{ "markdown": "

\"CowAgent\"

\n\n

\n \"Latest\n \"License:\n \"Stars\"\n \"Docs\"\n \"WeChat\n \"Discord\"\n

\n\n

\n \"zhayujie%2FCowAgent\n

\n\n

\n [English] | [中文] | [繁體中文] | [日本語]\n

\n\n**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.\n\nCowAgent 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.\n\n

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

\n\n
\n\n## 🎬 Demo\n\n

\n \n

\n\n
\n\n## 🌟 Highlights\n\n| Capability | Description |\n| :--- | :--- |\n| [Planning](https://docs.cowagent.ai/intro/architecture) | Decomposes complex tasks and executes them step by step, looping over tools until the goal is reached |\n| [Multi-Agent](https://docs.cowagent.ai/multi-agent/team) | Build a team of Agents, each with its own role, model, skills, and knowledge, collaborating within a shared conversation |\n| [Memory](https://docs.cowagent.ai/memory/index) | Three-tier architecture (context → daily → core), automatic Deep Dream distillation, hybrid keyword + vector retrieval |\n| [Knowledge](https://docs.cowagent.ai/knowledge/index) | Auto-curates structured knowledge into a Markdown wiki, builds an evolving knowledge graph with visual browsing |\n| [Evolution](https://docs.cowagent.ai/memory/self-evolution) | Self-Evolution reviews conversations automatically to improve skills, follow up on unfinished tasks, and consolidate memory and knowledge, growing through everyday use |\n| [Skills](https://docs.cowagent.ai/skills/index) | One-click install from [Skill Hub](https://skills.cowagent.ai/), GitHub, ClawHub; or create custom skills via natural-language conversation |\n| [Tools](https://docs.cowagent.ai/tools/index) | Built-in file I/O, terminal, browser, scheduler, memory retrieval, web search, and 10+ more tools — with native MCP integration |\n| [Channels](https://docs.cowagent.ai/channels/index) | Integrates with Web, WeChat, Feishu, DingTalk, WeCom, QQ, Official Accounts, Telegram, and Slack |\n| Multimodal | First-class support for text, images, voice, and files — recognition, generation, and delivery |\n| [Models](https://docs.cowagent.ai/models/index) | Claude, GPT, Gemini, DeepSeek, Qwen, GLM, Kimi, MiniMax, Doubao, and more — swap providers from the Web console with one click |\n| [Deploy](https://docs.cowagent.ai/guide/quick-start) | One-line installer, unified Web console, multiple deployment modes (local, Docker, server) |\n\n
\n\n## 🏗️ Architecture\n\n\"CowAgent\n\nCowAgent 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.\n\nRead more in [Architecture](https://docs.cowagent.ai/intro/architecture).\n\n
\n\n## 🚀 Quick Start\n\nA one-line installer takes care of dependencies, configuration, and startup:\n\n**Linux / macOS:**\n\n```bash\nbash <(curl -fsSL https://cdn.link-ai.tech/code/cow/run.sh)\n```\n\n**Windows (PowerShell):**\n\n```powershell\nirm https://cdn.link-ai.tech/code/cow/run.ps1 | iex\n```\n\n**Docker:**\n\n```bash\ncurl -O https://cdn.link-ai.tech/code/cow/docker-compose.yml\ndocker compose up -d\n```\n\nOnce 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.\n\n> 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.\n\n> 📖 Detailed guides: [Quick Start](https://docs.cowagent.ai/guide/quick-start) · [Install from Source](https://docs.cowagent.ai/guide/manual-install) · [Upgrade](https://docs.cowagent.ai/guide/upgrade)\n\nAfter installation, manage the service with the [cow CLI](https://docs.cowagent.ai/cli/index):\n\n```bash\ncow start | stop | restart # service control\ncow status | logs # status and logs\ncow update # pull latest code and restart\ncow skill install # install a skill\ncow install-browser # install browser automation\n```\n\n> 💻 Desktop client: download the **[CowAgent Desktop client](https://cowagent.ai/download/)** (macOS / Windows) — the backend is bundled, ready to use out of the box.\n\n
