Summary

GitVizz transforms complex codebases into interactive documentation, dependency graphs, and AI-powered conversational interfaces, revolutionizing understanding. It targets developers, code reviewers, and researchers needing rapid comprehension of project structures. The core benefit is accelerated analysis, enabling users to grasp codebases in minutes via AI insights and visual mapping.

How It Works

The system combines advanced code parsing with Large Language Models (LLMs). It uses Tree-sitter for Abstract Syntax Tree (AST) analysis across multiple languages and generates interactive dependency graphs. The FastAPI backend integrates with LLM providers (OpenAI, Anthropic, local models) for features like "Chat with Repository" and automated documentation. This synergy facilitates deep structural understanding and intelligent, context-aware code exploration.

Quick Start & Requirements

A live demo is available at gitvizz.com. For local development, Docker Compose is recommended (docker-compose up --build after cloning and configuring .env). Manual setup requires Python 3.9+ and Node.js 18+ with pip and pnpm. Essential prerequisites include Docker, Python, Node.js, and pnpm. Optional but recommended for full functionality are MongoDB, a GitHub PAT/App, and LLM API keys (OpenAI, Anthropic, Gemini, Groq). Detailed setup guides are in ./docs.

Highlighted Details

• Interactive dependency graphs with intelligent search for visual code navigation.
• AI-powered chat for context-aware codebase querying.
• Automatic documentation generation from repository structures.
• LLM Context Builder for preparing code context for LLMs.
• Standalone Python library (gitvizz/) for core analysis and graph generation (Python, JS, TS, React, Next.js).

Maintenance & Community

Contributions are encouraged via GitHub Issues and Discussions. A Discord server is available for real-time help. The project is developed by CognitiveLab.

Licensing & Compatibility

The backend and frontend applications are licensed under the GNU Affero General Public License v3.0 (AGPLv3). The core GitVizz Python library uses the Apache License 2.0. The AGPLv3's strong copyleft nature requires network-distributed modifications to be open-sourced under AGPLv3, potentially limiting integration into proprietary, closed-source commercial products.

Limitations & Caveats

The README does not explicitly detail known bugs or indicate an alpha status. The AGPLv3 license for core application components is a significant consideration for commercial adoption due to its strong copyleft provisions. Full local setup requires numerous API keys and database configurations.