abhigyanpatwari/GitNexus

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or ZIP file, and get an interactive knowledge graph with a built in Graph RAG Agent. Perfect for code exploration

What it solves

GitNexus provides AI coding agents with a deep architectural understanding of a codebase. It prevents common AI errors, such as breaking dependencies or missing call chains, by replacing raw graph RAG with precomputed relational intelligence, ensuring agents have full structural clarity even if they are smaller models.

How it works

GitNexus indexes a codebase into a knowledge graph that tracks every dependency, call chain, and execution flow. It then exposes this graph through a Model Context Protocol (MCP) server, providing agents with 17 specialized tools (e.g., impact for blast radius analysis, trace for call paths) and custom agent skills. It also includes a Web UI for visual exploration and a CLI for local indexing.

Who it’s for

Developers using AI-powered editors and agents like Cursor, Claude Code, Codex, Windsurf, and Antigravity who want to make their AI assistants more reliable and architecturally aware.

Highlights

  • Precomputed Relational Intelligence: Unlike traditional Graph RAG, it precomputes structure at index time to provide complete context in a single tool call.
  • MCP Integration: Offers 17 tools for tasks like blast radius analysis, API route mapping, and coordinated renames.
  • Deep Editor Integration: Supports hooks for Claude Code and Codex to enrich searches and prompt for re-indexing after commits.
  • Knowledge Graph: Indexes dependencies, clusters, and execution flows using Tree-sitter for parsing.
  • Multi-modal Access: Available as a CLI for local development, an MCP server for agents, and a Web UI for browser-based analysis.

Related

  • Project
    DeusData/codebase-memory-mcp

    A native, zero‑runtime executable that builds a persistent, multi‑language knowledge graph of a codebase (158 languages) using Tree‑sitter and a custom “Hybrid LSP” type resolver. The graph can be queried instantly (structural, semantic, Cypher‑like) and is consumed by AI coding agents (Claude Code, Codex, OpenCode, etc.) to answer code‑understanding questions without sending source files to the cloud. Includes a built‑in 3D UI, cross‑repo linking, dead‑code detection, impact analysis, and integrates automatically with 43 supported agents. All processing is local, fast (Linux kernel indexed in ~3 min), and distributed via npm, PyPI, Homebrew, etc.

  • Project
    NVIDIA/cudnn-frontend

    NVIDIA’s cuDNN Frontend is an open‑source, header‑only C++ API plus Python package that wraps the cuDNN Graph API. It provides easy‑to‑use graph construction, autotuning, and a catalog of open‑source high‑performance kernels (Flash‑Attention, fused GEMM + SwiGLU, block‑sparse attention, etc.) for Hopper/Blackwell GPUs. Install via pip or include the header; integrates with PyTorch and lets researchers and engineers get backend‑level speed without writing CUDA kernels from scratch.

  • Project
    Tencent/teamai-cli

    TeamAI CLI is an npm‑distributed command‑line tool that lets a software team keep AI‑assistant resources (skills, rules, docs, hooks, MCP configs, and a shared knowledge base) in a single Git repo and automatically sync them into local Claude, Codex, Cursor, and other agents. It supports role‑/tag‑based filtering, source subscription, session‑learning capture, a code‑base knowledge graph, and dashboards for usage/knowledge‑base health.

  • Project
    jacob-bd/gemini-notebook-mcp-cli

    A CLI and MCP server that provides programmatic access to Gemini Notebook (NotebookLM), enabling AI agents and scripts to manage notebooks, sources, and generate studio content.

  • Project
    Neeeophytee/finding-unknowns-skills

    A collection of 11 installable “skills” (SKILL.md files) for Claude Code, OpenAI Codex, Kimi, Hermes, Cursor, etc. They help developers surface unknowns, plan implementations, and keep agent context clean. Install with a single `npx skills add …` command or via each agent’s plugin system.