CowAgent

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.

🎬 Demo

🌟 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 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.

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-5-5 / sonnet-5-5	✅	✅
OpenAI	gpt-6.1-terra / gpt-6.1-sol	✅	✅	✅	✅	✅	✅
Gemini	gemini-4-argon	✅	✅	✅
MiniMax	MiniMax-M3.1-Flash / M3	✅	✅	✅		✅
GLM	glm-5.3-flash, glm-5v-turbo	✅	✅		✅		✅
Qwen	qwen3.8-flash	✅	✅	✅	✅	✅	✅
Kimi	kimi-k3.1-pro / kimi-k3	✅	✅
Doubao	doubao-seed-2.1 series	✅	✅	✅			✅
ERNIE	ernie-5.1	✅	✅
MiMo	mimo-v2.6-pro / flash	✅	✅		✅	✅
LinkAI	One key for 100+ models	✅	✅	✅	✅	✅	✅
Custom	Local models / third-party proxy	✅

For details on each provider, see the Models overview.

💬 Channels

A single Agent instance can serve multiple channels in parallel. Most channels can be onboarded right from the Web console.

Channel	Text	Image	File	Voice	Group
Web Console (default)	✅	✅	✅	✅
Telegram	✅	✅	✅	✅	✅
Slack	✅	✅	✅		✅
Discord	✅	✅	✅		✅
WeChat	✅	✅	✅	✅
Feishu / Lark	✅	✅	✅	✅	✅
DingTalk	✅	✅	✅	✅	✅
WeCom Bot	✅	✅	✅	✅	✅
QQ	✅	✅	✅		✅
WeCom App	✅	✅	✅	✅
WeChat Customer Service	✅	✅	✅	✅
WeChat Official Account	✅	✅		✅

See the Channels overview for setup details.

The Web console is the default channel and the unified entry point to configure models, channels, skills, memory, and more.

🧠 Memory & Knowledge Base

Long-term memory uses a three-tier architecture: conversation context (short-term) → daily memory (mid-term) → MEMORY.md (long-term). A nightly Deep Dream pass distills scattered memories into refined long-term entries and a narrative journal. See Long-term Memory · Deep Dream.

Personal knowledge base complements the time-ordered memory by organizing structured knowledge by topic. The Agent automatically curates valuable information from conversations, maintains cross-references and indexes, and the Web console offers an interactive knowledge-graph view. See Personal Knowledge Base.

🔧 Tools & Skills

Tools are atomic capabilities the Agent uses to interact with system resources. Skills are higher-level workflows defined by a manifest file that compose multiple tools to accomplish complex tasks.

Tool System

Built-in tools cover file I/O (read / write / edit / ls), terminal (bash), file sending (send), memory retrieval (memory), environment variables (env_config), web fetching (web_fetch), scheduling (scheduler), web search (web_search), vision (vision), and browser automation (browser).

MCP protocol integrates the open ecosystem of Model Context Protocol servers. A single mcp.json is enough — supports stdio / SSE transports, hot reload, and zero-code integration.

Learn more: Tools overview · MCP integration.

Skills System

• Skill Hub — open skill marketplace: browse, search, install in one click
• GitHub / ClawHub / URL and more — install skills from any source
• Conversational authoring — generate custom skills through dialogue with skill-creator; turn any workflow or third-party API into a reusable skill

/skill list                   # list installed skills
/skill search <keyword>        # search the marketplace
/skill install <name>          # one-click install

Learn more: Skills overview · Creating Skills.

🏷 Changelog

2026.10.30: v2.2.2 — Standalone guest pages and embeddable chat windows, custom themes, native multimodal input for the main model, new models, tool, channel and security improvements.

2026.10.14: v2.2.1 — Artifacts center and custom menu, open Agent Chat API, prompt caching and context cost savings, tool, channel and security improvements.

2026.09.30: v2.2.0 — Capabilities center, multi-Agent collaboration improvements, Web console rebuild, higher model cache hit rates, broad stability and security hardening.

