Your files, your Mac, your AI.
Garage indexes your documents, code repositories, notes and messages on your Mac and hands them to your AI assistant over the Model Context Protocol. Nothing is uploaded, nothing is sent anywhere you did not point it at.
What Garage does
Indexes what you already have
Folders, git repositories, Markdown, PDF, Office documents, scanned images and Apple Messages and Mail, parsed into searchable chunks in a private PostgreSQL database.
Hybrid search
Vector similarity and full-text search fused with Reciprocal Rank Fusion, so a question finds the meaning and a keyword finds the exact line.
Knows who wrote it
Git history, document metadata and path rules classify every document as authored by you, reference material or received from someone else, with the evidence recorded.
Works with your AI assistant
An MCP 2.0 server lets Claude Desktop, Claude Code, Cursor and other MCP clients search your corpus, read documents and ask grounded questions.
Local models, your choice
Embeddings and fact distillation run on the built-in llama.cpp engine, or on the Ollama or LM Studio server you already have. Switch models without re-ingesting.
Private by construction
No cloud AI client in the app. One tested egress choke point with a destination allowlist, and your messages never leave the machine. Read the privacy policy →
How it works
sources ──▶ walker ──▶ [materialize] ──▶ extract ──▶ quality gate
│
attribution ◀─────────────────┤
│ ▼
└──────▶ documents ── chunks
│
┌───────────┴───────────┐
▼ ▼
emb_<model_1> emb_<model_2>
└───────────┬───────────┘
▼
hybrid search (RRF)
│
MCP server
Garage walks the sources you register, extracts text, decides who wrote each document and how much to trust it, and splits it into chunks. Each chunk is embedded under every model you register, one table per model, so adding a model is a backfill rather than a re-ingest. Search fuses the vector and keyword rankings and serves the result to your assistant over MCP. Everything lives in a PostgreSQL 18 + pgvector cluster the app bundles and runs for you.
Download
Garage for Mac
Apple Silicon (M1 and later), macOS 14 Sonoma or later. A signed and notarized .pkg installer.
After installing
- Open Garage from Applications. It appears in the menu bar and starts its private database.
- The first-run assistant picks your folders, an embedding model and the AI clients to connect.
- Ask Claude, or any MCP client, a question about your own files.
Garage checks for updates through Sparkle, only after asking you once. Garage runs on Apple Silicon only. The .zip archive is on the GitHub release page.
Also a command line and a Python package
The app installs a garage command for terminal workflows and a garage-mcp stdio server for MCP clients. The same pipeline ships as the garage_rag Python package, so the indexer, extractors and search run anywhere PostgreSQL with pgvector does. Sources, build instructions and the developer documentation are on GitHub: the architecture guide, attribution engine, privacy internals and database schema.
The Support Center has the user guide, troubleshooting, the FAQ and how to report a bug.