Local semantic search for Claude Code: /find, /ingest, /remember, /explain, /source, /quarry
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Local semantic search for AI agents and humans.
Quarry indexes documents in 20+ formats, embeds them with a local ONNX model (snowflake-arctic-embed-m-v1.5, 768-dim), stores vectors in LanceDB, and serves semantic search to Claude Code, Claude Desktop, and the CLI. Everything runs locally — no API keys, no cloud accounts. The embedding model (~120 MB int8) downloads once on first use. CUDA GPUs are auto-detected for faster inference.
Platforms: macOS, Linux
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
curl -fsSL https://raw.githubusercontent.com/punt-labs/quarry/a3c10f9/install.sh | sh
Restart Claude Code, then:
> /ingest report.pdf # index a document (runs in background)
> /quarry status # after a moment, confirm it's there
> /find "what does the report say about margins" # search by meaning
Once installed, a plugin hook auto-indexes your current project directory on every session start — you don't need to /ingest your codebase manually.
uv tool install punt-quarry
quarry install
quarry doctor
For non-Claude harnesses (Codex, Cursor, a plain terminal) or Claude Code users whose org policy blocks marketplace/plugin installs, add --no-plugin to install the CLI, daemon, and MCP server while skipping only the marketplace-register and plugin-install steps:
curl -fsSL https://raw.githubusercontent.com/punt-labs/quarry/a3c10f9/install.sh | sh -s -- --no-plugin
In contexts that cannot pass a flag (CI templating a bare curl … | sh, config systems that set only env), set QUARRY_NO_PLUGIN=1 — honored only when exactly 1:
curl -fsSL https://raw.githubusercontent.com/punt-labs/quarry/a3c10f9/install.sh | QUARRY_NO_PLUGIN=1 sh
Everything else runs unchanged — binary, PATH, embedding model, TLS, and the health check. Use the CLI (quarry find, quarry ingest, quarry remember) and the stdio MCP server (quarry mcp) directly; both talk to the resident quarryd daemon that quarry install starts. To add the plugin later, re-run the installer without --no-plugin.
curl -fsSL https://raw.githubusercontent.com/punt-labs/quarry/a3c10f9/install.sh -o install.sh
shasum -a 256 install.sh
cat install.sh
sh install.sh
Run quarry on a GPU server and connect from any Mac or Linux client over TLS.
Server (GPU host, serves remote clients):
export QUARRY_API_KEY=$(openssl rand -hex 32)
curl -fsSL https://raw.githubusercontent.com/punt-labs/quarry/a3c10f9/install.sh | sh -s -- --network
Generates TLS certificates, binds daemon to 0.0.0.0, registers a systemd service, and prints a CA fingerprint. NVIDIA GPUs are auto-detected for CUDA inference.
Client (connects to remote server):
curl -fsSL https://raw.githubusercontent.com/punt-labs/quarry/a3c10f9/install.sh | sh
quarry login <server-hostname> --api-key <token>
No special flag needed --- the default install runs a local daemon on localhost. quarry login redirects queries to the remote server over wss:// with TOFU certificate pinning.
The .mcpb bundle is an on-top way to reach the same local quarry index from Claude Desktop and CoWork agents. It embeds no engine: it registers the thin quarry mcp stdio client, which talks to the same resident quarryd daemon that backs the CLI and Claude Code. Desktop searches exactly the data you have already indexed --- not a separate store --- precisely because every surface shares one daemon. The dependency is the same one a menu-bar surface would have: a thin client over the running quarryd, not a self-contained app.
It is not a standalone install. Quarry must already be present: install it first, which puts the quarry binary on your PATH and starts the daemon:
curl -fsSL https://raw.githubusercontent.com/punt-labs/quarry/a3c10f9/install.sh | sh
With quarry installed, add it to Claude Desktop by either route:
npx claudepluginhub punt-labs/claude-plugins --plugin quarryAmazon Working Backwards PR/FAQ process — generate professional LaTeX documents for product discovery and decision-making
punt-labsAutonomous agent daemon with cryptographic owner control. Email communication via IMAP/SMTP with PGP trust model.
punt-labsCreate, validate, and test formal Z specifications for stateful systems using fuzz and probcli
punt-labsUNIX-style team communication for Claude Code: /who, /finger, /plan, /write, /read, /mesg, /tty, /last, /wall, /talk
punt-labsIdentity binding for humans and AI agents — voice, email, GitHub, writing style, personality.
punt-labsSearch your local documents with natural language. Index folders of PDFs, Word docs, markdown, and more — then ask questions in English or German and get answers with source citations.
ZhuBitSafe, explicit memory search and persistence workflows backed by the memtomem MCP server
memtomemZero-config knowledge base MCP server — search, manage, and embed documentation (SQLite default, PostgreSQL optional)
nicholasglazerLocal RAG system with embedded Multi-Agent Framework for Claude Code plugin
ItMeDiaTechOptimized file search, semantic indexing, and persistent memory for Claude Code — with optional sync to a self-hosted web dashboard
iagocavalcanteDocument search with hybrid BM25/semantic retrieval, GraphRAG knowledge graphs, and pluggable providers for Claude Code. Index documentation and code, then search using keyword matching, semantic similarity, graph relationships, or comprehensive multi-mode fusion.
SpillwaveSolutions