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

# Quickstart Guide

Get started with CyborgDB in minutes! This guide will help you choose the right deployment model and get your first confidential vector search running quickly.

## Choose Your Deployment Path

CyborgDB offers two main deployment approaches - both **self-hosted** on your infrastructure:

<CardGroup cols={2}>
  <Card title="CyborgDB Service" href="../service/guides/intro/quickstart-docker" icon="cloud">
    *Self-deployed REST API service*

    Deploy as a microservice with REST API and client SDKs. Best for:

    * Multi-language team environments
    * Independent scaling capabilities
    * Operational simplicity with centralized management
    * Microservice architecture patterns
  </Card>

  <Card title="CyborgDB Embedded" href="../embedded/guides/intro/quickstart" icon="code">
    *Direct library integration*

    Embed directly in your applications using Python/C++ libraries. Best for:

    * Maximum performance and control
    * Custom integrations and workflows
    * Single-application deployments
    * Sub-millisecond latency requirements
  </Card>
</CardGroup>

***

## Migrating from Another Database

Already have vectors in Pinecone, Qdrant, Weaviate, ChromaDB, or Milvus? Use **CyborgDB Migrate** to bring them over:

<Card title="CyborgDB Migrate" href="./migrate" icon="arrow-right-arrow-left">
  *Migrate embeddings from other vector databases*

  Interactive TUI wizard or headless TOML config. Supports Pinecone, Qdrant, Weaviate, ChromaDB, and Milvus.

  ```bash theme={null}
  pip install "cyborgdb-migrate[pinecone]"
  cyborgdb-migrate
  ```
</Card>

***

## Framework Integrations

Already using AI frameworks? Get started even faster with our native integrations:

<CardGroup cols={2}>
  <Card title="LangChain Integration" href="../integrations/langchain/introduction" icon="link">
    *Drop-in replacement for existing vector stores*

    Replace your current vector store with CyborgDB's encrypted alternative:

    ```python theme={null}
    from cyborgdb_core.integrations.langchain import CyborgVectorStore

    store = CyborgVectorStore.from_texts(
        texts=["hello world", "goodbye world"],
        embedding="all-MiniLM-L6-v2",
        index_key=CyborgVectorStore.generate_key(save=True),
        # ... other config
    )
    ```
  </Card>

  <Card title="More Integrations Coming" href="../integrations/about" icon="plus">
    *Expanding framework support*

    We're actively building integrations for:

    * LlamaIndex
    * Haystack
    * Semantic Kernel
    * Custom frameworks

    [Request an integration →](https://www.cyborg.co/contact)
  </Card>
</CardGroup>

***

## Quick Decision Guide

<Tabs>
  <Tab title="I want to get started quickly">
    **Fastest path to working confidential vector search**

    → Run [**CyborgDB Service**](../service/guides/intro/quickstart-docker) with Docker

    Spin up the service in one `docker run`, then connect via the Python SDK. Minimal setup required.
  </Tab>

  <Tab title="I have a LangChain application">
    **Drop-in replacement for existing vector stores**

    → Use the [**LangChain Integration**](../integrations/langchain/introduction) guide

    Replace your existing vector store with just a few lines of code changes.
  </Tab>

  <Tab title="I need maximum performance">
    **Sub-millisecond latency requirements**

    → Use [**CyborgDB Embedded**](../embedded/guides/intro/quickstart) libraries

    Direct integration eliminates network overhead for ultimate performance.
  </Tab>

  <Tab title="I'm building a distributed application">
    **Multi-language team or microservice architecture**

    → Use [**CyborgDB Service**](../service/guides/intro/quickstart-docker) deployment

    One service supports Python, JavaScript, Go, and C++ client SDKs.
  </Tab>
</Tabs>

***

## Next Steps After Quickstart

<CardGroup cols={3}>
  <Card title="Learn the Concepts" href="./about" icon="book">
    *Understand the architecture*

    Dive deeper into how CyborgDB enables confidential vector search
  </Card>

  <Card title="Choose Your Database" href="./backing-stores" icon="database">
    *PostgreSQL, Redis, S3, or Memory*

    Understand database options and performance characteristics
  </Card>

  <Card title="Production Planning" href="./deployment-models" icon="server">
    *Service vs Embedded comparison*

    Review deployment models and choose the right approach for production
  </Card>
</CardGroup>

Ready to get started? Choose your deployment path above and follow the step-by-step guide!