codegraph-summary
Enables AI assistants to search code summaries using Chinese business terms, with support for semantic search and PRD linkage.
README
codegraph-summary
CodeGraph 中文语义摘要工具 — 为代码符号生成中文业务摘要,支持语义搜索和 PRD 关联分析。
将代码知识图谱与 LLM 结合,让你用中文业务术语搜索代码、理解系统架构、追踪需求覆盖。
特性
- 一键初始化 —
codegraph-summary init自动构建索引 + 生成摘要 - 中文语义搜索 — 用 "交易查询"、"清退流程" 等业务术语搜索代码
- FTS5 trigram — 高质量中文子串匹配,无需分词器
- 图谱扩展 — 搜索结果展示调用链(谁调用了它、它调用了谁)
- PRD 关联 — 导入需求文档,自动关联到代码实现
- 多协议 LLM — 支持 Anthropic / OpenAI 兼容 API
- 启发式降级 — 无 LLM API Key 时仍可生成基础摘要
- 三种接口 — CLI / HTTP API / MCP Server
快速开始
安装
npm install -g codegraph-summary
需要先安装 CodeGraph:
npm install -g @colbymchenry/codegraph
一键初始化
cd your-project
codegraph-summary init
这会自动完成:
- 构建 CodeGraph 代码索引(如果不存在)
- 用 LLM 为所有导出符号生成中文摘要
配置 LLM(可选)
在项目根目录创建 .env 文件:
SUMMARY_LLM_API_KEY=your-api-key
SUMMARY_LLM_BASE_URL=https://api.anthropic.com
SUMMARY_LLM_MODEL=claude-sonnet-4-20250514
SUMMARY_LLM_API_TYPE=anthropic
不配置 API Key 也能用(启发式模式,用函数签名作为摘要)。
使用
搜索代码
codegraph-summary search "交易查询" -p /path/to/project
查看状态
codegraph-summary status -p /path/to/project
强制重新生成
codegraph-summary init -f
codegraph-summary generate -f -p /path/to/project
PRD 关联
# 导入 PRD 文档(支持 .md / .docx / .pdf / .txt)
codegraph-summary prd-import ./docs/prd.md -p /path/to/project
# 用需求描述搜索代码
codegraph-summary prd-search "用户清退流程" -p /path/to/project
# 查看需求覆盖率
codegraph-summary prd-coverage -p /path/to/project
MCP Server(AI 助手集成)
codegraph-summary mcp
在 Claude Code 的 MCP 配置中添加即可让 AI 助手直接搜索代码摘要。
HTTP API
codegraph-summary serve --port 3000
环境变量
| 变量 | 说明 | 默认值 |
|---|---|---|
SUMMARY_LLM_API_KEY |
LLM API Key | (空,启发式模式) |
SUMMARY_LLM_BASE_URL |
LLM API 地址 | (空) |
SUMMARY_LLM_MODEL |
模型名称 | (空) |
SUMMARY_LLM_API_TYPE |
anthropic 或 openai |
anthropic |
SUMMARY_LLM_BATCH_SIZE |
每批符号数量 | 10 |
SUMMARY_LLM_CONCURRENCY |
并发请求数 | 3 |
SUMMARY_VECTOR_GATEWAY_URL |
向量服务地址(可选) | (空) |
CODEGRAPH_BIN |
自定义 codegraph 路径 | (自动查找) |
系统要求
- Node.js >= 22.5.0
- CodeGraph (用于代码索引)
- PDF 支持需要
poppler-utils(macOS:brew install poppler) - DOCX 支持需要
unzip命令
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.