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

# Atomic Agents

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

export const TechArticleSchema = ({title, description, path, articleSection, about, proficiencyLevel = "Beginner", dependencies, keywords = [], datePublished, dateModified, image, inLanguage = "en"}) => {
  const baseUrl = "https://www.edenai.co/docs";
  const canonicalUrl = `${baseUrl}/${path}`.replace(/\/+$/, "");
  const ogParams = new URLSearchParams({
    division: articleSection || "",
    title: title || "",
    description: description || ""
  });
  const resolvedImage = image || `https://edenai.mintlify.app/_mintlify/api/og?${ogParams.toString()}`;
  const data = {
    "@context": "https://schema.org",
    "@type": "TechArticle",
    "@id": `${canonicalUrl}#techarticle`,
    mainEntityOfPage: {
      "@type": "WebPage",
      "@id": canonicalUrl
    },
    headline: title,
    name: title,
    description: description,
    url: canonicalUrl,
    inLanguage: inLanguage,
    isPartOf: {
      "@type": "WebSite",
      name: "Eden AI Documentation",
      url: baseUrl
    },
    author: [{
      "@type": "Organization",
      name: "Eden AI",
      url: "https://www.edenai.co/"
    }],
    publisher: {
      "@type": "Organization",
      name: "Eden AI",
      url: "https://www.edenai.co/",
      logo: {
        "@type": "ImageObject",
        url: "https://www.edenai.co/assets/logo.png"
      }
    }
  };
  if (articleSection) data.articleSection = articleSection;
  if (about) data.about = {
    "@type": "Thing",
    name: about
  };
  if (proficiencyLevel) data.proficiencyLevel = proficiencyLevel;
  if (dependencies) data.dependencies = dependencies;
  if (keywords && keywords.length) data.keywords = keywords;
  if (datePublished) data.datePublished = datePublished;
  if (dateModified) data.dateModified = dateModified;
  data.image = Array.isArray(resolvedImage) ? resolvedImage : [resolvedImage];
  const json = JSON.stringify(data);
  const schemaId = `techarticle-${canonicalUrl}`;
  React.useEffect(() => {
    if (typeof document === "undefined") return;
    document.querySelectorAll(`script[data-schema-id="${schemaId}"]`).forEach(n => n.remove());
    const script = document.createElement("script");
    script.type = "application/ld+json";
    script.dataset.schemaId = schemaId;
    script.textContent = json;
    document.head.appendChild(script);
    return () => script.remove();
  }, [json, schemaId]);
  return null;
};

<TechArticleSchema title={"Atomic Agents"} description={"Use Atomic Agents with Eden AI to build agents on 500+ AI models through an OpenAI-compatible, Instructor-powered interface."} path="v3/integrations/atomic-agents" articleSection="AI Frameworks" about={"Agent Framework Integration"} proficiencyLevel="Intermediate" keywords={["Eden AI", "AI API", "Atomic Agents", "Python", "Instructor"]} datePublished="2026-07-27T00:00:00Z" dateModified="2026-07-27T00:00:00Z" />

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

## Overview

[Atomic Agents](https://github.com/Eigenwise/atomic-agents) is a lightweight, modular Python framework for building AI agents on composable, schema-driven building blocks (via [Instructor](https://github.com/instructor-ai/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:

<CodeGroup>
  ```bash pip theme={null}
  pip install atomic-agents openai instructor
  ```

  ```bash poetry theme={null}
  poetry add atomic-agents openai instructor
  ```
</CodeGroup>

## 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:

<CodeGroup>
  ```bash .env theme={null}
  EDENAI_API_KEY=your_api_key_here
  ```

  ```python Python theme={null}
  import os
  import instructor
  from openai import OpenAI
  from atomic_agents.agents.base_agent import BaseAgent, BaseAgentConfig

  client = instructor.from_openai(
      OpenAI(
          base_url="https://api.edenai.run/v3",
          api_key=os.getenv("EDENAI_API_KEY"),
      )
  )

  agent = BaseAgent(
      config=BaseAgentConfig(
          client=client,
          model="anthropic/claude-sonnet-5",  # <provider>/<model>
      )
  )

  response = agent.run(agent.input_schema(chat_message="Hello! How are you?"))
  print(response.chat_message)
  ```
</CodeGroup>

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:

<CodeGroup>
  ```python Python theme={null}
  for model in [
      "openai/gpt-5.5",
      "anthropic/claude-sonnet-5",
      "mistral/mistral-large-2512",
  ]:
      agent = BaseAgent(config=BaseAgentConfig(client=client, model=model))
      response = agent.run(agent.input_schema(chat_message="Write a haiku about the sea."))
      print(model, "->", response.chat_message)
  ```
</CodeGroup>

## 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

<CodeGroup>
  ```bash .env theme={null}
  EDENAI_API_KEY=your_api_key_here
  ```
</CodeGroup>

## Next Steps

* [aisuite](/docs/v3/integrations/aisuite) - Another OpenAI-style multi-provider interface
* [Chat Completions](/docs/v3/llms/chat-completions) - Core LLM endpoint
* [List LLM Models](/docs/v3/llms/listing-models) - Browse available providers and models