convez.ai
MCP ServerDesenvolvimento WebIntermediário
zzet

Gortex

zzet/gortex

Engine de graph de código com 50x menos tokens para agentes IA

Ver no GitHub
Muito bomPluginScore · de 0 a 100

Motor de inteligência de código que indexa repositórios e expõe análise via MCP Server, CLI e API. Suporta 257 linguagens e múltiplos repositórios, reduzindo uso de tokens em até 50x. Totalmente local e otimizado para agentes de IA.

Instalação

$npx convez-ai zzet/gortex

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
2,1 mil
Forks
207
Acompanhando
7
Saúde
100%
Último commit
há 1 dia
Versão
v0.64.11
Issues abertas
197
Contribuidores
5

Casos de uso

  • Potenciar agentes de IA com contexto preciso de repositórios
  • Reduzir consumo de tokens em análise de código
  • Integrar com Claude Code, Cursor, Windsurf e outros IDEs com IA

Veredito

Ferramenta especializada e bem executada para quem precisa fornecer contexto de código a agentes IA com eficiência. A redução de 50x em tokens é um ganho real, e o suporte a 257 linguagens e compatibilidade com múltiplos agentes (Claude Code, Cursor, VS Code Copilot, etc.) a torna versátil. Recomendado para times que trabalham com IA para coding.

README

A tradução para o português deste README ainda está na fila.

Code graph and intelligence engine that indexes repositories

and exposes it via CLI, MCP Server, and web UI.


CI Go Report Card Latest release Go Reference OpenSSF Scorecard

Sigstore signed SLSA 3 VirusTotal

macOS Linux Windows

Claude Code Kiro Cursor Windsurf VS Code / Copilot Continue.dev Cline opencode Antigravity Codex CLI Gemini CLI Zed Aider Kilo Code OpenClaw Hermes

Up to 50× fewer tokens per response. See BENCHMARK.md or reproduce it yourself.

Built for 16 AI coding agents (Claude Code, Kiro, Cursor, Windsurf, VS Code / Copilot, Continue.dev, Cline, OpenCode, Antigravity, Codex CLI, Gemini CLI, Zed, Aider, Kilo Code, OpenClaw, Hermes). One install configures every one detected on your machine — see docs/agents.md.

Gortex Web UI — force-directed knowledge graph visualization

Why it matters

  • 50× fewer tokens per response — graph-native lookups beat naive file reads. Agents read the symbol they need, not the 500-line file around it.
  • Sub-millisecond impact analysis — a precomputed depth-3 reach index turns blast-radius queries into O(seeds × reach) map lookups. Safe to ask "what breaks if I change this?" on every edit.
  • Cross-repo by default — N repos in one graph; contracts, references, and call chains span repo boundaries with evidence-gated resolution.
  • Zero external dependencies — everything in-process, in-memory. No DB, no network, no model download to get started.

Install

# macOS / Linux
curl -fsSL https://get.gortex.dev | sh

# Windows (PowerShell)
irm https://get.gortex.dev/install.ps1 | iex

Detects OS/arch, verifies SHA256 + cosign, installs to PATH. Re-run to upgrade. Homebrew, .deb / .rpm / .apk, scoop, signed binaries, and from-source builds: docs/installation.md.

Quick Start

gortex install                          # one-time machine setup (MCP, skills, slash commands)
gortex daemon start --detach            # background daemon
gortex track ~/projects/myapp           # add a repo
cd ~/projects/myapp && gortex init      # per-repo: .mcp.json, hooks, community routing

Your AI assistant now uses graph queries. Full 15-minute walkthrough: docs/onboarding.md.

Highlights

  • 257 languages — three tiers (bespoke tree-sitter, regex, forest-backed signatures) plus Jupyter and Databricks notebooks → docs/languages.md
  • 100+ MCP tools, 16 resources, 3 prompts — symbol lookup, call chains, blast radius, dataflow, clone detection, refactoring, code actions → docs/mcp.md
  • Semantic search default-on — baked GloVe-50d (3.8 MB embedded), hybrid BM25 + vector + RRF, zero deps; opt-in MiniLM / Ollama / OpenAI → docs/semantic-search.md
  • Multi-repo workspaces — cross-repo symbol resolution, contract matching, impact analysis, per-session isolation → docs/multi-repo.md
  • Speculative execution — preview_edit / simulate_chain answer "what would change if I applied this WorkspaceEdit?" without touching disk
  • Live editor overlays — push unsaved buffers as a shadow graph; tools read through it. Branching for parallel speculative sessions
  • GCX1 wire format — published, round-trippable. −27 % tokens vs JSON at same fidelity → docs/wire-format.md
  • Long-living daemon — one process serves every IDE window; live fsnotify, on-disk snapshots, sub-second restart, OS-supervised lifecycle
  • 9 LLM providers (optional) — local llama.cpp, Anthropic, OpenAI, Ollama, Claude / Codex CLI subprocess, Gemini, Bedrock, DeepSeek → docs/llm.md
  • HTTP server + Web UI — versioned /v1/* API + MCP 2026 Streamable HTTP; standalone Next.js 15 UI with five 3D graph modes → docs/server.md
  • Composable safety — verify_change, check_guards, audit_agent_config flag broken callers, guard violations, stale docs before they ship
  • PR review, end to end — gortex prs triages open PRs (per-PR blast radius, merge-order conflicts via shared communities, AI-ranked queue, reviewer suggestions); gortex review emits line-anchored findings with a BLOCK/REVIEW/APPROVE verdict from a graph-grounded rulepack; MCP tools (pr_risk, get_pr_impact, review, review_pack, post_review, …) expose it to agents → docs/cli.md
  • Agent integrations (16) — gortex init configures every detected coding assistant on the machine → docs/agents.md

