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...

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 26 minutes ago
Added to GitGenius on March 2nd, 2026
Created on August 2nd, 2025
Open Issues & Pull Requests: 334 (+0)
Number of forks: 5,061
Total Stargazers: 45,745 (+0)
Total Subscribers: 153 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 14.2 hours
Mean response time: 5.7 days
90th percentile: 14.9 days
Tracked items: 1,073

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 85% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "refactor" is answered fastest, typically in about 6 hours, while "ring:3-language" waits about 3 days. 58% of tracked open issues have had no activity in three months. Only 10% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 279
New in 7 days: 23
Closed in 7 days: 4
Avg open age: 28 days
Stale 30+ days: 219
Stale 90+ days: 164

Recent activity

Opened in 7 days: 20
Closed in 7 days: 2
Comments in 7 days: 21
Events in 7 days: 28

Top labels

  • bug (270)
  • enhancement (161)
  • Language Support (126)
  • semantic-model (44)
  • rfc:scope-resolution (40)
  • ring:3-language (38)
  • refactor (32)
  • good first issue (19)

Detailed Description

GitNexus is a client-side code intelligence tool that builds an interactive knowledge graph of a repository and runs entirely in your browser.

The tool solves the problem of AI agents missing architectural context when analyzing code. It indexes a codebase into a knowledge graph that tracks dependencies, call chains, clusters, and execution flows, then exposes this graph through MCP tools so that AI agents like Claude Code and Cursor can understand the full structure of a project. The approach works by analyzing code relationships at scale and making that context available both through a web interface for interactive exploration and through CLI commands that integrate with AI coding assistants.

GitNexus suits developers who want their AI coding assistants to have reliable architectural awareness, particularly those using tools like Cursor, Claude Code, or other agents that benefit from deep codebase context. The web UI provides a quick way to explore any repository in the browser without setup, while the CLI with MCP integration is designed for developers who want to embed this knowledge graph into their AI agent workflows. The README positions it as deeper than DeepWiki, tracking every relationship rather than just descriptions, and emphasizes that even smaller models gain full architectural clarity when given access to the graph.

The project receives almost all of its open issues from outside users rather than the core team, indicating a substantial base of adopters reporting real-world use. Maintainers typically respond to new issues and pull requests within a day. Work in the issue tracker is dominated by bug reports, enhancement requests, and language support additions.