\n\n## 👥 Multi-Agent Team\n\nCreate 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.\n\n\"CowAgent\n\n> See [Agent Team](https://docs.cowagent.ai/multi-agent/team) for details.\n\n
\n\n## 🤖 Models\n\nCowAgent 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.\n\n| Provider | Featured Models | Chat | Vision | Image Gen | ASR | TTS | Embedding |\n| --- | --- | :-: | :-: | :-: | :-: | :-: | :-: |\n| [DeepSeek](https://docs.cowagent.ai/models/deepseek) | deepseek-flash (V4.1) / pro | ✅ | ✅ | | | | |\n| [Claude](https://docs.cowagent.ai/models/claude) | claude-opus-5-5 / fable-5.1 | ✅ | ✅ | | | | |\n| [OpenAI](https://docs.cowagent.ai/models/openai) | gpt-6.1-sol / gpt-6 series | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |\n| [Gemini](https://docs.cowagent.ai/models/gemini) | gemini-3.8-flash | ✅ | ✅ | ✅ | | | |\n| [MiniMax](https://docs.cowagent.ai/models/minimax) | MiniMax-M3 | ✅ | ✅ | ✅ | | ✅ | |\n| [GLM](https://docs.cowagent.ai/models/glm) | glm-5.3-flash, glm-5v-turbo | ✅ | ✅ | | ✅ | | ✅ |\n| [Qwen](https://docs.cowagent.ai/models/qwen) | qwen3.8-flash | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |\n| [Kimi](https://docs.cowagent.ai/models/kimi) | kimi-k3 | ✅ | ✅ | | | | |\n| [Doubao](https://docs.cowagent.ai/models/doubao) | doubao-seed-2.1 series | ✅ | ✅ | ✅ | | | ✅ |\n| [ERNIE](https://docs.cowagent.ai/models/qianfan) | ernie-5.1 | ✅ | ✅ | | | | |\n| [MiMo](https://docs.cowagent.ai/models/mimo) | mimo-v2.5 / pro | ✅ | ✅ | | | ✅ | |\n| [LinkAI](https://docs.cowagent.ai/models/linkai) | One key for 100+ models | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |\n| [Custom](https://docs.cowagent.ai/models/custom) | Local models / third-party proxy | ✅ | | | | | |\n\n> For details on each provider, see the [Models overview](https://docs.cowagent.ai/models/index).\n\n
\n\n## 💬 Channels\n\nA single Agent instance can serve multiple channels in parallel. Most channels can be onboarded right from the Web console.\n\n| Channel | Text | Image | File | Voice | Group |\n| --- | :-: | :-: | :-: | :-: | :-: |\n| [Web Console](https://docs.cowagent.ai/channels/web) (default) | ✅ | ✅ | ✅ | ✅ | |\n| [Telegram](https://docs.cowagent.ai/channels/telegram) | ✅ | ✅ | ✅ | ✅ | ✅ |\n| [Slack](https://docs.cowagent.ai/channels/slack) | ✅ | ✅ | ✅ | | ✅ |\n| [Discord](https://docs.cowagent.ai/channels/discord) | ✅ | ✅ | ✅ | | ✅ |\n| [WeChat](https://docs.cowagent.ai/channels/weixin) | ✅ | ✅ | ✅ | ✅ | |\n| [Feishu / Lark](https://docs.cowagent.ai/channels/feishu) | ✅ | ✅ | ✅ | ✅ | ✅ |\n| [DingTalk](https://docs.cowagent.ai/channels/dingtalk) | ✅ | ✅ | ✅ | ✅ | ✅ |\n| [WeCom Bot](https://docs.cowagent.ai/channels/wecom-bot) | ✅ | ✅ | ✅ | ✅ | ✅ |\n| [QQ](https://docs.cowagent.ai/channels/qq) | ✅ | ✅ | ✅ | | ✅ |\n| [WeCom App](https://docs.cowagent.ai/channels/wecom) | ✅ | ✅ | ✅ | ✅ | |\n| [WeChat Customer Service](https://docs.cowagent.ai/channels/wechat-kf) | ✅ | ✅ | ✅ | ✅ | |\n| [WeChat Official Account](https://docs.cowagent.ai/channels/wechatmp) | ✅ | ✅ | | ✅ | |\n\n> See the [Channels overview](https://docs.cowagent.ai/channels/index) for setup details.\n\n\"CowAgent\n\n*The Web console is the default channel and the unified entry point to configure models, channels, skills, memory, and more.*\n\n
\n\n## 🧠 Memory & Knowledge Base\n\n**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](https://docs.cowagent.ai/memory/index) · [Deep Dream](https://docs.cowagent.ai/memory/deep-dream).\n\n**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](https://docs.cowagent.ai/knowledge/index).\n\n\n \n \n \n \n
\n \"Long-term\n

