[opensourcedex]

CowAgent is a free, open source ai development platforms project written in Python and released under MIT. It has 47,017 GitHub stars, 10,360 forks and 24 open issues, and was last pushed 14 hours ago. On this registry it ranks #18 of 61 tracked projects in AI Development Platforms, with 5 head-to-head comparisons available. It gained 30 stars over the last 3 tracked days.

What is CowAgent?

What it is

CowAgent is an open-source super AI assistant and Agent Harness, distributed under the MIT license and written in Python. It is the project formerly known as chatgpt-on-wechat, and it sits in the AI & Machine Learning / AI Development Platforms category. The repository carries roughly 46,975 stars, 10,351 forks, and 24 open issues, with four years of history and a most recent push on 15 September 2026. Its homepage is cowagent.ai, and the project describes itself as lightweight, easy to deploy, and built to extend.

The concrete problem it addresses is the gap between a raw model API and a working assistant. CowAgent plans tasks and loops over tools until a goal is reached, runs tools and Skills, builds a personal knowledge base and long-term memory, forms multi-agent teams, and self-evolves through use. It treats this assembly as a reference implementation of Agent Harness engineering: messages arrive through Channels, the Agent Core plans and reasons over memory, knowledge, tools, and skills, Models generate the response, and the answer returns through the originating channel. Any major LLM provider can be plugged in, and the service runs around the clock on a personal computer or server across the web and major IM platforms.

Key capabilities

  • Planning that decomposes complex tasks, executes them step by step, and loops over tools until the goal is reached.
  • Multi-Agent teams where each Agent carries its own role, model, skills, and knowledge while collaborating in a shared conversation.
  • A three-tier memory architecture of context, daily, and core layers, with automatic Deep Dream distillation and hybrid keyword plus vector retrieval.
  • Knowledge curation that turns material into a structured Markdown wiki and an evolving knowledge graph with visual browsing.
  • Self-Evolution that reviews conversations automatically to improve skills, follow up on unfinished tasks, and consolidate memory and knowledge.
  • Skills installed in one click from Skill Hub, GitHub, or ClawHub, or created through natural-language conversation.
  • Built-in tools for file I/O, terminal, browser, scheduler, memory retrieval, and web search, plus native MCP integration.

Who uses it and how

  • Individuals running a personal assistant 24/7 on a home computer or a server, reachable from the web console and messengers.
  • Teams deploying into IM platforms including Web, WeChat, Feishu, DingTalk, WeCom, QQ, Official Accounts, Telegram, and Slack.
  • Operators installing the bundled macOS or Windows desktop client, where the backend ships included and works out of the box.
  • Server administrators managing the service through the cow CLI with start, stop, restart, status,
project readme (upstream, from github) — read inline

CowAgent

Latest release License: MIT Stars Docs WeChat Group Discord

zhayujie%2FCowAgent | Trendshift

[English] | [中文] | [繁體中文] | [日本語]

CowAgent is an open-source super AI assistant that proactively plans tasks, controls your computer and external services, creates and runs Skills, builds a personal knowledge base and long-term memory, forms multi-agent teams, and grows alongside you through self-evolution — a reference implementation of Agent Harness engineering.

CowAgent is lightweight, easy to deploy, and built to extend. Plug in any major LLM provider and run it 24/7 on a personal computer or server, across the web and all major IM platforms.

🌐 Website  ·  📖 Docs  ·  🚀 Quick Start  ·  🧩 Skill Hub  ·  💻 Download  ·  ☁️ Try Online


🎬 Demo

Your browser can't play this video.

