinct roles to form a team, with group-chat collaboration, task delegation, and sub-Agents — usable in the Web console, desktop client, and channel integrations.

Quick Start

Run one of the commands below to install, configure, and start CowAgent in a single step:
Once started, open http://localhost:9899 to access the Web console — the unified place to chat, configure providers, connect channels, and install skills. You can also use the desktop client (macOS / Windows), which bundles the Agent runtime: download it and it’s ready to use. If you’d rather not deploy anything or collect model keys, try it online: a dedicated instance in your browser with built-in models, online 24/7. See CowAgent Cloud for details.

Quick Start

Complete installation and run guide

Architecture

CowAgent system architecture

Disclaimer

  1. This project is licensed under the MIT License and is intended for technical research and learning. You are responsible for complying with applicable laws and regulations in your jurisdiction; the maintainers assume no liability for any consequences arising from use of this project.
  2. Cost & safety: Agent mode consumes substantially more tokens than plain chat — pick models that balance quality and cost. The Agent has access to your local operating system; deploy only in trusted environments.
  3. CowAgent is a pure open-source project and does not participate in, authorize, or issue any cryptocurrency.

Community

Join our Discord

Ask questions, share skills, and follow development
Or scan the WeChat QR code to join the open-source community group: