开源 CowAgent 提供多智能体、多模型、多渠道 AI 助手,一行安装
开源个人 AI 助手与 Agent Harness。规划任务,运行工具与技能,通过记忆与知识自我进化。
多智能体、多模型、多渠道。轻量、可扩展,一行安装。
Skill 会改变智能体的行为并可能包含可执行脚本。安装前请先阅读其 SKILL.md 与脚本,社区来源尤其要谨慎。
npx skills add zhayujie/CowAgent
npx skills add zhayujie/CowAgent -g
npx skills add zhayujie/CowAgent -l
命令使用开源的 skills CLI(vercel-labs/skills),支持 Claude Code、Cursor、Codex 等多种智能体。
摘自项目自己的说明,具体以项目主页为准。
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_hostto0.0.0.0inconfig.jsonto make the console reachable from outside, and setweb_passwordto protect it. Don't forget to open port9899in 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 # install a skill
cow install-browser # install browser automation
<br/>💻 Desktop client: download the CowAgent Desktop client (macOS / Windows) — the backend is bundled, ready to use out of the box.