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

# Welcome

> Complete reference documentation for the Artaios Multi-Agent System API

Welcome to the API reference documentation for the Artaios Multi-Agent System (AMAS). This API allows you to programmatically create, configure, and execute intelligent agents for a wide range of tasks and workflows.

## API Overview

The AMAS API is organized around REST principles. It accepts JSON and YAML-encoded request bodies, returns JSON-encoded responses, and uses standard HTTP response codes, authentication, and verbs.

<CardGroup cols={2}>
  <Card title="Base URL" icon="server" color="#6366F1">
    All API requests should be made to:

    ```
    https://api.artaios.ai/api/v1
    ```
  </Card>

  <Card title="API Versioning" icon="code-branch" color="#6366F1">
    The current API version is `v1`. All endpoints are prefixed with `/api/v1/`.
  </Card>
</CardGroup>

<Note>
  For a comprehensive interactive API reference, visit the [Swagger Documentation](https://api.artaios.ai/api/v1/docs/).
</Note>

## Key Concepts

<AccordionGroup>
  <Accordion title="Agents">
    Agents are AI-powered entities configured with specific capabilities, instructions, and behaviors. AMAS supports two types: **LLM Agents** (conversational) and **ReAct Agents** (tool-using, reasoning agents).
  </Accordion>

  <Accordion title="Sessions">
    A session represents a conversation instance with an agent. Each session maintains its own message history and state. Sessions are created with a complete agent configuration in YAML or JSON format.
  </Accordion>

  <Accordion title="Runtime">
    The Runtime API allows you to execute messages in sessions and interact with agents in real-time. Send user messages, retrieve agent responses, access conversation history, and monitor execution status with detailed metadata and usage statistics.
  </Accordion>

  <Accordion title="Knowledge Bases">
    Knowledge bases provide agents with access to domain-specific information through semantic search. AMAS supports Milvus vector database for production-ready retrieval.
  </Accordion>

  <Accordion title="Collections & Files">
    Files are uploaded documents that can be organized into collections. Collections group related data sources for knowledge base ingestion and management.
  </Accordion>
</AccordionGroup>

## Getting Started

<Steps>
  <Step title="Get your API key">
    Contact your administrator or use the dashboard to generate an API key.

    <Warning>
      Keep your API keys secure! Do not expose them in client-side code or public repositories.
    </Warning>
  </Step>

  <Step title="Validate your agent configuration">
    Test your agent configuration before creating a session:

    <CodeGroup>
      ```bash cURL theme={null}
      curl -X POST https://api.artaios.ai/api/v1/agent/validate/ \
        -H "x-api-key: YOUR_API_KEY" \
        -H "Content-Type: application/json" \
        -d '{
          "name": "My First Agent",
          "agent_type": "llm_agent",
          "system_prompt": "You are a helpful assistant.",
          "llm_config": {
            "model": "gpt-4o",
            "temperature": 0.7
          }
        }'
      ```
    </CodeGroup>
  </Step>

  <Step title="Create a session and execute">
    Create a session with your configuration and start executing messages:

    <CodeGroup>
      ```bash cURL theme={null}
      # Create session
      curl -X POST https://api.artaios.ai/api/v1/sessions/ \
        -H "x-api-key: YOUR_API_KEY" \
        -H "Content-Type: application/json" \
        -d '{
          "name": "My Session",
          "agent_type": "llm_agent",
          "system_prompt": "You are a helpful assistant.",
          "llm_config": {"model": "gpt-4o"}
        }'

      # Execute message
      curl -X POST https://api.artaios.ai/api/v1/runtime/SESSION_ID/execute/ \
        -H "x-api-key: YOUR_API_KEY" \
        -H "Content-Type: application/json" \
        -d '{"content": "Hello, how can you help me?"}'
      ```
    </CodeGroup>
  </Step>
</Steps>

## What's Next

Explore the full API documentation to learn about all available endpoints and features:

<CardGroup cols={2}>
  <Card title="Authentication" icon="key" href="/api-reference/authentication">
    Learn how to authenticate your API requests
  </Card>
</CardGroup>