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

# AutoGen Studio

> Rapidly prototype AI agents with a visual interface

AutoGen Studio is an AutoGen-powered AI application (user interface) to help you rapidly prototype AI agents, enhance them with skills, compose them into workflows, and interact with them to accomplish tasks. It is built on top of the [AutoGen](https://microsoft.github.io/autogen) framework.

<Warning>
  AutoGen Studio is under active development and is currently not meant to be a production-ready app. Expect breaking changes in upcoming releases.
</Warning>

## Installation

There are two ways to install AutoGen Studio: from PyPI or from source. We **recommend installing from PyPI** unless you plan to modify the source code.

### Install from PyPI (Recommended)

We recommend using a virtual environment (e.g., venv) to avoid conflicts with existing Python packages. With Python 3.10 or newer active in your virtual environment, use pip to install AutoGen Studio:

<Steps>
  <Step title="Create a virtual environment">
    ```bash theme={null}
    python -m venv autogen-env
    source autogen-env/bin/activate  # On Windows: autogen-env\Scripts\activate
    ```
  </Step>

  <Step title="Install AutoGen Studio">
    ```bash theme={null}
    pip install -U autogenstudio
    ```
  </Step>
</Steps>

### Install from Source

<Note>
  This approach requires familiarity with building interfaces in React and Git LFS.
</Note>

<Steps>
  <Step title="Install Git LFS">
    AutoGen Studio uses Git Large File Storage (LFS) for managing image and other large files.

    ```bash theme={null}
    # On Debian/Ubuntu
    apt-get install git-lfs

    # On macOS with Homebrew
    brew install git-lfs

    # On Windows with Chocolatey
    choco install git-lfs
    ```

    Then set up git-lfs:

    ```bash theme={null}
    git lfs install
    ```
  </Step>

  <Step title="Clone and install dependencies">
    ```bash theme={null}
    git clone https://github.com/microsoft/autogen.git
    cd autogen/python/packages/autogen-studio
    pip install -e .
    ```
  </Step>

  <Step title="Build the UI">
    ```bash theme={null}
    npm install -g gatsby-cli
    npm install --global yarn
    cd frontend
    yarn install
    yarn build
    ```

    <Note>
      Windows users may need alternative commands to build the frontend. See the [README](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-studio) for details.
    </Note>
  </Step>
</Steps>

## Running the Application

Once installed, run the web UI by entering the following in your terminal:

```bash theme={null}
autogenstudio ui --port 8081
```

This command will start the application on the specified port. Open your web browser and go to `http://localhost:8081/` to use AutoGen Studio.

### CLI Options

AutoGen Studio accepts several parameters to customize the application:

<ParamField path="--host" type="string" default="localhost">
  Specify the host address
</ParamField>

<ParamField path="--port" type="number" default="8080">
  Specify the port number
</ParamField>

<ParamField path="--appdir" type="string" default="~/.autogenstudio">
  Directory where app files (database, generated files) are stored
</ParamField>

<ParamField path="--database-uri" type="string">
  Database URI for backend storage. Examples:

  * SQLite: `sqlite:///database.sqlite`
  * PostgreSQL: `postgresql+psycopg://user:password@localhost/dbname`

  If not specified, defaults to `database.sqlite` in the `--appdir` directory.
</ParamField>

<ParamField path="--reload" type="boolean" default="false">
  Enable auto-reloading when code changes are made
</ParamField>

<ParamField path="--upgrade-database" type="boolean" default="false">
  Upgrade the database schema to the latest version
</ParamField>

### Example Commands

```bash theme={null}
# Run on custom port
autogenstudio ui --port 8081

# Use PostgreSQL backend
autogenstudio ui --database-uri postgresql+psycopg://user:password@localhost/dbname

# Specify custom app directory
autogenstudio ui --appdir /path/to/folder

# Enable development mode with auto-reload
autogenstudio ui --reload
```

## AutoGen Studio Lite

AutoGen Studio Lite provides a lightweight way to quickly prototype and experiment with AI agent teams without the full database setup. It's designed for rapid experimentation.

