CodeGraph - Knowledge Graph Visualization Tool

Visualize your repository with our graph for code analysis

Live Demo

Project Structure

code-graph/
├── api/                  # Python backend (Flask)
│   ├── index.py          # Main Flask app with API routes
│   ├── graph.py          # Graph operations (FalkorDB)
│   ├── llm.py            # LLM integration for chat
│   ├── project.py        # Project management
│   ├── info.py           # Repository info
│   ├── prompts.py        # LLM prompts
│   ├── auto_complete.py  # Auto-completion
│   ├── analyzers/        # Source code analyzers (Python, Java, C, C#)
│   ├── entities/         # Entity models
│   ├── git_utils/        # Git operations
│   └── code_coverage/    # Code coverage utilities
├── app/                  # React frontend (Vite)
│   ├── src/              # Frontend source code
│   │   ├── App.tsx       # Main application component
│   │   ├── main.tsx      # Entry point
│   │   ├── components/   # React components
│   │   └── lib/          # Utility functions
│   ├── public/           # Static assets
│   ├── package.json      # Frontend dependencies
│   ├── vite.config.ts    # Vite configuration
│   └── tsconfig.json     # TypeScript configuration
├── tests/                # Backend tests
├── e2e/                  # End-to-end tests (Playwright)
├── Dockerfile            # Unified Docker build
├── docker-compose.yml    # Docker Compose setup
├── Makefile              # Development commands
├── start.sh              # Container startup script
├── pyproject.toml        # Python project configuration
└── .env.template         # Environment variables template

Running Locally

Prerequisites

• Python 3.12+
• Node.js 20+
• FalkorDB instance (local or cloud)

1. Start FalkorDB

Option A: Free cloud instance at app.falkordb.cloud

Option B: Run locally with Docker:

docker run -p 6379:6379 -it --rm falkordb/falkordb

2. Set Up Environment Variables

Copy the template and configure:

cp .env.template .env

Edit .env with your values:

FALKORDB_HOST=localhost
FALKORDB_PORT=6379
OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>
SECRET_TOKEN=<YOUR_SECRET_TOKEN>

3. Install Dependencies

# Install backend dependencies
pip install -e ".[test]"

# Install frontend dependencies
npm install --prefix ./app

Or using Make:

make install

4. Build & Start

# Build the frontend
npm --prefix ./app run build

# Start the backend (serves both API and frontend)
flask --app api/index.py run --debug

The application will be available at http://localhost:5000.

Development Mode

For frontend development with hot-reload:

# Terminal 1: Start the Python backend
flask --app api/index.py run --debug --port 5000

# Terminal 2: Start the Vite dev server (proxies API calls to backend)
cd app && npm run dev

The Vite dev server runs on http://localhost:3000 and proxies API requests to the Flask backend on port 5000.

Using Make

make install       # Install all dependencies
make build-dev     # Build frontend (development)
make build-prod    # Build frontend (production)
make run-dev       # Build + start dev server
make run-prod      # Build + start production server
make test          # Run backend tests
make lint          # Run frontend linting
make clean         # Clean build artifacts

Running with Docker

Using Docker Compose

docker-compose up

This starts both FalkorDB and the CodeGraph application.

Using Docker Directly

docker build -t code-graph .

docker run -p 5000:5000 \
  -e FALKORDB_HOST=host.docker.internal \
  -e FALKORDB_PORT=6379 \
  -e OPENAI_API_KEY=<YOUR_KEY> \
  -e SECRET_TOKEN=<YOUR_TOKEN> \
  code-graph

Creating a Code Graph

Analyze a Local Folder

curl -X POST http://127.0.0.1:5000/analyze_folder \
  -H "Content-Type: application/json" \
  -H "Authorization: <YOUR_SECRET_TOKEN>" \
  -d '{"path": "<FULL_PATH_TO_FOLDER>", "ignore": [".github", ".git"]}'

Analyze a GitHub Repository

curl -X POST http://127.0.0.1:5000/analyze_repo \
  -H "Content-Type: application/json" \
  -H "Authorization: <YOUR_SECRET_TOKEN>" \
  -d '{"repo_url": "https://github.com/user/repo"}'

Supported Languages

• Python
• Java
• C
• C#

Support for additional languages is planned.

API Endpoints

Method	Endpoint	Description
GET	/list_repos	List all available repositories
GET	/graph_entities?repo=<name>	Get graph entities for a repository
POST	/get_neighbors	Get neighbors of specified nodes
POST	/auto_complete	Auto-complete entity names
POST	/repo_info	Get repository information
POST	/find_paths	Find paths between two nodes
POST	/chat	Chat with the code graph using natural language
POST	/analyze_folder	Analyze a local source folder
POST	/analyze_repo	Analyze a GitHub repository
POST	/list_commits	List commits of a repository
POST	/switch_commit	Switch to a specific commit

Community

Have questions or feedback? Reach out via:

• GitHub Issues
• Join our Discord

If you find this repository helpful, please consider giving it a star!

Knowledge Graph, Code Analysis, Code Visualization, Dead Code Analysis, Graph Database