Gortex is a high-performance code-intelligence engine that gives AI coding agents a knowledge graph of your repository, so they stop wasting tokens re-reading files. One graph query returns the symbols, callers and context an agent needs — cutting token usage by up to 50x per response — across 257 programming languages, entirely on your machine. It has 1,913 stars on GitHub.
Every coding agent session burns budget on the same ritual: read a file, grep for a symbol, read four more files, guess at an interface. Gortex replaces that with a single static binary that indexes your repos into an in-memory graph and serves it over MCP, HTTP and a web UI. It layers on semantic search with embedded embeddings, live overlays of unsaved editor buffers, speculative edit simulation, dataflow and clone analysis, and graph-grounded PR review — with adapters that auto-configure 19 popular agents including Claude Code, Cursor and Copilot. Everything runs 100% locally with zero external services.
Gortex is completely free and open source under the Apache-2.0 license, including for commercial use. There is no cloud tier and no account — the binary runs entirely on your own machine.
Gortex is for developers who use AI coding agents daily and feel the token bill and context churn of large repositories. If your agent spends more time reading than writing, giving it a real code graph is one of the highest-leverage upgrades available.