CodeGraphContext

Turn code repositories into a queryable graph for AI agents.

- 🇬🇧English
- 🇨🇳中文
- 🇰🇷한국어
- 🇺🇦Українська
- 🇷🇺Русский
- 🇯🇵日本語
- 🇮🇳தமிழ்
- 🇪🇸 Español (Soon)

🌍Help translate CodeGraphContext to your language by raising an issue & PR onGitHub Issues!

[](https://pypi.org/project/codegraphcontext/)<<<[](https://pypi.org/project/codegraphcontext/)<<<[](https://github.com/Shashankss1205/CodeGraphContext/blob/HEAD/LICENSE)<<<

[](https://github.com/CodeGraphContext/CodeGraphContext/stargazers)<<<[](https://github.com/CodeGraphContext/CodeGraphContext/network/members)<<<[](https://github.com/CodeGraphContext/CodeGraphContext/issues)<<<[](https://github.com/CodeGraphContext/CodeGraphContext/pulls)<<<

[](https://github.com/CodeGraphContext/CodeGraphContext/actions/workflows/test.yml)<<<[](https://github.com/CodeGraphContext/CodeGraphContext/actions/workflows/e2e-tests.yml)<<<[](http://codegraphcontext.vercel.app/)<<<[](https://codegraphcontext.vercel.app/)<<<

- 🚀 Quick Start
- 📋 Prerequisites
- 🏃 How to Run the Project Locally
- 🌐 Supported Programming Languages
- 🛠️ CLI Toolkit
- 🤖 MCP Server
- 🗄️ Database Options
- 🔬 SCIP indexing (optional)

flowchart LR A[Source code] --> B[Tree-sitter and SCIP indexers] B --> C[Graph database] C --> D[CLI queries] C --> E[MCP server] D --> F[Direct analysis] E --> G[AI assistants with repo context]

- Trace call chains across files and packages.
- Understand class hierarchies, imports, and module boundaries.
- Find dead code, hotspots, and unexpected dependencies.
- Give an AI assistant the same structural context a maintainer would use.

- Do I need a remote service?No. CGC works locally with embedded backends or with external graph databases when you want them.
- Is it only for one language?No. It supports a broad mix of mainstream languages and keeps expanding.
- Can I use it with an AI assistant?Yes. That is one of the main reasons the MCP server exists.

- Version:0.5.1
- Authors:Shashank Shekhar Singhshashankshekharsingh1205@gmail.com
- License:MIT License (SeeLICENSEfor details)
- Website:CodeGraphContext

- 📧 Email:shashankshekharsingh1205@gmail.com
- 🐙 GitHub:@Shashankss1205
- 🔗 LinkedIn:Shashank Shekhar Singh
- 🌐 Website:codegraphcontext.vercel.app

- Code Indexing:Analyzes code and builds a knowledge graph of its components.
- Relationship Analysis:Query for callers, callees, class hierarchies, call chains and more.
- Pre-indexed Bundles:Load famous repositories instantly with.cgcbundles - no indexing required! (Learn more)
- Live File Watching:Watch directories for changes and automatically update the graph in real-time (cgc watch).
- Interactive Setup:A user-friendly command-line wizard for easy setup.
- Dual Mode:Works as a standaloneCLI toolkitfor developers and as anMCP serverfor AI agents.
- Multi-Language Support:Full support for 23 programming languages.
- Flexible Database Backend:FalkorDB Lite (Default), KuzuDB, LadybugDB, FalkorDB Remote, Nornic DB, or Neo4j (all platforms via Docker/native).

flowchart TD A[Code Repository] --> B[Tree-sitter / SCIP Indexing] B --> C[Knowledge Graph] C --> D[Graph Database] D --> E[CLI Toolkit] D --> F[MCP Server] F --> G[AI Assistant]

- Source code is parsed using Tree-sitter or SCIP indexers.
- Relationships between functions, classes, imports, and calls are extracted.
- A knowledge graph is generated and stored in a graph database.
- Users can query the graph through the CLI or AI assistants using MCP.

CodeGraphContext parses your source code and builds a comprehensive knowledge graph. This graph can be queried directly via the CLI toolkit or exposed to AI assistants through the MCP server.

flowchart TD A[Code Repository] -->|Parsed by| B[Tree-sitter / SCIP Indexing] B -->|Generates| C[Knowledge Graph] C -->|Stored in| D[(Graph Database)] D -->|Queried via| E[CLI Toolkit] D -->|Served by| F[MCP Server] F -->|Provides context to| G[🤖 AI Assistant] classDef default fill:#1f2937,stroke:#8b5cf6,stroke-width:2px,color:#fff; classDef db fill:#0f172a,stroke:#3b82f6,stroke-width:2px,color:#fff; classDef ai fill:#312e81,stroke:#a855f7,stroke-width:2px,color:#fff; D:::db G:::ai

CodeGraphContext parses your source code and builds a comprehensive knowledge graph. This graph can be queried directly via the CLI toolkit or exposed to AI assistants through the MCP server.

flowchart TD A[Code Repository] -->|Parsed by| B[Tree-sitter / SCIP Indexing] B -->|Generates| C[Knowledge Graph] C -->|Stored in| D[(Graph Database)] D -->|Queried via| E[CLI Toolkit] D -->|Served by| F[MCP Server] F -->|Provides context to| G[🤖 AI Assistant] classDef default fill:#1f2937,stroke:#8b5cf6,stroke-width:2px,color:#fff; classDef db fill:#0f172a,stroke:#3b82f6,stroke-width:2px,color:#fff; classDef ai fill:#312e81,stroke:#a855f7,stroke-width:2px,color:#fff; D:::db G:::ai

CodeGraphContext provides comprehensive parsing and analysis for the following languages:

…