AI/TLDR

CowAgent

A self-hosted assistant that plans tasks, runs tools and answers wherever your team already chats

Assistants & ChatbotsOpen source
Language
Python
License
MIT

Overview

CowAgent is a self-hosted AI assistant and agent harness that grew out of chatgpt-on-wechat, one of the longest-running open-source chat-assistant projects. The rewrite keeps the thing that made the original useful — it meets people inside the messaging app they already use — and adds the machinery an agent needs to do work rather than only reply: task planning and decomposition, iterative tool execution, and a memory that persists between conversations.

The built-in tool set covers file I/O, a terminal, a browser, a scheduler, web search and vision, with MCP support for anything not bundled. Input is multimodal — text, images, voice and files. Skills install in one click from a marketplace, and agents can be grouped into multi-agent teams that share a conversation. Memory is organised in three tiers with automatic distillation, alongside an auto-curated knowledge base you can browse as a graph.

Deployment is deliberately undemanding: a one-line install script on Linux, macOS or Windows, or a Docker Compose file, after which a web console runs on port 9899. Model providers are swappable from that console and span the major hosted families — Claude, GPT, Gemini, DeepSeek, Qwen, GLM, Kimi, MiniMax, Doubao and ERNIE among them — and the assistant can be exposed through the web console plus Telegram, Slack, Discord, WeChat, Feishu/Lark, DingTalk, WeCom and QQ. It is MIT-licensed, with the project noting it is open-sourced for technical research and learning.

What it does

  • Task planning and decomposition with iterative tool execution
  • Built-in file, terminal, browser, scheduler, web-search and vision tools, plus MCP integration
  • Three-tier memory with automatic distillation, and an auto-curated knowledge base with a graph view
  • Multi-agent teams that share a conversation
  • One-click skill installation from a marketplace
  • Multimodal input: text, images, voice and files
  • Swappable model providers and a dozen messaging channels, configured from a web console

Getting started

CowAgent installs with a single command and then runs behind a local web console. The commands below come from the project README.

Install on Linux or macOS

One script fetches and starts the assistant.

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

Install on Windows

The PowerShell equivalent of the same installer.

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

Or run it with Docker

Pull the published Compose file and bring the stack up in the background.

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

Open the web console

The console is where models, channels, tools and skills are configured.

texttext
http://localhost:9899

Pick a model and connect a channel

Choose a provider from the console — Claude, GPT, Gemini, DeepSeek, Qwen, GLM, Kimi, MiniMax, Doubao and ERNIE are among those supported — then connect the messaging platforms you want the assistant to answer in.

texttext
Console → Models → select provider
Console → Channels → Telegram / Slack / Discord / WeChat / Feishu / DingTalk / WeCom / QQ

Commands and code are distilled from the project's own documentation — always check the official repo for the latest.

When to use it

  • Reach for it when the assistant has to live inside the messaging apps a team already uses, not a separate web app
  • Reach for it when you want a self-hosted assistant that can actually run terminal, file and browser tools
  • Reach for it when conversations should build up long-term memory and a browsable knowledge base
  • Reach for it when you need to swap model providers from a console instead of redeploying

How CowAgent compares

CowAgent alongside other open-source assistants & chatbots tools AI/TLDR tracks, ranked by GitHub stars.

ToolStarsWhat it does
OpenClaw★ 390kOpenClaw is a self-hosted personal AI assistant that answers you on WhatsApp, Telegram, Slack, Discord, and many other channels, with voice and a live visual canvas.
Hermes Agent★ 246kA self-improving personal AI agent from Nous Research that builds skills from experience, remembers across sessions, and reaches you on Telegram, Discord, Slack, and more.
Odysseus★ 87.3kA self-hosted AI workspace that puts chat, agents, deep research, documents, email, notes, tasks and calendar behind one Docker Compose stack, over local or API models.
CowAgent★ 47kA self-hosted assistant that plans tasks, runs tools and answers wherever your team already chats
AstrBot★ 40.6kAn all-in-one agent chatbot platform that puts LLM conversations, tools, knowledge bases and a plugin marketplace inside messaging apps like Telegram, Slack, Discord, QQ and Feishu.
OpenHuman★ 39.8kA local-first desktop personal AI for macOS, Windows and Linux that keeps a compressed memory tree on your machine and orchestrates checkpointed research and automation workflows.
MindsHub★ 39.7kAn agent workspace for knowledge work and software development that runs swappable open-source agent harnesses against your choice of frontier or open models.
Khoj★ 37.4kAn open-source, self-hostable personal AI that chats with any local or online LLM, answers from your own documents and the web, and runs custom agents.