> ## Documentation Index
> Fetch the complete documentation index at: https://docs.moorcheh.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Welcome to Moorcheh

> Ultra-fast, deterministic, index-free semantic search - and the full AI infrastructure that grew around it.

## The World's First Information-Theoretic Search Engine

[Moorcheh](https://www.moorcheh.ai/) delivers ultra-fast, deterministic, index-free semantic search - and the full AI infrastructure that grew around it. Built for agentic AI applications, Moorcheh combines high-fidelity storage, stateful context, and explainable retrieval so intelligent systems can understand, remember, and reason about information.

## Choose your deployment

<CardGroup cols={3}>
  <Card title="Moorcheh Cloud" icon="cloud" href="/quickstart">
    Hosted API, console, free tier
  </Card>

  <Card title="Moorcheh On-Prem" icon="server" href="/on-prem/introduction">
    Self-hosted local API with moorcheh-client
  </Card>

  <Card title="Moorcheh On-Edge" icon="microchip" href="/on-edge/coming-soon">
    Coming soon — edge devices and offline environments
  </Card>
</CardGroup>

### What Makes Moorcheh Different?

Moorcheh uses **Maximally Informative Binarization (MIB)** and **Information-Theoretic Score (ITS)** to deliver superior search accuracy and performance compared to traditional vector databases. These advanced technologies enable:

* **Higher Accuracy**: ITS scoring provides more nuanced relevance measurements than traditional cosine similarity
* **Better Performance**: MIB technology optimizes storage and retrieval for faster search results
* **Explainable Results**: Clear relevance labels help you understand why results are returned
* **Stateful Context**: Maintain conversation context and build intelligent memory systems
* **High-Fidelity Storage**: Preserve semantic meaning while optimizing for performance

## Traditional Vector Stores vs. Moorcheh ITS

Traditional vector stores typically use Hierarchical Navigable Small World (HNSW) graphs for indexing and rely on cosine similarity or Euclidean distance for similarity search. These systems store high-dimensional floating-point embeddings, resulting in higher storage and computational overhead.

Moorcheh, in contrast, employs a **Universal Relevance Score (ITS – Information Theoretical Score)** that operates on binarized embeddings. This design significantly reduces storage requirements while maintaining computational efficiency. ITS maintains relevance quality equivalent to conventional vector similarity methods, despite using a more compact representation.

As a result, Moorcheh delivers equivalent retrieval relevance to traditional vector stores while achieving substantial reductions in storage and operational costs, making it a cost-efficient alternative for large-scale retrieval systems.

## Ready to Get Started?

Whether you're building AI agents, semantic search applications, or intelligent knowledge bases, Moorcheh provides the foundation you need. Join thousands of developers who are already using Moorcheh to power their AI applications.

<CardGroup cols={2}>
  <Card title="Free Tier Available" icon="gift" href="https://console.moorcheh.ai">
    Get started with our free tier - no credit card required
  </Card>

  <Card title="Quick Start Guide" icon="rocket" href="/quickstart">
    Build your first semantic search in 5 minutes
  </Card>

  <Card title="Python SDK" icon="python" href="/python-sdk/introduction">
    Install and start coding with our Python SDK
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/introduction">
    Explore our comprehensive API documentation
  </Card>
</CardGroup>

<CardGroup cols={2}>
  <Card title="MIB Technology" icon="brain">
    Uses Maximally Informative Binarization for superior search accuracy
  </Card>

  <Card title="ITS Scoring" icon="chart-line">
    Information-Theoretic Score provides better relevance ranking
  </Card>

  <Card title="Lightning Fast" icon="bolt">
    Optimized for speed and performance
  </Card>

  <Card title="Easy Integration" icon="plug">
    Simple API, Python SDK, and integrations with LangChain & LlamaIndex
  </Card>
</CardGroup>

## Get Started in 3 Steps

<Steps>
  <Step title="Sign Up">
    Create your free account and get your API key from the [Moorcheh Console](https://console.moorcheh.ai). No credit card required.
  </Step>

  <Step title="Install SDK">
    Install the Python SDK: `pip install moorcheh-sdk` or use our REST API directly
  </Step>

  <Step title="Start Building">
    Follow our [Quick Start Guide](/quickstart) to make your first semantic search request in minutes
  </Step>
</Steps>

## API Reference

<CardGroup cols={2}>
  <Card title="Authentication" icon="key" href="/api-reference/introduction">
    API key authentication methods
  </Card>

  <Card title="Namespaces" icon="folder" href="/api-reference/namespaces/create">
    Create, list, and delete namespaces
  </Card>

  <Card title="Search & Discovery" icon="magnifying-glass" href="/api-reference/search/query">
    Perform semantic search across namespaces
  </Card>

  <Card title="AI Generation" icon="sparkles" href="/api-reference/ai/generate">
    Generate AI-powered answers from your data
  </Card>

  <Card title="Data Operations" icon="database" href="/api-reference/data/upload-text">
    Upload and manage text or vector data
  </Card>

  <Card title="Python SDK" icon="python" href="/python-sdk/introduction">
    Complete Python SDK documentation
  </Card>
</CardGroup>

## Integrations

<CardGroup cols={3}>
  <Card title="LangChain" icon="link" href="/integrations/langchain/overview">
    Seamless LangChain vector store integration
  </Card>

  <Card title="LlamaIndex" icon="database" href="/integrations/llamaindex/overview">
    Native LlamaIndex vector store support
  </Card>

  <Card title="MCP Server" icon="server" href="/integrations/mcp/overview">
    Model Context Protocol for AI assistants
  </Card>

  <Card title="Chat Boilerplate" icon="messages" href="/integrations/chat-boilerplate/overview">
    Production-ready chat application template
  </Card>
</CardGroup>

## Supported AI Models

Moorcheh supports 9 state-of-the-art AI models for answer generation:

| Model                | Provider  | Description                                                                         |
| -------------------- | --------- | ----------------------------------------------------------------------------------- |
| Claude Sonnet 4.6    | Anthropic | Fast flagship: coding, tools, long docs and RAG (\~1M context).                     |
| Claude Opus 4.6      | Anthropic | Deepest reasoning and hardest tasks; pick when quality matters most (\~1M context). |
| Llama 4 Maverick 17B | Meta      | Long context, summarization, function calling, fine-tuning friendly.                |
| Amazon Nova Pro      | Amazon    | Chat, math, and structured answers for AWS-style workloads.                         |
| DeepSeek R1          | DeepSeek  | Step-by-step reasoning; math, logic, and technical explanations.                    |
| DeepSeek V3.2        | DeepSeek  | Efficient general Q\&A, multilingual, everyday RAG (\~164K context).                |
| OpenAI GPT OSS 120B  | OpenAI    | Large generalist: research-style answers and long-form writing.                     |
| Qwen 3 32B           | Qwen      | Code and bilingual (EN/ZH) tasks in a smaller footprint.                            |
| Qwen3 Next 80B A3B   | Qwen      | MoE model for long chats, docs, and code at scale (\~256K context).                 |

## Need Help?

<CardGroup cols={2}>
  <Card title="API Reference" icon="code" href="/api-reference/introduction">
    Complete API documentation
  </Card>

  <Card title="Python SDK" icon="python" href="/python-sdk/introduction">
    Python SDK guide and examples
  </Card>

  <Card title="Support" icon="headset" href="mailto:support@moorcheh.ai">
    Get help from our team
  </Card>

  <Card title="GitHub" icon="github" href="https://github.com/moorcheh-ai">
    Explore our open-source SDKs
  </Card>
</CardGroup>