zzet/gortex

High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d

What it solves

Gortex is a high-performance code-intelligence engine designed to help AI coding agents and IDEs understand large codebases. It solves the problem of "token bloat" where agents must read entire files or large chunks of code to find specific information, which increases costs and reduces accuracy. By indexing code into a graph, it allows agents to retrieve only the precise symbols, call chains, and dependencies they need.

How it works

It uses tree-sitter AST analysis to parse 257 languages and grammars, creating a persistent knowledge graph of functions, classes, and cross-service contracts. This graph is stored in a local SQLite database and managed by a long-living daemon. Gortex exposes this intelligence via a CLI, a Model Context Protocol (MCP) server, and a web UI for visualization.

Who it’s for

Developers using AI coding assistants (such as Claude Code, Cursor, Windsurf, or Aider) who want to reduce LLM token usage, speed up context retrieval, and manage complex, multi-repository projects.

Highlights

  • Massive Token Savings: Reduces tokens per response by up to 50x by replacing naive file reads with graph-native lookups.
  • Multi-Repository Support: Indexes multiple repositories into a single graph to track contracts and call chains across service boundaries.
  • Broad Language Support: High-quality parsing for 257 languages, including compiler-grade resolution for major languages like Python, TypeScript, Go, and Rust.
  • Zero Dependencies: Distributed as a single static binary for macOS, Linux, and Windows.
  • Coded-Intelligence Tools: Provides over 100 MCP tools for symbol lookup, blast-radius analysis, dataflow tracking, and refactoring.
  • Semantic Search: Built-in vector search with adaptive alpha fusion and optional integration with external LLM providers.
  • PR Review Integration: Includes tools to triage PRs and emit line-anchored findings based on graph-grounded rules.

Related

  • Project
    Arch1eSUN/Arcgentic

    A harness engineering layer for Codex and Claude Code that turns AI coding into a gated workflow with specialized roles for planning, development, and auditing.

  • Project
    colbymchenry/codegraph

    A semantic code intelligence platform that provides AI agents with a pre-built knowledge graph of a codebase to eliminate slow file-by-file discovery and reduce token costs.

  • Project
    CodeGraphContext/CodeGraphContext

    A toolkit and MCP server that indexes local code repositories into a graph database to provide AI agents and developers with structural context like call chains and class hierarchies.

  • Project
    Houseofmvps/codesight

    A zero-dependency tool that pre-compiles codebase structure and documentation into compact context maps and wikis to drastically reduce token consumption for AI coding assistants.

  • Project
    cocoindex-io/cocoindex-code

    An AST-based semantic code search tool that enables AI coding agents and developers to find code by meaning and structure, reducing token usage by up to 70%.