Baby Gpt
FreeNot checkedExposes baby-gpt's tools (shell, filesystem, search, memory, GitHub integration, etc.) to Claude Desktop or Cursor, enabling natural language interaction with t
About
Exposes baby-gpt's tools (shell, filesystem, search, memory, GitHub integration, etc.) to Claude Desktop or Cursor, enabling natural language interaction with these capabilities.
README
从零实现的通用 Agent,完整覆盖 ReAct 架构的每一个环节。 Hello Agents 课程毕业设计项目。
快速开始
方式一:本地运行(开发者)
前置条件:Python 3.10+,Node.js 18+(MCP 功能需要)
# 1. 克隆仓库
git clone <repo-url>
cd baby-gpt
# 2. 安装依赖
make install
# 或者手动:python3 -m venv venv && venv/bin/python3 -m pip install -r requirements.txt
# 3. 配置 API Key
cp .env.example .env
# 编辑 .env,填入你的 DEEPSEEK_API_KEY
# 4. 启动
make run
方式二:Docker 运行(推荐分发给他人)
前置条件:Docker
# 1. 构建镜像
make docker-build
# 2. 配置 Key(只需做一次)
cp .env.example .env
# 编辑 .env
# 3. 运行
make docker-run
配置文件
复制 .env.example 为 .env,填入以下 Key:
| 变量名 | 必填 | 说明 |
|---|---|---|
LLM_PROVIDER |
可选 | LLM 提供方:anthropic(Claude 原生 tool_use)或 deepseek(默认,ReAct 文本) |
DEEPSEEK_API_KEY |
✅* | DeepSeek API Key(默认主 LLM;用 Claude 时非必填) |
ANTHROPIC_API_KEY |
✅* | Claude API Key(LLM_PROVIDER=anthropic 时必填) |
ANTHROPIC_MODEL |
可选 | Claude 模型,默认 claude-opus-4-8 |
OPENAI_API_KEY |
可选 | 图片生成功能需要 |
GITHUB_PERSONAL_ACCESS_TOKEN |
可选 | 启用 GitHub MCP(26 个工具) |
TAVILY_API_KEY |
可选 | 更好的网络搜索,无则自动用 DuckDuckGo |
功能
- 双 LLM 后端 — DeepSeek(ReAct 文本,默认)/ Claude(Anthropic SDK 原生
tool_use结构化调用),LLM_PROVIDER一键切换 - ReAct 核心循环 — Thought → Action → Observation 迭代
- 工具注册系统 —
@register_tool装饰器,tools/目录自动扫描 - 远程 Skill 加载 —
find_skills+load_skill,运行时扩展能力 - 能力自扩展 — 遇到未知任务自动搜索并安装工具
- 多轮对话 —
AgentSession滑动窗口,保留最近 20 轮上下文 - 网络搜索 — DuckDuckGo(免费)/ Tavily(可选)双后端
- GitHub MCP — 连接 GitHub MCP Server,读写仓库、搜索代码、管理 Issue/PR
- RAG 记忆 — Chroma 向量数据库,
remember/recall工具 - MCP Server — 把自己的工具暴露给 Claude Desktop / Cursor
项目结构
baby-gpt/
├── core/
│ ├── agent.py ← ReAct 主循环
│ ├── llm_client.py ← LLM 调用(DeepSeek / OpenAI / Claude·Anthropic SDK)
│ ├── registry.py ← 工具注册中心
│ ├── session.py ← 多轮对话管理
│ └── tracer.py ← 可观测性(Timeline + 日志)
├── tools/
│ ├── shell.py ← Shell 执行(黑名单安全模型)
│ ├── filesystem.py ← 文件读写
│ ├── search.py ← 网络搜索
│ ├── memory.py ← RAG 记忆
│ ├── utils.py ← 计算器等工具
│ └── mcp_client.py ← MCP Client(连接外部 MCP Server)
├── skills/
│ └── remote_loader.py ← find_skills + load_skill
├── mcp_server/
│ └── server.py ← MCP Server(暴露给 Claude Desktop)
├── main.py ← 启动入口
├── Dockerfile
├── Makefile
└── .env.example
接入 Claude Desktop(MCP Server 模式)
在 ~/Library/Application Support/Claude/claude_desktop_config.json 添加:
{
"mcpServers": {
"baby-gpt": {
"command": "/path/to/baby-gpt/venv/bin/python",
"args": ["/path/to/baby-gpt/mcp_server/server.py"]
}
}
}
或者 Docker 方式:
{
"mcpServers": {
"baby-gpt": {
"command": "docker",
"args": ["run", "-i", "--rm", "-v", "/path/to/.env:/app/.env", "baby-gpt", "python", "mcp_server/server.py"]
}
}
}
Installing Baby Gpt
This server has no published package — it is built from source. Open the repository and follow its README.
▸ github.com/MiaMia-Li/baby-gptFAQ
Is Baby Gpt MCP free?
Yes, Baby Gpt MCP is free — one-click install via Unyly at no cost.
Does Baby Gpt need an API key?
No, Baby Gpt runs without API keys or environment variables.
Is Baby Gpt hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Baby Gpt in Claude Desktop, Claude Code or Cursor?
Open Baby Gpt on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
GitHub
PRs, issues, code search, CI status
by GitHubFilesystem
Secure file operations with configurable access controls.
Memory
Knowledge graph-based persistent memory system.
Template MCP Server
A CLI tool to create a new Model Context Protocol server project with TypeScript support, dual transport options, and an extensible structure
by mcpdotdirectCompare Baby Gpt with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All development MCPs
