High-performance code graph engine that indexes repos and exposes them via CLI, MCP, and API, cutting token usage up to 50x.
gortex is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view zzet/gortex --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
Gortex is a tool that scans your code and builds a smart map of how everything connects. Instead of reading whole files, AI coding agents can ask Gortex for just the piece of code they need, which saves a lot of tokens and speeds up responses. It works with many popular AI coding assistants and runs entirely on your machine.
Gortex is a high-performance code graph and intelligence engine that indexes repositories and exposes the knowledge graph via CLI, MCP Server, and web UI. It supports 257 languages and multiple repositories, building an in-memory knowledge graph that enables sub-millisecond impact analysis and context-aware code lookups. By providing only the necessary symbols and relationships to AI coding agents, Gortex reduces token usage by up to 50x compared to naive file reads. It is designed for 16 AI coding agents including Claude Code, Kiro, Cursor, Windsurf, VS Code/Copilot, Continue.dev, Cline, OpenCode, Antigravity, Codex CLI, Gemini CLI, Zed, Aider, Kilo Code, OpenClaw, and Hermes. One install configures every detected agent on your machine. Gortex is 100% local, open-source under Apache-2.0, and built in Go.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 1 days ago.
75 GitHub stars indicate community interest.
2 open issues signal maintenance load.
Apache-2.0 license detected.
Reduce token consumption for AI coding agents by providing only relevant code symbols instead of entire files.
Perform rapid impact analysis to understand how changes in one part of the codebase affect others.
Enable context-aware code navigation and search across multiple repositories.
Integrate with MCP-compatible tools and IDEs for enhanced code intelligence.
Run a local knowledge graph server for team-wide or personal use without sending data to the cloud.
75
Stars
6
Forks
2
Issues
Apache-2.0
License
Local codebase intelligence CLI and MCP server for AI coding agents with change-safety gates and audit evidence.
An offline MCP server that indexes your codebase for semantic search, code search, and git history retrieval.
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
0 security/trust notes recorded.
Setup difficulty is 3/5.