2026.09.14: v2.1.9 — Multi-Agent collaboration refinements, configurable model lists and multiple fallback models, channel integration fixes, new image models (gpt-image-2.5), plus voice fixes.

2026.09.10: v2.1.8 — Multi-Agent teams, manual scheduled task creation, context-usage visualization, new models and search providers, workspace file editing.

2026.08.20: v2.1.7 — Multiple workspaces, session-level permission modes, task notifications, desktop improvements, plus new model support.

2026.08.12: v2.1.6 — Sub agents for parallel task delegation, reasoning-effort settings, a pluggable memory vector backend, plus experience and security improvements.

2026.07.29: v2.1.5 — Workspace with file preview, core tool improvements (file search, write-time validation, background commands), context compaction (/compact), one-click prompt optimization, security hardening.

2026.07.20: v2.1.4 — Desktop experience improvements, MCP OAuth authorization, Lark channel enhancements, scheduler improvements and data backup, new models.

2026.07.08: v2.1.3 — Desktop client for macOS / Windows, knowledge base document management, on-demand MCP tool retrieval, Traditional Chinese support, new models.

2026.06.18: v2.1.2 — Web console upgrades (scheduled task management, knowledge base categories, multiple custom model providers), Self-Evolution improvements, new models (kimi-k2.7-code, glm-5.2), security hardening and refinements.

2026.06.09: v2.1.1 — Self-Evolution, Web console upgrades (message management, parallel sessions), cross-platform MCP enhancements with concurrent calls, new models (MiniMax-M3, qwen3.7-plus), Python 3.13 support.

2026.06.01: v2.1.0 — Internationalization, new channels (Telegram, Discord, Slack, WeChat Customer Service), CLI interaction upgrades, streamlined one-line install, MCP Streamable HTTP support, new models (claude-opus-4-8, MiMo).

Full history: Release Notes

🤝 Community & Support

Join our Discord server to ask questions, share skills, and follow development:

You can also file an issue on GitHub, or scan the QR code below to join our WeChat group:

🔗 Related Projects

• Cow Skill Hub — open skill marketplace for AI Agents; works with CowAgent, OpenClaw, Claude Code, and more
• bot-on-anything — lightweight LLM application framework with integrations for Slack, Telegram, Discord, Gmail, and more
• AgentMesh — open-source multi-agent framework for solving complex problems through team collaboration

🏢 Enterprise Services

LinkAI is an all-in-one AI Agent platform for enterprises and developers, offering managed hosting and enterprise-grade support for CowAgent:

• 🚀 Zero-deployment hosted runtime — spin up a CowAgent online assistant in under a minute, no server required
• 🧠 Agent infrastructure — unified access to LLMs, knowledge bases, databases, skills, and workflows; plug-and-play building blocks that extend what CowAgent can do
• 🏢 Team & enterprise features — workspaces, role-based access, audit logs, and private deployment for production use cases

For enterprise inquiries: sales@simple-future.tech or scan the QR code to reach our team on WeChat.

🛠️ Development & Contributing

All kinds of contributions are welcome — new features, bug fixes, performance improvements, docs, or sharing your own skills on the Skill Hub. See CONTRIBUTING.md to get started, then open an Issue to discuss or send a PR directly.

⭐ Star the project to show your support, and Watch → Custom → Releases to get notified of new versions. PRs and Issues are always welcome.

🌟 Contributors

[cow contributors]

⚠️ 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 regular chat — pick models that balance quality and cost. The Agent has access to your local operating system, so only deploy it in trusted environments.
3. CowAgent is a pure open-source project and does not participate in, authorize, or issue any cryptocurrency.

📌 Project Renaming Notice

This project was previously named chatgpt-on-wechat and is now officially CowAgent. The old GitHub URL redirects automatically; existing users may optionally run git remote set-url origin https://github.com/zhayujie/CowAgent.git to update the local remote.