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

# Installation

> Install LangGraph using pip, poetry, or uv package managers

# Installation

This guide covers installing LangGraph and its dependencies for Python projects.

## Requirements

LangGraph requires:

* **Python 3.10 or higher**
* Supported Python versions: 3.10, 3.11, 3.12, 3.13

<Warning>
  Python 3.9 and earlier are not supported. Please upgrade to Python 3.10 or later.
</Warning>

## Installing LangGraph

Choose your preferred package manager:

<CodeGroup>
  ```bash pip theme={null}
  pip install -U langgraph
  ```

  ```bash poetry theme={null}
  poetry add langgraph
  ```

  ```bash uv theme={null}
  uv add langgraph
  ```
</CodeGroup>

The `-U` flag in pip ensures you get the latest version.

## Core Dependencies

When you install LangGraph, the following dependencies are automatically included:

* **langchain-core** (>=0.1) - Core LangChain abstractions
* **langgraph-checkpoint** (>=2.1.0, \<5.0.0) - Checkpointing interfaces
* **langgraph-sdk** (>=0.3.0, \<0.4.0) - SDK for LangGraph Server API
* **langgraph-prebuilt** (>=1.0.8, \<1.1.0) - Prebuilt agent components
* **xxhash** (>=3.5.0) - Fast hashing for state management
* **pydantic** (>=2.7.4) - Data validation and settings management

<Note>
  You don't need to install these dependencies separately unless you want specific versions.
</Note>

## Optional Dependencies

Depending on your use case, you may want to install additional packages:

### Checkpointing Backends

For persistent state storage:

<CodeGroup>
  ```bash SQLite theme={null}
  pip install langgraph-checkpoint-sqlite
  ```

  ```bash PostgreSQL theme={null}
  pip install langgraph-checkpoint-postgres
  ```
</CodeGroup>

### LangGraph CLI

For local development and deployment:

```bash theme={null}
pip install langgraph-cli
```

<Tip>
  The LangGraph CLI includes tools for developing, testing, and deploying LangGraph applications. It supports Python versions up to 3.13.
</Tip>

### LangChain Integrations

While LangGraph works standalone, you may want LangChain for additional integrations:

```bash theme={null}
pip install langchain
```

For specific integrations:

<CodeGroup>
  ```bash OpenAI theme={null}
  pip install langchain-openai
  ```

  ```bash Anthropic theme={null}
  pip install langchain-anthropic
  ```

  ```bash Community theme={null}
  pip install langchain-community
  ```
</CodeGroup>

## Verify Installation

Confirm LangGraph is installed correctly:

```python theme={null}
import langgraph
print(langgraph.__version__)
```

You should see the version number (e.g., `1.0.10`).

Or run a simple test:

```python theme={null}
from langgraph.graph import StateGraph
from typing_extensions import TypedDict

class State(TypedDict):
    value: int

graph = StateGraph(State)
print("LangGraph is installed correctly!")
```

## Development Installation

For contributing to LangGraph or running from source:

<Steps>
  ### Clone the Repository

  ```bash theme={null}
  git clone https://github.com/langchain-ai/langgraph.git
  cd langgraph/libs/langgraph
  ```

  ### Install in Editable Mode

  <CodeGroup>
    ```bash pip theme={null}
    pip install -e .
    ```

    ```bash uv theme={null}
    uv pip install -e .
    ```
  </CodeGroup>

  ### Install Development Dependencies

  ```bash theme={null}
  pip install -e ".[dev]"
  ```

  This installs:

  * Testing tools (pytest, pytest-cov, pytest-mock, etc.)
  * Linting tools (mypy, ruff)
  * Development utilities (jupyter)
</Steps>

## Version Management

### Check Current Version

```bash theme={null}
pip show langgraph
```

### Upgrade to Latest Version

<CodeGroup>
  ```bash pip theme={null}
  pip install --upgrade langgraph
  ```

  ```bash poetry theme={null}
  poetry update langgraph
  ```

  ```bash uv theme={null}
  uv pip install --upgrade langgraph
  ```
</CodeGroup>

### Install Specific Version

```bash theme={null}
pip install langgraph==1.0.10
```

## Common Installation Issues

### Python Version Mismatch

If you see errors about Python version:

```bash theme={null}
# Check your Python version
python --version

# Use Python 3.10+ explicitly
python3.10 -m pip install langgraph
```

### Dependency Conflicts

If you encounter dependency conflicts:

```bash theme={null}
# Create a fresh virtual environment
python -m venv langgraph-env
source langgraph-env/bin/activate  # On Windows: langgraph-env\Scripts\activate
pip install langgraph
```

### Permission Errors

On Linux/Mac, if you get permission errors:

```bash theme={null}
# Use --user flag
pip install --user langgraph

# Or use a virtual environment (recommended)
python -m venv venv
source venv/bin/activate
pip install langgraph
```

## Virtual Environment Setup

<Tip>
  Always use virtual environments to avoid dependency conflicts.
</Tip>

<CodeGroup>
  ```bash venv theme={null}
  # Create virtual environment
  python -m venv myenv

  # Activate (Linux/Mac)
  source myenv/bin/activate

  # Activate (Windows)
  myenv\Scripts\activate

  # Install LangGraph
  pip install langgraph
  ```

  ```bash conda theme={null}
  # Create conda environment
  conda create -n langgraph-env python=3.11
  conda activate langgraph-env
  pip install langgraph
  ```

  ```bash poetry theme={null}
  # Initialize project with poetry
  poetry init
  poetry add langgraph
  poetry shell
  ```
</CodeGroup>

## Docker Installation

For containerized deployments:

```dockerfile theme={null}
FROM python:3.11-slim

WORKDIR /app

# Install LangGraph
RUN pip install --no-cache-dir langgraph

# Copy your application
COPY . .

CMD ["python", "your_app.py"]
```

## Next Steps

Now that LangGraph is installed:

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Build your first LangGraph application
  </Card>

  <Card title="Core Concepts" icon="book" href="/concepts">
    Learn the fundamentals of LangGraph
  </Card>

  <Card title="API Reference" icon="code" href="https://reference.langchain.com/python/langgraph/">
    Explore the complete API documentation
  </Card>

  <Card title="Examples" icon="flask" href="https://docs.langchain.com/oss/python/langgraph/agentic-rag">
    See real-world implementations
  </Card>
</CardGroup>

## Additional Resources

* [PyPI Package](https://pypi.org/project/langgraph/) - Official package page
* [GitHub Repository](https://github.com/langchain-ai/langgraph) - Source code and issues
* [Changelog](https://github.com/langchain-ai/langgraph/releases) - Release notes and updates
* [LangSmith](https://docs.langchain.com/langsmith/home) - Debugging and deployment tools

<Note>
  For JavaScript/TypeScript, see the [LangGraph.js installation guide](https://docs.langchain.com/oss/javascript/langgraph/overview).
</Note>