# Agent Manager

## Docs

- [Background Agent Runs — Async Execution API](https://operativusai.mintlify.app/api/agents/background.md): Submit agent runs that execute asynchronously and poll for completion — ideal for long-running tasks and batch processing pipelines.
- [GET /api/agents — List and Retrieve Agent Definitions](https://operativusai.mintlify.app/api/agents/list.md): Retrieve all registered agents or fetch a single agent definition by ID, including is_team flags, display names, and capability descriptions.
- [Run an Agent Synchronously — API Reference](https://operativusai.mintlify.app/api/agents/run.md): Execute an agent synchronously and receive the complete RunResponse in one request, with built-in HITL pause/resume and cancellation support.
- [Stream Agent Responses via SSE — API Reference](https://operativusai.mintlify.app/api/agents/stream.md): Execute an agent run over a Server-Sent Events stream and receive reasoning traces, tool call notifications, and content deltas in real time.
- [Knowledge Base API — Upload, Search, Delete](https://operativusai.mintlify.app/api/knowledge.md): Manage RAG documents: upload files, run semantic search against vector embeddings, delete documents, and trigger URL ingestion for agents.
- [Memory API — Long-Term User Facts](https://operativusai.mintlify.app/api/memory.md): Store, search, optimize, and delete semantic vector memories that persist user preferences and facts across all agent conversations.
- [Sessions API — Conversation History](https://operativusai.mintlify.app/api/sessions.md): List, retrieve, and delete agent conversation sessions, and fetch the complete run history within each session for auditing and replay.
- [Teams API — Multi-Agent Orchestration](https://operativusai.mintlify.app/api/teams.md): Configure, manage, and run multi-agent teams using Coordinator or Router orchestration modes, with member management and real-time SSE streaming.
- [Workflows API — Create and Execute Pipelines](https://operativusai.mintlify.app/api/workflows.md): Design, manage, and execute deterministic multi-step agent workflows with CRUD operations, step management, cloning, and paginated run history.
- [Key Concepts: Agents, Runs, Sessions, and Memory](https://operativusai.mintlify.app/concepts.md): Understand the core building blocks of Agent Manager — agents, runs, sessions, knowledge bases, memory, teams, workflows, HITL, and MCP.
- [Managing and Running AI Agents](https://operativusai.mintlify.app/features/agents.md): Learn how to list, inspect, and execute AI agents in Agent Manager, including synchronous runs, Human-in-the-Loop approvals, and run cancellation.
- [Real-Time Streaming Chat with AI Agents](https://operativusai.mintlify.app/features/chat.md): Stream agent responses token-by-token via Server-Sent Events, inspect live reasoning steps, and send multimodal image inputs to vision-capable agents.
- [Multi-Agent Teams: Coordinator and Router](https://operativusai.mintlify.app/features/teams.md): Orchestrate specialist AI agents using Coordinator and Router strategies to answer complex, multi-domain queries that no single agent can handle alone.
- [Automating Multi-Step Agent Workflows](https://operativusai.mintlify.app/features/workflows.md): Design and run durable multi-step pipelines where each step invokes an AI agent, with async execution, Human-in-the-Loop pausing, and workflow cloning.
- [Agent Manager: Private AI Agent Orchestration Platform](https://operativusai.mintlify.app/introduction.md): Agent Manager is an enterprise control plane for autonomous LLM agents with streaming, HITL, RAG, multi-agent teams, and FinOps — private by design.
- [Building a Knowledge Base for RAG-Powered Agents](https://operativusai.mintlify.app/knowledge/knowledge-base.md): Upload PDF and text documents into vector storage so your agents can retrieve accurate, domain-specific information using Active RAG on demand.
- [Long-Term Memory: Persistent User Facts](https://operativusai.mintlify.app/knowledge/memory.md): Store semantic facts about users in vector storage so agents recall preferences and context across every conversation, not just the current one.
- [Sessions: Conversation History and Context](https://operativusai.mintlify.app/knowledge/sessions.md): Group agent runs into sessions to maintain multi-turn conversation history and short-term episodic memory across related requests.
- [Evaluating Agent Performance and Quality](https://operativusai.mintlify.app/platform/evaluations.md): How to create evaluation suites, add test cases with expected outputs, run suites against agents, and track scores and pass rates over time.
- [FinOps: Budget Controls and Usage Tracking](https://operativusai.mintlify.app/platform/finops.md): How to track LLM token usage and costs per agent, set burn-rate baselines, detect spending anomalies, and query Prometheus metrics for cost visibility.
- [Model Context Protocol (MCP) Integration](https://operativusai.mintlify.app/platform/mcp.md): How to connect MCP-compatible clients like Claude Desktop and Cursor to Agent Manager, authenticate over SSE, and invoke your agents as MCP tools.
- [Configuring LLM Providers and Models](https://operativusai.mintlify.app/platform/models.md): How to activate OpenAI, Anthropic, and Google providers by setting API keys, view available models, assign models per-run, and manage provider health.
- [Scheduling Automated Agent Runs](https://operativusai.mintlify.app/platform/scheduling.md): How to create, manage, and monitor scheduled agent runs using cron expressions, view run history per schedule, and manually trigger executions.
- [Agent Manager Quickstart: First Run in Minutes](https://operativusai.mintlify.app/quickstart.md): Boot the Agent Manager backend, make your first synchronous agent run via the REST API, and open the management UI — all in under ten minutes.
- [Authenticating Requests to Agent Manager](https://operativusai.mintlify.app/security/authentication.md): How to obtain a JWT access token, authenticate API requests with Bearer headers, associate runs with users and orgs, and handle SSE streaming auth.
- [Guardrails: PII, Injection, and Content Safety](https://operativusai.mintlify.app/security/guardrails.md): Agent Manager's built-in safety layers: PII redaction, prompt injection blocking, output moderation, and sandboxed code execution active on every request.
- [Security and Privacy in Agent Manager](https://operativusai.mintlify.app/security/overview.md): How Agent Manager keeps data private with PII redaction, injection protection, sandboxed code execution, RBAC, and full audit logging on by default.

## OpenAPI Specs

- [openapi](https://operativusai.mintlify.app/api-reference/openapi.json)