Now Available · Self-Hosted

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.

moorcheh terminalInstall
$
Client
Server
Ollama
Vault
InstallDeployUploadSearch
How It Works

Your Machine. Your Pipeline.

Text and vector namespaces follow different paths — both stay entirely local.

Local perimeter · No egress
pip installmoorcheh-client
moorcheh upDocker · :8080
Ready~/.moorcheh/data

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.

Why On-Prem

Built for Developers Who Own Their Stack

The advantages of running Moorcheh locally — without sacrificing search quality.

100%
Local data

Nothing leaves your machine

Documents, embeddings, and queries stay on localhost or your trusted network. You own the full stack.

Zero
API keys

No cloud account needed

Start moorcheh up and call the API immediately. No signup, no tokens, no billing surprises.

Namespaces

No artificial caps

Create as many text or vector namespaces as your project needs — no cloud-tier namespace limits.

1 cmd
Deploy

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.

ITS
Engine

Same search science as cloud

Information-theoretic scoring — deterministic, audit-safe semantic retrieval on your hardware.

100K
Item vault

Persistent local storage

Up to 100,000 items across all namespaces. Data survives moorcheh down — back up ~/.moorcheh anytime.

Limits

Built-In Limits

Transparent quotas so you know exactly what to expect on-prem.

Unlimited
Namespaces

No cloud-tier cap

Create as many text or vector namespaces as you need — no cloud-tier namespace count limit.

100,000
Items total

Global storage quota

100,000 items total across all namespaces (text documents and vectors combined). Check usage via /health or moorcheh status.

Ollama
Text workflows

Required for text

Ollama is required for text namespace uploads and text search queries. Vector-only workflows do not call Ollama.

Get started

Start in 5 Minutespip install moorcheh-client · moorcheh up · search locally