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

# Agent Manager: Enterprise AI Agent Orchestration

> Agent Manager is a secure, private control plane for deploying and orchestrating autonomous LLM-based agents. Build, run, and monitor AI workflows at scale.

Agent Manager gives you a complete platform for running AI agents in production. Connect to OpenAI, Anthropic, or Google models; equip agents with tools and knowledge; orchestrate multi-agent teams; and monitor every run — all within your own infrastructure, with no data leaving to third-party platforms.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Make your first agent run in under five minutes
  </Card>

  <Card title="Core Concepts" icon="book-open" href="/concepts">
    Understand agents, runs, sessions, and memory
  </Card>

  <Card title="API Reference" icon="code" href="/api/agents/list">
    Full REST API with request and response examples
  </Card>

  <Card title="Multi-Agent Teams" icon="users" href="/features/teams">
    Coordinate and route work across multiple agents
  </Card>
</CardGroup>

## What you can build

<CardGroup cols={2}>
  <Card title="Streaming Chat" icon="message" href="/features/chat">
    Real-time token streaming with reasoning traces visible to users
  </Card>

  <Card title="Knowledge Base (RAG)" icon="database" href="/knowledge/knowledge-base">
    Upload PDFs and URLs; agents search your docs automatically
  </Card>

  <Card title="Automated Workflows" icon="diagram-project" href="/features/workflows">
    Chain agent steps into repeatable, durable pipelines
  </Card>

  <Card title="Human-in-the-Loop" icon="hand" href="/features/agents">
    Pause sensitive operations and require human approval to continue
  </Card>
</CardGroup>

## Get started

<Steps>
  <Step title="Configure your LLM provider">
    Set your `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, or `GOOGLE_API_KEY`. Agent Manager automatically activates the providers with valid keys.
  </Step>

  <Step title="Start the server">
    Boot the backend with `./mvnw spring-boot:run`. It seeds default agents and connects to PostgreSQL on startup.
  </Step>

  <Step title="Run your first agent">
    Send a POST request to `/api/agents/{agentId}/runs` with a message. Get back a complete response with tool traces.
  </Step>

  <Step title="Explore the UI">
    Open the Agent Manager UI at `http://localhost:5173` to chat, manage knowledge, and inspect runs visually.
  </Step>
</Steps>

<Note>
  Agent Manager is **private by design** — all conversation history, memory, and knowledge embeddings are stored exclusively in your PostgreSQL instance. No user data is sent to external observability platforms unless you explicitly configure it.
</Note>