# 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

Repository: https://github.com/zzet/gortex
Canonical: https://ross.abutalabs.com/products/gortex
Homepage: https://gortex.dev/
Language: Go
License: Apache-2.0
License Family: permissive
Topics: ai-tools, antigravity, claude-code, code-assistant, copilot, cursor, graphrag, kiro, knowledge-graph, mcp-server, windsurf, tokens, context-window, context-window-optimization, context-window-optimizer, skills, prompts, local-first, code-analysis, developer-tools
Last push: 2026-08-26T17:50:05+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 10
- inputs: {"age_days": 149, "days_push": 7, "days_rel": 13, "gap_med": 0, "n_releases_24m": 116}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1494, forks 137 (observed 2026-08-28T04:04:52.671299+00:00)

## What it is
Gortex is a high-performance code-intelligence engine that indexes codebases into a persistent knowledge graph using tree-sitter AST analysis and compiler-grade resolution across 257 languages. It exposes the graph via CLI, MCP Server, HTTP API, and web UI as a single static binary, letting AI coding agents answer code questions with up to 50x fewer tokens, fully locally.

## Use cases
- reduce token usage when AI coding agents read my codebase
- index multiple repositories into a code knowledge graph for an agent
- give Claude Code or Cursor graph-based code navigation via MCP
- find callers, callees, and blast radius of a function without reading files
- analyze cross-service contracts and HTTP routes across repos
- run a fully local code-intelligence server for my IDE or agent

## When to choose
- you use AI coding agents (Claude Code, Cursor, Windsurf, Copilot) and want to cut context/token costs
- you need fast, local, dependency-free code navigation across many languages
- you work with multi-repository workspaces and need cross-repo symbol resolution
- you want an MCP server exposing curated code context instead of raw file reads

## When to avoid
- you need a hosted or cloud-based code intelligence service
- your project uses languages with weak tree-sitter or LSP support and need deep resolution
- you want a full IDE plugin experience rather than a CLI/MCP tool
- you need semantic code search powered by embeddings rather than graph/AST analysis

## Facets
- artifact type: cli-tool
- maturity: active
- function: search-engine, parser, mcp, developer-tools, code-review, llm-inference
- domain: developer-tools, large-language-models, programming-languages, parsers
- platform: windows, cli, go
- tags: code-intelligence, knowledge-graph, tree-sitter, context-window-optimization, token-optimization, mcp-server, local-first, multi-repo, ai-coding-agents, static-binary, ai-agents, macos, linux

## Member repositories
- zzet/gortex (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:52.671299+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:33:25.149757+00:00, confidence not recorded.
  - readme: https://github.com/zzet/gortex (fetched 2026-08-28T04:04:52.671299+00:00, sha 613d8064288a)
  - homepage: https://gortex.dev/ (fetched 2026-08-29T11:38:56.698689+00:00, sha afffd58cd344)
  - site_page: https://gortex.dev/docs.html (fetched 2026-08-29T11:38:56.708044+00:00, sha 930ea9d910a6)
- Data as of 2026-08-30T08:39:29.467469+00:00.