Install Agentor and configure LLM providers

Install the Agentor Python framework on macOS, Linux, or Windows with pip or uv, pick the optional extras you need, and set up your LLM provider API keys.

Requirements

Before installing Agentor, make sure you have:

• Python 3.11 or higher — check your version with python --version
• pip or uv package manager
• An API key from your LLM provider (OpenAI, Anthropic, Google, and many more)

Install from PyPI

pip install agentor

0.1.0 rebuilt the agent engine and is a breaking change from the 0.0.x line — DurableAgent is gone and hosted tools were dropped. See the 0.1.0 release notes for what changed and how to migrate.

To stay on the old 0.0.x line instead, pin it explicitly:

pip install "agentor<0.1"

For faster dependency resolution and better virtual environment management, use uv. On macOS and Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh
uv pip install agentor

Install from source

To install the latest development version directly from GitHub:

pip install git+https://github.com/celestoai/agentor@main

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

Optional dependencies

The core install stays small. Tools that need a heavyweight SDK live behind an extra, so you only download what you use.

Extra	Install	Needed by
google	pip install "agentor[google]"	GmailTool, CalendarTool, SuperAuth
exa	pip install "agentor[exa]"	ExaSearchTool
git	pip install "agentor[git]"	GitTool
github	pip install "agentor[github]"	GitHubTool
postgres	pip install "agentor[postgres]"	PostgreSQLTool
slack	pip install "agentor[slack]"	SlackTool
scrapegraph	pip install "agentor[scrapegraph]"	ScrapeGraphAI
all	pip install "agentor[all]"	Everything above

Google tools moved in 0.1.0. The Google API client and SuperAuth are roughly 100 MB and used to be installed for everyone. They are now in the google extra. If GmailTool or CalendarTool raises an ImportError, run pip install "agentor[google]".

The scrapegraph extra requires Python 3.12 or newer, because scrapegraph-py>=2.1.0 ships no wheels for 3.11. On 3.11 the extra installs but the SDK is skipped, and instantiating ScrapeGraphAI raises ImportError. See the ScrapeGraphAI tool reference for the full capability surface.

Set up environment variables

Agentor reads provider credentials from the environment. Create a .env file in your project root:

.env

# OpenAI (for gpt-4o, 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=...

You only need the key for the provider you plan to use. Agentor reaches most providers through their OpenAI-compatible endpoint, and the rest through LiteLLM.

Load environment variables

In your Python code, load the environment variables:

import dotenv

dotenv.load_dotenv()

Or set them directly in your shell:

export OPENAI_API_KEY=sk-...
export CELESTO_API_KEY=...

Verify installation

Confirm Agentor is installed correctly:

import agentor

print(agentor.__version__)

You should see 0.1.0 (or later), or a 0.0.x version if you pinned the old line.

import agentor should return almost instantly. Heavy dependencies are loaded only when something actually needs them.

Enable observability (optional)

To turn on tracing and monitoring, set your Celesto API key:

export CELESTO_API_KEY=your_api_key

Get your key from the Celesto dashboard.

Tracing is off unless you ask for it. Opt in on the agent, or on a single call:

from agentor import Agentor

agent = Agentor(
    name="My Agent",
    model="gpt-5-mini",
    enable_tracing=True,   # trace every run this agent makes
)

# Or trace one call from an otherwise-untraced agent.
agent.run("Debug this", tracing=True)

View traces at celesto.ai/observe. See Tracing for the full guide.

Next steps

Quick start

Build your first agent in under 5 minutes.

Model providers

Point Agentor at OpenRouter, Groq, Ollama, or any compatible endpoint.

Model settings

Tune temperature, token limits, and other generation parameters.

Durable runs

Save runs so a new process can finish them after a crash.