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 reduce the token cost and noise for AI coding agents. Instead of agents reading entire files or large chunks of code, Gortex indexes code into a knowledge graph, allowing agents to retrieve only the specific symbols, call chains, and references they actually need.

How it works

Gortex uses tree-sitter AST analysis to parse 257 languages and grammars. It builds a persistent, provenance-tiered knowledge graph of functions, classes, and cross-service contracts. This graph is stored in an on-disk SQLite database and served via a long-living daemon. It exposes this intelligence via a CLI, a web UI for visualization, and an MCP (Model Context Protocol) server with over 100 tools for symbol lookup, blast-radius analysis, and refactoring.

Who it’s for

Developers using AI coding assistants (such as Claude Code, Cursor, Windsurf, or Aider) who want to improve the accuracy of their agents and significantly reduce token usage when working with large or multi-repository codebases.

Highlights

  • Massive Token Savings: Claims up to 50x fewer tokens per response 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 repo boundaries.
  • Broad Language Support: High-quality parsing for 257 languages, including compiler-grade resolution for major languages like Python, TS/JS, Go, and Rust.
  • Zero Dependencies: Distributed as a single static binary for macOS, Linux, and Windows.
  • Agent Integration: Out-of-the-box configuration for 19 different AI coding agents.
  • Cross-Repo API Contracts: Automatically detects and matches HTTP routes, gRPC, GraphQL, and message topics across different services.
  • Speculative Execution: Allows agents to simulate changes via preview_edit without modifying the disk.

Related

  • Project
    ix-infrastructure/Ix

    Ix is a system intelligence tool that parses codebases into a persistent graph of symbols and relationships, allowing humans and AI agents to query structure instead of searching text.

  • Project
    DeusData/codebase-memory-mcp
  • Project
    aovestdipaperino/tokensave

    tokensave is a Rust‑based local server that builds a semantic knowledge graph of a codebase, letting AI coding agents query symbols, relationships, and snippets in a single call. By replacing costly grep/glob scans, it cuts token usage, supports multi‑branch indexing, offers crash‑resilient syncing, and integrates with dozens of LLM‑powered coding tools.

  • Project
    Context-Engine-AI/Context-Engine

    Context Engine is a service that adds semantic code search, symbol graph navigation, and persistent memory to AI coding assistants via MCP tools and per-editor skill files, letting them understand and navigate codebases more accurately than grep-based approaches.

  • Project
    cocoindex-io/cocoindex-code

    cocoindex‑code is a real, open‑source tool that builds an AST‑based semantic index of a codebase and lets you search it with natural‑language queries. Install via pipx (full or slim variant), run `ccc init` and `ccc index`, then use `ccc search` or integrate the provided `ccc` skill/MCP server with Claude, Grok, Oh My Pi, Codex, etc. Docker images are also available for reproducible deployments.