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

# Install Agentor and configure LLM providers

> Install the Agentor Python framework on macOS, Linux, or Windows using pip or uv, and configure LLM provider API keys for OpenAI, Anthropic, or Gemini.

## Requirements

Before installing Agentor, ensure you have:

* **Python 3.10 or higher** - Check your version with `python --version`
* **pip** or **uv** package manager
* An API key from your LLM provider (OpenAI, Anthropic, Google, etc.)

## Install from PyPI

The recommended method is to install Agentor from PyPI using pip:

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

This installs the core framework with all required dependencies.

<Tip>
  For faster dependency resolution and better virtual environment management, consider using [uv](https://github.com/astral-sh/uv) instead of pip. On macOS and Linux, install uv with:

  ```bash theme={null} theme={null}
  curl -LsSf https://astral.sh/uv/install.sh | sh
  uv pip install agentor
  ```
</Tip>

## Install from source

To install the latest development version directly from GitHub:

```bash theme={null} theme={null}
pip install git+https://github.com/celestoai/agentor@main
```

<Warning>
  The development version may contain unreleased features and breaking changes. Use this only if you need cutting-edge features or want to contribute.
</Warning>

## Optional dependencies

Agentor provides optional dependencies for specific tools and integrations:

### Exa search

```bash theme={null} theme={null}
pip install agentor[exa]
```

### Git operations

```bash theme={null} theme={null}
pip install agentor[git]
```

### GitHub integration

```bash theme={null} theme={null}
pip install agentor[github]
```

### PostgreSQL database

```bash theme={null} theme={null}
pip install agentor[postgres]
```

### Slack integration

```bash theme={null} theme={null}
pip install agentor[slack]
```

### ScrapeGraph AI

```bash theme={null} theme={null}
pip install agentor[scrapegraph]
```

<Info>
  The `scrapegraph` extra requires **Python 3.12 or newer** because `scrapegraph-py>=2.1.0` does not ship wheels for Python 3.10 or 3.11. On older interpreters, the extra installs but the SDK is skipped, and instantiating `ScrapeGraphAI` raises `ImportError`. See the [ScrapeGraphAI tool reference](/agentor/api/tools/scrapegraphai) for the full capability surface.
</Info>

### Install all optional dependencies

```bash theme={null} theme={null}
pip install agentor[all]
```

## Set up environment variables

Agentor requires API keys to connect to LLM providers. Create a `.env` file in your project root:

```bash .env theme={null} theme={null}
# OpenAI (for gpt-4, gpt-5, etc.)
OPENAI_API_KEY=sk-...

# Anthropic (for Claude models)
ANTHROPIC_API_KEY=sk-ant-...

# Google (for Gemini models)
GEMINI_API_KEY=...

# Celesto (for observability and deployment)
CELESTO_API_KEY=...
```

<Note>
  You only need the API key for the LLM provider you plan to use. Agentor supports 100+ LLM providers through LiteLLM.
</Note>

## Load environment variables

In your Python code, load the environment variables:

```python theme={null} theme={null}
import dotenv

dotenv.load_dotenv()
```

Or set them directly in your shell:

```bash theme={null} theme={null}
export OPENAI_API_KEY=sk-...
export CELESTO_API_KEY=...
```

## Verify installation

Confirm Agentor is installed correctly:

```python theme={null} theme={null}
import agentor

print(agentor.__version__)
```

You should see the version number printed (e.g., `0.0.22`).

## Enable observability (optional)

To enable automatic tracing and monitoring, set your Celesto API key:

```bash theme={null} theme={null}
export CELESTO_API_KEY=your_api_key
```

Get your API key from the [Celesto dashboard](https://celesto.ai/dashboard).

When the `CELESTO_API_KEY` environment variable is set, Agentor automatically enables LLM monitoring and tracing:

```python theme={null} theme={null}
from agentor import Agentor

# Tracing enabled automatically if CELESTO_API_KEY is set
agent = Agentor(
    name="My Agent",
    model="gpt-5-mini"
)
```

View traces at [https://celesto.ai/observe](https://celesto.ai/observe).

To disable automatic tracing:

```bash theme={null} theme={null}
export CELESTO_DISABLE_AUTO_TRACING=True
```

## Next steps

<CardGroup cols={2}>
  <Card title="Quick start" icon="bolt" href="/agentor/quickstart">
    Build your first agent in under 5 minutes
  </Card>

  <Card title="Model settings" icon="gear" href="/agentor/api/model-settings">
    Learn about model settings and configuration options
  </Card>
</CardGroup>