Community Edition · Free

Moorcheh On-PremOwn your data. Run your search. Keep your memory.

Self-hosted semantic search and RAG - free Community Edition, source-available on GitHub, local by default. Choose Ollama, OpenAI, or Cohere for embeddings and LLM answers. Your index stays under ~/.moorcheh/data.

Community
Edition · free
Source
available · GitHub
Zero
cloud keys
moorcheh terminalInstall
$
Client
Server
Provider
Vault
InstallDeployUploadSearch
Data Ownership

You Should Own Your Data

Not as a slogan - as architecture.

Your documents, embeddings, and queries belong on your machine - not spread across a vector SaaS, reranker API, and glue code you do not control.

Index hosted by a vector SaaS

Index under ~/.moorcheh/data

Queries logged by a third party

Queries stay on localhost

Separate reranker API

Built-in ITS scoring

Five services to wire together

moorcheh up

Need billion-scale in a private VPC? Moorcheh Enterprise

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, mounts ~/.moorcheh/data, and runs setup - choose Ollama, OpenAI, or Cohere for embeddings and LLM.

The Engine

What Makes Moorcheh Different

Three layers - compress at ingest, score at query, rank without a reranker.

Not pgvector on Postgres - a purpose-built information-theoretic retrieval engine. Same stack on-prem as cloud.

  • MIB
    At ingest

    Maximum Information Binarization

  • EDM
    At query

    Efficient Distance Metric

  • ITS
    Built-in

    Information-Theoretic Scoring

Cards auto-rotate · hover to pause

MIB
At ingest

Maximum Information Binarization

Float embeddings become compact one-bit codes - ~96 B per 768-d vector vs ~3 KB float32.

EDM
At query

Efficient Distance Metric

CPU-friendly bitwise scoring instead of high-dimensional float cosine - no HNSW graph in RAM.

ITS
Built-in

Information-Theoretic Scoring

Replaces the separate reranker pass - no cross-encoder model or second vendor API to wire in.

Why On-Prem

Built for Developers Who Own Their Stack

Self-hosted retrieval and RAG - same engine as cloud, on your machine.

100%
Local

Your data stays yours

Documents, embeddings, and queries on localhost - index under ~/.moorcheh/data.

Free
Community

Source-available on GitHub

Moorcheh Community License - free for single-node, non-commercial use. Enterprise for commercial and multi-node.

3
Providers

Ollama, OpenAI, or Cohere

Configure embedding and LLM providers with moorcheh configure - fully local with Ollama, or cloud models while your index stays on-prem.

ITS
Engine

Built-in scoring

Information-theoretic retrieval - no separate reranker API to wire in.

1 cmd
Deploy

Docker does the work

moorcheh up pulls moorcheh/server, mounts your data, and exposes localhost:8080.

100K
Items

Persistent storage

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.

3
Providers

Embed & LLM choice

Ollama, OpenAI, or Cohere for text embeddings and /answer generation - set once in ~/.moorcheh/config.json via moorcheh configure.

Get started

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

First run configures Ollama, OpenAI, or Cohere for embeddings and LLM via moorcheh configure.