Skip to main content
Use Atomic Agents with Eden AI to build agents on 500+ AI models through an OpenAI-compatible, Instructor-powered interface.

Overview

Atomic Agents is a lightweight, modular Python framework for building AI agents on composable, schema-driven building blocks (via Instructor and Pydantic). Atomic Agents works with Eden AI out of the box through its existing OpenAI-compatible client, so your agents reach models from OpenAI, Anthropic, Google, Mistral and more behind one key, with EU-based, GDPR-aligned inference.

Installation

Eden AI reuses the OpenAI client and Instructor that Atomic Agents already relies on:

Quick Start

Wrap an OpenAI client pointed at Eden AI with Instructor — the same pattern used for any other OpenAI-compatible provider — and pass it to your agent:
Both Instructor TOOLS and JSON modes work unchanged with Eden AI.

Switching models

Change the model string on BaseAgentConfig to reach any Eden AI model — no per-provider SDKs, no code changes:

Available Models

Use the provider/model format for any Eden AI model: OpenAI
  • openai/gpt-5.5
  • openai/gpt-5-mini
Anthropic
  • anthropic/claude-sonnet-5
  • anthropic/claude-haiku-4-5
Google
  • google/gemini-2.5-pro
  • google/gemini-3.5-flash
Mistral
  • mistral/mistral-large-2512
  • mistral/mistral-small-2603

Environment Variables

Next Steps