Moorcheh On-PremSearch that never leaves home.
Install the client, start Moorcheh server with Ollama, upload your documents, and search locally — the full semantic search engine on your machine.
Your Machine. Your Pipeline.
Text and vector namespaces follow different paths — both stay entirely local.
One command. Full stack.
moorcheh up starts the server in Docker and mounts ~/.moorcheh/data. Ollama starts only when needed for text workflows — or use your host instance if already running.
Built for Developers Who Own Their Stack
The advantages of running Moorcheh locally — without sacrificing search quality.
Nothing leaves your machine
Documents, embeddings, and queries stay on localhost or your trusted network. You own the full stack.
No cloud account needed
Start moorcheh up and call the API immediately. No signup, no tokens, no billing surprises.
No artificial caps
Create as many text or vector namespaces as your project needs — no cloud-tier namespace limits.
Docker does the heavy lifting
moorcheh up handles compose, image pulls, and data mounts. Ollama starts when you need text workflows — vector-only setups skip it entirely.
Same search science as cloud
Information-theoretic scoring — deterministic, audit-safe semantic retrieval on your hardware.
Persistent local storage
Up to 100,000 items across all namespaces. Data survives moorcheh down — back up ~/.moorcheh anytime.
Built-In Limits
Transparent quotas so you know exactly what to expect on-prem.
No cloud-tier cap
Create as many text or vector namespaces as you need — no cloud-tier namespace count limit.
Global storage quota
100,000 items total across all namespaces (text documents and vectors combined). Check usage via /health or moorcheh status.
Required for text
Ollama is required for text namespace uploads and text search queries. Vector-only workflows do not call Ollama.