Watch the demo on our website →


🌟 Highlights

Capability Description
Planning Decomposes complex tasks and executes them step by step, looping over tools until the goal is reached
Multi-Agent Build a team of Agents, each with its own role, model, skills, and knowledge, collaborating within a shared conversation
Memory Three-tier architecture (context → daily → core), automatic Deep Dream distillation, hybrid keyword + vector retrieval
Knowledge Auto-curates structured knowledge into a Markdown wiki, builds an evolving knowledge graph with visual browsing
Evolution Self-Evolution reviews conversations automatically to improve skills, follow up on unfinished tasks, and consolidate memory and knowledge, growing through everyday use
Skills One-click install from Skill Hub, GitHub, ClawHub; or create custom skills via natural-language conversation
Tools Built-in file I/O, terminal, browser, scheduler, memory retrieval, web search, and 10+ more tools — with native MCP integration
Channels Integrates with Web, WeChat, Feishu, DingTalk, WeCom, QQ, Official Accounts, Telegram, and Slack
Multimodal First-class support for text, images, voice, and files — recognition, generation, and delivery
Models Claude, GPT, Gemini, DeepSeek, Qwen, GLM, Kimi, MiniMax, Doubao, and more — swap providers from the Web console with one click
Deploy One-line installer, unified Web console, multiple deployment modes (local, Docker, server)

🏗️ Architecture

CowAgent Architecture

CowAgent is a complete Agent Harness: messages flow in through Channels; the Agent Core plans and reasons over memory, knowledge, and the available tools and skills; Models generate the response, which is sent back through the originating channel. Every layer is decoupled and independently extensible.

Read more in Architecture.


🚀 Quick Start

A one-line installer takes care of dependencies, configuration, and startup:

Linux / macOS:

bash <(curl -fsSL https://cdn.link-ai.tech/code/cow/run.sh)

Windows (PowerShell):

irm https://cdn.link-ai.tech/code/cow/run.ps1 | iex

Docker:

curl -O https://cdn.link-ai.tech/code/cow/docker-compose.yml
docker compose up -d

Once started, open http://localhost:9899 to access the Web console — your one-stop hub to chat with the Agent, configure models, connect channels, and install skills.

Deploying on a server? Set web_host to 0.0.0.0 in config.json to make the console reachable from outside, and set web_password to protect it. Don't forget to open port 9899 in your firewall or security group.

📖 Detailed guides: Quick Start · Install from Source · Upgrade

After installation, manage the service with the cow CLI:

cow start | stop | restart        # service control
cow status | logs                  # status and logs
cow update                         # pull latest code and restart
cow skill install <name>           # install a skill
cow install-browser                # install browser automation

💻 Desktop client: download the CowAgent Desktop client (macOS / Windows) — the backend is bundled, ready to use out of the box.


👥 Multi-Agent Team

Create a team of Agents, each with its own memory, capabilities, knowledge, and workspace. Each can focus on its own domain, or collaborate within a shared conversation to tackle complex tasks together. Multi-Agent teams are available on the Web, the desktop client, and IM channel integrations.

CowAgent Multi-Agent Team

See Agent Team for details.


🤖 Models

CowAgent supports all mainstream LLM providers. Chat, vision, image generation, ASR/TTS, and embeddings can each be routed to a different vendor. Providers are configured directly in the Web console — no manual file editing required.

Provider Featured Models Chat Vision Image Gen ASR TTS Embedding
DeepSeek deepseek-flash (V4.1) / pro ✅ ✅
Claude claude-opus-5 / fable-5.1 ✅ ✅
OpenAI gpt-6-astra / gpt-5.6 series ✅ ✅ ✅ ✅ ✅ ✅
Gemini gemini-3.8-flash ✅ ✅ ✅
MiniMax MiniMax-M3 ✅ ✅ ✅ ✅
GLM glm-5.3-flash, glm-5v-turbo ✅ ✅ ✅ ✅
Qwen qwen3.8-flash ✅ ✅ ✅ ✅ ✅ ✅
Kimi kimi-k3 ✅ ✅
Doubao doubao-seed-2.1 series ✅ ✅ ✅ ✅
ERNIE ernie-5.1 ✅ ✅
MiMo mimo-v2.5 / pro ✅ ✅ ✅
[LinkAI](https://docs.cowagent.ai/

readme truncated — read the full docs on github

Frequently asked questions

Is CowAgent free to use?

CowAgent is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does CowAgent do?

Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-chan

What is CowAgent written in?

CowAgent is primarily written in Python. Its source is publicly available at https://github.com/zhayujie/CowAgent, and it has 47,017 GitHub stars.