Full catalog of features: docs/features.md. Complete CLI reference: docs/cli.md.

Cross-Repo API Contracts

Gortex auto-detects API contracts across repos and matches providers to consumers, surfaced via the contracts MCP tool and the web UI Contracts page.

Contract typeDetectionProviderConsumer
HTTP routesFramework annotations (gin, Express, FastAPI, Spring, …)Route handlerHTTP client calls (fetch, http.Get)
gRPCProto service definitionsService RPCClient stub calls
GraphQLSchema type/field definitionsSchemaQuery/mutation strings
Message topicsKafka / RabbitMQ / NATS / Redis pub/subPublish callsSubscribe calls
WebSocketEvent emit/listen patternsemit()on()
Env varsos.Getenv, process.env, .env filesSetenv / .envGetenv / process.env
OpenAPISwagger / OpenAPI spec filesSpec paths(linked to HTTP routes)
Temporal workflowsGo / Java SDK annotationsActivity / workflow functionExecuteActivity / ExecuteChildWorkflow

Contracts are normalised to canonical IDs (e.g. http::GET::/api/users/{id}) and matched across repos to detect orphan providers / consumers and mismatches. See docs/contracts.md.

Scale — battle-tested on large repos

Measured on an Apple Silicon laptop with the default CGO build.

RepositoryFilesNodesEdgesIndex timeThroughputPeak heap
torvalds/linux70,3331,690,1746,239,570~3 min300 files/s5.07 GB
microsoft/vscode10,762204,501808,902~1 min143 files/s580 MB
zzet/gortex (self)4305,58353,8303.4s127 files/s52 MB

Parsing dominates wall time (65–80 %); reference resolution and search-index build scale sub-linearly.

Token savings dashboard

gortex savings reports tokens saved vs naive file reads — per-call, per-session, and cumulative across restarts, priced in USD against the headline model.

Gortex Token Savings
====================
Cost avoided:   $168.69 (claude-opus-4) across 1,878 calls · 11,246,094 tokens saved

Today       ████████░░░░░░░░   50.0%  saved 9,200 / 18,400 tokens   $0.14
Last 7 days ██████████░░░░░░   62.5%  saved 60,100 / 96,200 tokens  $0.90
All time    ███████████████░   93.3%  saved 11,246,094 / 12,050,716 tokens  $168.69

--verbose adds the per-tool breakdown; --json is machine-readable. Full reference: docs/savings.md.

Architecture

gortex binary
  CLI (cobra)    ──> MultiIndexer ──> In-Memory Graph (shared, per-repo indexed)
  MCP (stdio)    ──────────────────> Query Engine (repo/project/ref scoping)
  HTTP /v1/*     ──────────────────> same tools + /v1/graph + /v1/events (SSE)
  Daemon (unix)  ──────────────────> shared graph for every MCP client, session isolation
                  MultiWatcher    <── filesystem events (fsnotify, per-repo)
                  CrossRepoResolver ──> cross-repo edge creation (type-aware)
                  Persistence     ──> gob+gzip snapshot (pluggable backend)

Data flow, graph schema (node and edge kinds, multi-repo fields, test taxonomy), persistence model: docs/architecture.md.

Documentation

TopicReference
First-time walkthroughonboarding.md
Installation & supply-chain verificationinstallation.md
Full feature catalogfeatures.md
CLI referencecli.md
MCP tools, resources, promptsmcp.md
Multi-repo workspacesmulti-repo.md
HTTP server + Web UI + MCP 2026 transportserver.md
Cross-repo API contractscontracts.md
Semantic searchsemantic-search.md
Optional LLM featuresllm.md
LSP integrationlsp.md
Per-community skills & agent usageskills.md
AI agent adapters (15)agents.md
Supported languages (257)languages.md
Token savingssavings.md
GCX1 wire formatwire-format.md
Architecture & graph schemaarchitecture.md
Evaluation methodology04-evaluation/
Versioning policyversioning.md

Building from source

make build          # binary with version stamping
make test           # go test -race ./...
make lint           # golangci-lint

Requires Go 1.26+ and CGO (for tree-sitter C bindings).

License

Apache License 2.0. See LICENSE.md. Copyright 2024-2026 Andrey Kumanyaev me@zzet.org.

Contributing

See CONTRIBUTING.md for guidelines on adding features, language extractors, and submitting PRs.

Ver o original no GitHub

Bom para

Relacionados