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

# Installation

> Choose an installation for embedded development, agent development, or production

## Prerequisites

* Python 3.11, 3.12, or 3.13.
* An isolated environment created with `venv`, uv, Poetry, or an equivalent tool.
* Docker, PostgreSQL, and Redis only for the complete server deployment.

<Tabs>
  <Tab title="pip">
    ```bash theme={null}
    python -m venv .venv
    # Linux/macOS
    source .venv/bin/activate
    # Windows PowerShell
    .venv\Scripts\Activate.ps1

    pip install lingxigraph
    ```
  </Tab>

  <Tab title="uv">
    ```bash theme={null}
    uv venv
    uv pip install lingxigraph
    ```
  </Tab>

  <Tab title="Source">
    ```bash theme={null}
    git clone https://github.com/LingXi-Org/LingxiGraph.git
    cd LingxiGraph
    pip install -e ".[dev,all]"
    ```
  </Tab>
</Tabs>

## Optional dependencies

The core package has no third-party runtime dependencies. Install only the extras your application needs:

| Extra      | Command                               | Includes                                  |
| ---------- | ------------------------------------- | ----------------------------------------- |
| `server`   | `pip install "lingxigraph[server]"`   | FastAPI, Uvicorn, JWT, HTTP client        |
| `sdk`      | `pip install "lingxigraph[sdk]"`      | Sync and async Python HTTP SDK            |
| `postgres` | `pip install "lingxigraph[postgres]"` | PostgreSQL repository, checkpoints, Store |
| `redis`    | `pip install "lingxigraph[redis]"`    | Cache, PubSub, cancellation acceleration  |
| `otel`     | `pip install "lingxigraph[otel]"`     | OpenTelemetry SDK and OTLP exporter       |
| `coze`     | `pip install "lingxigraph[coze]"`     | Coze Bot, Workflow, and ChatModel         |
| `openai`   | `pip install "lingxigraph[openai]"`   | OpenAI-compatible ChatModel               |
| `all`      | `pip install "lingxigraph[all]"`      | Complete production feature set           |

## Verify the installation

```bash theme={null}
lingxigraph --version
python -c "from lingxigraph import StateGraph; print('LingxiGraph ready')"
```

<Note>
  `lingxigraph dev` requires the `server` extra. `lingxigraph server` also needs `postgres` when a PostgreSQL URL is configured. Project images built from the supplied Dockerfile include production dependencies.
</Note>

## Next step

<CardGroup cols={2}>
  <Card title="Embedded runtime" icon="python" href="./first-graph">Create and invoke your first state graph.</Card>
  <Card title="Server runtime" icon="server" href="./agent-server">Scaffold a project and open Studio.</Card>
</CardGroup>