经 AI Skill Hub 精选评估,混合智能代理 获评「强烈推荐」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
混合智能代理 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
混合智能代理 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/brcampidelli/chimera-agent
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"------": {
"command": "npx",
"args": ["-y", "chimera-agent"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 混合智能代理 执行以下任务... Claude: [自动调用 混合智能代理 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"______": {
"command": "npx",
"args": ["-y", "chimera-agent"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<img src="assets/logo-wide.png" alt="Chimera logo" width="460" />
You need Python 3.11+ and uv (a fast Python installer).
1. Install — from PyPI:
pip install chimera-agent That gives you the chimera command. (The examples below use uv run chimera for a from-source checkout — with a pip install, just run chimera ….) To hack on Chimera itself, clone the repo: git clone https://github.com/brcampidelli/chimera-agent.git
cd chimera-agent
uv sync --extra dev
2. Add one AI provider key. The easiest is an OpenRouter key — one key unlocks 100+ models. ```bash cp .env.example .env
**3. Check everything is ready**bash uv run chimera doctor
**4. Try it**bash uv run chimera chat # have a conversation (it remembers) uv run chimera run "Explain what you can do in 3 bullets" uv run chimera fuse "What's the best way to learn to cook?" --show-panel # see several models blended uv run chimera solve "add a hello() function to app.py and a test for it" --verify "pytest -q"
**Run it on a server (so it works 24/7):**bash docker compose up -d # gateway + scheduler; restarts automatically Full guide (Docker or systemd, scheduling, backups, security): **[docs/deploy.md](docs/deploy.md)**.
**5. Do something real in 5 minutes: email triage.** Point Chimera at your inbox and get a
ten-second digest — read-only, classify URGENT / PERSONAL / NEWSLETTER / COLD-SALES, and
optionally schedule it every morning:bash uv run chimera workflow examples/email_triage/triage.yaml -w ./triage_workspace ``` Setup + daily scheduling + honest caveats: examples/email_triage/README.md.
Chimera doesn't try to out-channel the giant agent projects. It bets on the three things a real reverse-engineering study of five leaders (OpenClaw, Hermes, nanobot, CrewAI, LangGraph) found they all leave open — and makes them its core:
bench/terminal_bench/RESULTS.md), including retracting a wrong intermediate read once the control arm was measured. Null results and self-corrections ship too; that's the point.In one line: the governed, self-evolving agent — proved and governed. It's alpha, and it says so.
创新性的AI代理项目,值得关注
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:混合智能代理 的核心功能完整,质量优秀。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | chimera-agent |
| Topics | aiai-agentpython |
| GitHub | https://github.com/brcampidelli/chimera-agent |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-07-13 · 更新时间:2026-07-13 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端