Long-term Memory · Three-tier architecture + Deep Dream

\n 		\n \"Personal\n

Knowledge Base · Auto-curated Markdown wiki

\n
\n\n
\n\n## 🔧 Tools & Skills\n\n**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.\n\n### Tool System\n\n**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`).\n\n**MCP protocol** integrates the open ecosystem of [Model Context Protocol](https://modelcontextprotocol.io) servers. A single `mcp.json` is enough — supports stdio / SSE transports, hot reload, and zero-code integration.\n\nLearn more: [Tools overview](https://docs.cowagent.ai/tools/index) · [MCP integration](https://docs.cowagent.ai/tools/mcp).\n\n### Skills System\n\n- **[Skill Hub](https://skills.cowagent.ai/)** — open skill marketplace: browse, search, install in one click\n- **GitHub / ClawHub / URL and more** — install skills from any source\n- **Conversational authoring** — generate custom skills through dialogue with `skill-creator`; turn any workflow or third-party API into a reusable skill\n\n```bash\n/skill list # list installed skills\n/skill search # search the marketplace\n/skill install # one-click install\n```\n\nLearn more: [Skills overview](https://docs.cowagent.ai/skills/index) · [Creating Skills](https://docs.cowagent.ai/skills/create).\n\n
\n\n## 🏷 Changelog\n\n> **2026.09.30:** [v2.2.0](https://github.com/zhayujie/CowAgent/releases/tag/2.2.0) — Capabilities center, multi-Agent collaboration improvements, Web console rebuild, higher model cache hit rates, broad stability and security hardening.\n\n> **2026.09.14:** [v2.1.9](https://github.com/zhayujie/CowAgent/releases/tag/2.1.9) — Multi-Agent collaboration refinements, configurable model lists and multiple fallback models, channel integration fixes, new image models (gpt-image-2.5), plus voice fixes.\n\n> **2026.09.10:** [v2.1.8](https://github.com/zhayujie/CowAgent/releases/tag/2.1.8) — Multi-Agent teams, manual scheduled task creation, context-usage visualization, new models and search providers, workspace file editing.\n\n> **2026.08.20:** [v2.1.7](https://github.com/zhayujie/CowAgent/releases/tag/2.1.7) — Multiple workspaces, session-level permission modes, task notifications, desktop improvements, plus new model support.\n\n> **2026.08.12:** [v2.1.6](https://github.com/zhayujie/CowAgent/releases/tag/2.1.6) — Sub agents for parallel task delegation, reasoning-effort settings, a pluggable memory vector backend, plus experience and security improvements.\n\n> **2026.07.29:** [v2.1.5](https://github.com/zhayujie/CowAgent/releases/tag/2.1.5) — Workspace with file preview, core tool improvements (file search, write-time validation, background commands), context compaction (`/compact`), one-click prompt optimization, security hardening.\n\n> **2026.07.20:** [v2.1.4](https://github.com/zhayujie/CowAgent/releases/tag/2.1.4) — Desktop experience improvements, MCP OAuth authorization, Lark channel enhancements, scheduler improvements and data backup, new models.\n\n> **2026.07.08:** [v2.1.3](https://github.com/zhayujie/CowAgent/releases/tag/2.1.3) — [Desktop client](https://cowagent.ai/download/) for macOS / Windows, knowledge base document management, on-demand MCP tool retrieval, Traditional Chinese support, new models.\n\n> **2026.06.18:** [v2.1.2](https://github.com/zhayujie/CowAgent/releases/tag/2.1.2) — 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.\n\n> **2026.06.09:** [v2.1.1](https://github.com/zhayujie/CowAgent/releases/tag/2.1.1) — 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.\n\n> **2026.06.01:** [v2.1.0](https://github.com/zhayujie/CowAgent/releases/tag/2.1.0) — 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).\n\nFull history: [Release Notes](https://docs.cowagent.ai/releases/overview)\n\n
