--- title: "CrewAI Documentation" description: "Build collaborative AI agents, crews, and flows — production ready from day one." icon: "house" mode: "wide" ---
CrewAI

Ship multi‑agent systems with confidence

Design agents, orchestrate crews, and automate flows with guardrails, memory, knowledge, and observability baked in.

Install Quickstart First Crew First Flow LLM Setup API Reference
## Start in 3 steps Install via `uv`, configure API keys, and set up the CLI for local development. Launch your first working crew with a minimal project and iterate from there. Continue with canonical domain packs for Flows, Agents, Crews, LLMs, Memory, and Tools. ## Most-used pages Build a production-style crew with role/task configuration and execution flow. Build event-driven orchestration with state, listeners, and routing. Stateful chat history pattern with persistence and summary compaction. Agent role design, tool boundaries, and output contracts. Multi-agent collaboration patterns and process semantics. Deterministic orchestration, state lifecycle, persistence, and resume. Model setup, provider config, routing patterns, and reliability defaults. Semantic recall, scope strategy, and state-vs-memory architecture. Tool categories, integration surfaces, and practical usage patterns. ## Build the basics Compose agents with tools, memory, knowledge, and structured outputs using Pydantic. Includes templates and best practices. Orchestrate start/listen/router steps, manage state, persist execution, and resume long-running workflows. Define sequential, hierarchical, or hybrid processes with guardrails, callbacks, and human-in-the-loop triggers. ## Enterprise journey Manage environments, redeploy safely, and monitor live runs directly from the Enterprise console. Connect Gmail, Slack, Salesforce, and more. Pass trigger payloads into crews and flows automatically. Invite teammates, configure RBAC, and control access to production automations. ## What’s new Unified overview for Gmail, Drive, Outlook, Teams, OneDrive, HubSpot, and more — now with sample payloads and crews. Call existing CrewAI automations or Amazon Bedrock Agents directly from your crews using the updated integration toolkit. Browse the examples and cookbooks for end-to-end reference implementations across agents, flows, and enterprise automations. For a practical conversational pattern, start with Flowstate Chat History. Use the AI-First Documentation map for canonical domain packs across Flows, Agents, Crews, LLMs, Memory, and Tools. ## Stay connected If CrewAI helps you ship faster, give us a star and share your builds with the community. Ask questions, showcase workflows, and request features alongside other builders.