Turns a codebase, its docs, schemas and PDFs into a queryable knowledge graph for AI coding assistants, built locally with tree-sitter AST parsing.
vitali87/code-graph-rag
Parses multi-language codebases into a knowledge graph and lets you query, search, and edit the code in plain English via an AI agent.
Open source альтернатива:Sourcegraph Cody
GitHub Copilot
- Звёзды
- 5,264
- Форки
- 0
- Открытые issues
- 0
- Последний коммит
- позавчера
Ключевые возможности
- 01Builds a knowledge graph of functions, classes, methods, and modules across many languages
- 02Answers natural-language questions by generating and running Cypher queries
- 03Edits code with AST-based patching and a diff preview before changes apply
- 04Detects dead code by following call and reference edges from entry points
- 05Runs as an MCP server for Claude Code and other MCP clients
- 06Stores the graph in an embedded SQLite file with no database server required
Сценарии использования
- Onboarding onto a large multi-language monorepo and finding where logic lives
- Locating a function's source by name or intent during code review
- Finding unused functions before a refactor or cleanup
- Giving an AI coding assistant structured context about an existing codebase
Темы
Частые вопросы
- Что такое code-graph-rag?
- Parses multi-language codebases into a knowledge graph and lets you query, search, and edit the code in plain English via an AI agent.
- code-graph-rag можно использовать бесплатно? Какая у него лицензия?
- code-graph-rag распространяется с открытым исходным кодом под лицензией MIT. Перед использованием в коммерческих продуктах проверьте условия лицензии.
- code-graph-rag всё ещё поддерживается?
- Активно поддерживается. Последний коммит в code-graph-rag — 18 окт. 2026 г..
- Для чего можно использовать code-graph-rag?
- Onboarding onto a large multi-language monorepo and finding where logic lives Locating a function's source by name or intent during code review Finding unused functions before a refactor or cleanup Giving an AI coding assistant structured context about an existing codebase
- Где скачать code-graph-rag?
- Исходный код и инструкции по установке — на GitHub: https://github.com/vitali87/code-graph-rag
Описание создано ИИ на основе README проекта. Статистика GitHub обновляется ежедневно.
Похожие проекты
An open-source autonomous research agent that plans questions, gathers web and local sources, and writes cited reports with any LLM provider.
Incremental data pipeline framework in Python with a Rust core that keeps vector indexes and knowledge graphs in sync with changing sources for AI agents and RAG apps.
A Zotero plugin that lets you chat with one PDF, several PDFs, or your whole library, with clickable citations and optional fully local models.
A CLI that scans your codebase and generates compact AI context files so coding assistants spend fewer tokens exploring the project.
A local code knowledge graph that gives AI coding tools precise review context over MCP and a CLI.