\n\n## 🤝 Community & Support\n\nJoin our [**Discord server**](https://discord.gg/9U8eA8v9TR) to ask questions, share skills, and follow development:\n\n\"Join\n\nYou can also [file an issue](https://github.com/zhayujie/CowAgent/issues) on GitHub, or scan the QR code below to join our WeChat group:\n\n\n\n
\n\n## 🔗 Related Projects\n\n- **[Cow Skill Hub](https://github.com/zhayujie/cow-skill-hub)** — open skill marketplace for AI Agents; works with CowAgent, OpenClaw, Claude Code, and more\n- **[bot-on-anything](https://github.com/zhayujie/bot-on-anything)** — lightweight LLM application framework with integrations for Slack, Telegram, Discord, Gmail, and more\n- **[AgentMesh](https://github.com/MinimalFuture/AgentMesh)** — open-source multi-agent framework for solving complex problems through team collaboration\n\n
\n\n## 🏢 Enterprise Services\n\n[**LinkAI**](https://link-ai.tech/) is an all-in-one AI Agent platform for enterprises and developers, offering managed hosting and enterprise-grade support for CowAgent:\n\n- **🚀 Zero-deployment hosted runtime** — spin up a [CowAgent online assistant](https://link-ai.tech/cowagent/create) in under a minute, no server required\n- **🧠 Agent infrastructure** — unified access to LLMs, knowledge bases, databases, skills, and workflows; plug-and-play building blocks that extend what CowAgent can do\n- **🏢 Team & enterprise features** — workspaces, role-based access, audit logs, and private deployment for production use cases\n\nFor enterprise inquiries: sales@simple-future.tech or [scan the QR code](https://cdn.link-ai.tech/contact/customer-support.png) to reach our team on WeChat.\n\n
\n\n## 🛠️ Development & Contributing\n\nAll kinds of contributions are welcome — new features, bug fixes, performance improvements, docs, or sharing your own skills on the [Skill Hub](https://skills.cowagent.ai/submit). See [CONTRIBUTING.md](CONTRIBUTING.md) to get started, then open an Issue to discuss or send a PR directly.\n\n⭐ Star the project to show your support, and Watch → Custom → Releases to get notified of new versions. PRs and Issues are always welcome.\n\n## 🌟 Contributors\n\n![cow contributors](https://contrib.rocks/image?repo=zhayujie/CowAgent&max=1000)\n\n
\n\n## ⚠️ Disclaimer\n\n1. This project is licensed under the [MIT License](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.\n2. **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.\n3. CowAgent is a pure open-source project and does not participate in, authorize, or issue any cryptocurrency.\n\n
\n\n## 📌 Project Renaming Notice\n\nThis 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.\n", "bytes": 20098, "sha": "6cfa0b75abc274c5ff183dcb6b731aab302c9e2d745986efe93e7d469e87e078", "repo_slug": "zhayujie/cowagent", "fonte": "repo", "truncated": false, "api": "https://api.agentalog.com/api/listings/skl_zhayujie_cowagent_knowledge_wiki_14f2a9f4/readme" }