CowAgent

zhayujie/CowAgent

Open-source super AI assistant & Agent Harness

46k
Stars
10k
Forks
26
Open issues
304
Watchers
Python MITLast pushed Jul 7, 2026

Overview

CowAgent allows for multi-model and multi-channel interaction with AI assistants. It can plan tasks, run tools, and maintain a personal knowledge base and long-term memory.

Categories

Tags

Similar tools

Install

pip install CowAgent

README

CowAgent

Latest release License: MIT Stars Docs

zhayujie%2FCowAgent | Trendshift

[English] | [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, 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  ·  ☁️ Try Online


🌟 Highlights

CapabilityDescription
PlanningDecomposes complex tasks and executes them step by step, looping over tools until the goal is reached
MemoryThree-tier architecture (context → daily → core), automatic Deep Dream distillation, hybrid keyword + vector retrieval
KnowledgeAuto-curates structured knowledge into a Markdown wiki, builds an evolving knowledge graph with visual browsing
EvolutionSelf-Evolution reviews conversations automatically to improve skills, follow up on unfinished tasks, and consolidate memory and knowledge, growing through everyday use
SkillsOne-click install from Skill Hub, GitHub, ClawHub; or create custom skills via natural-language conversation
ToolsBuilt-in file I/O, terminal, browser, scheduler, memory retrieval, web search, and 10+ more tools — with native MCP integration
ChannelsIntegrates with Web, WeChat, Feishu, DingTalk, WeCom, QQ, Official Accounts, Telegram, and Slack
MultimodalFirst-class support for text, images, voice, and files — recognition, generation, and delivery
ModelsClaude, GPT, Gemini, DeepSeek, Qwen, GLM, Kimi, MiniMax, Doubao, and more — swap providers from the Web console with one click
DeployOne-line installer, unified Web console, multiple deployment modes (local, Docker, server)

🏗️ Architecture

<img src="https://cdn.jsdelivr.net/gh/zhayujie/cowagent-assets@main/architecture/en/architec