Back to directory

CrewAI

CrewAI is a Python framework for production multi-agent workflows, offering role-based autonomous agent "Crews" alongside precise, event-driven "Flows" that mix single LLM calls with agent collaboration.

CrewAI

Crews optimize for autonomous, role-based collaboration among agents, while Flows give a developer precise, event-driven control that can still call into a Crew where needed; the framework provides both high-level abstractions and lower-level APIs for building production multi-agent systems. A commercial AMP Suite adds an optional control plane on top, with tracing, a unified dashboard, enterprise integrations, security controls and support; one part of that suite, a Crew Control Plane, can be tried for free.

A Claude Code plugin teaches project conventions automatically, covering scaffolding new projects, configuring an agent's role and tools, writing task descriptions with structured output, and querying the live CrewAI documentation through an MCP server; the same skills also install for Cursor, Codex and Windsurf through a general skills installer.

MIT licensed.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.