### CLI Usage

Launch Studio Lite from the command line:

```bash theme={null}
# Quick start with default team
autogenstudio lite

# Use custom team file
autogenstudio lite --team ./my_team.json --port 8080

# Custom session name with auto-open browser
autogenstudio lite --session-name "My Experiment" --auto-open
```

### Programmatic Usage

Use Studio Lite directly in your Python code:

```python theme={null}
from autogenstudio.lite import LiteStudio
from autogen_agentchat.teams import RoundRobinGroupChat

# Quick start with default team
studio = LiteStudio()

# Use with custom AutoGen team objects
team = RoundRobinGroupChat([agent1, agent2], termination_condition=...)

# Context manager usage
with LiteStudio(team=team) as studio:
    # Studio runs in background
    # Do other work here
    pass
```

## Database Configuration

AutoGen Studio uses [SQLModel](https://sqlmodel.tiangolo.com/) (Pydantic + SQLAlchemy) for its database layer. This provides:

* Entity linking (skills, models, agents, and workflows are linked via association tables)
* Support for multiple database backends via [SQLAlchemy dialects](https://docs.sqlalchemy.org/en/20/dialects/)

### Supported Databases

<CardGroup cols={2}>
  <Card title="SQLite" icon="database">
    Default option, file-based database

    ```bash theme={null}
    autogenstudio ui --database-uri sqlite:///database.sqlite
    ```
  </Card>

  <Card title="PostgreSQL" icon="database">
    Production-ready relational database

    ```bash theme={null}
    autogenstudio ui --database-uri postgresql+psycopg://user:password@localhost/dbname
    ```
  </Card>

  <Card title="MySQL" icon="database">
    Popular open-source database

    ```bash theme={null}
    autogenstudio ui --database-uri mysql://user:password@localhost/dbname
    ```
  </Card>

  <Card title="Oracle / SQL Server" icon="database">
    Enterprise database support
  </Card>
</CardGroup>

### Environment Variables

Place a `.env` file in your `--appdir` directory to set environment variables for the app. This file will be automatically loaded when the application starts.

```bash .env theme={null}
OPENAI_API_KEY=your-api-key-here
AZURE_API_KEY=your-azure-key-here
# Add other environment variables as needed
```

## Project Structure

The AutoGen Studio codebase is organized as follows:

* `autogenstudio/` - Backend classes and web API (FastAPI)
* `frontend/` - Web UI built with Gatsby and TailwindCSS

## Key Features

<CardGroup cols={2}>
  <Card title="Visual Agent Builder" icon="robot">
    Define and configure AI agents through an intuitive interface
  </Card>

  <Card title="Workflow Composition" icon="diagram-project">
    Compose multiple agents into workflows to accomplish complex tasks
  </Card>

  <Card title="Skills Enhancement" icon="wand-magic-sparkles">
    Enhance agents with custom skills and capabilities
  </Card>

  <Card title="Interactive Sessions" icon="comments">
    Interact with agents in real-time to test and refine behavior
  </Card>
</CardGroup>

## Troubleshooting

### Git LFS Issues

If you encounter build errors related to image formats when installing from source:

```bash theme={null}
# Install git-lfs if not already installed
git lfs install

# Fetch all LFS files
git lfs fetch --all

# Checkout LFS files to working directory
git lfs checkout
```

### Database Migration

To upgrade your database schema to the latest version:

```bash theme={null}
autogenstudio ui --upgrade-database
```

## Contributing

We welcome contributions to AutoGen Studio! To contribute:

1. Review the [AutoGen contribution guide](https://github.com/microsoft/autogen?tab=readme-ov-file#contributing)
2. Check the [roadmap](https://github.com/microsoft/autogen/issues/4006) for current priorities
3. Use the tag `proj-studio` for issues, questions, and PRs related to Studio
4. Submit a pull request with your contribution

## Resources

<CardGroup cols={2}>
  <Card title="GitHub Repository" icon="github" href="https://github.com/microsoft/autogen/tree/main/python/packages/autogen-studio">
    View source code and contribute
  </Card>

  <Card title="AutoGen Framework" icon="book" href="https://microsoft.github.io/autogen">
    Learn about the underlying AutoGen framework
  </Card>

  <Card title="FAQs" icon="circle-question" href="https://microsoft.github.io/autogen/docs/autogen-studio/faqs">
    Find answers to common questions
  </Card>

  <Card title="PyPI Package" icon="python" href="https://badge.fury.io/py/autogenstudio">
    View package on PyPI
  </Card>
</CardGroup>