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:TOOLS and JSON modes work unchanged with Eden AI.
Switching models
Change themodel string on BaseAgentConfig to reach any Eden AI model — no per-provider SDKs, no code changes:
Available Models
Use theprovider/model format for any Eden AI model:
OpenAI
openai/gpt-5.5openai/gpt-5-mini
anthropic/claude-sonnet-5anthropic/claude-haiku-4-5
google/gemini-2.5-progoogle/gemini-3.5-flash
mistral/mistral-large-2512mistral/mistral-small-2603
Environment Variables
Next Steps
- aisuite - Another OpenAI-style multi-provider interface
- Chat Completions - Core LLM endpoint
- List LLM Models - Browse available providers and models