Back to directory

CrewAI Quickstarts

A collection of runnable quickstarts and feature demos for the CrewAI multi-agent framework, each a self-contained Jupyter notebook or Python example meant to be extended for a developer's own project.

CrewAI Quickstarts

CrewAI Quickstarts is a collection of hands-on examples for learning the CrewAI framework for building multi-agent systems. Each quickstart is self-contained, covering a specific CrewAI feature or pattern, and is meant to be run, modified and built upon rather than read as documentation alone.

Running the examples needs Python 3.8 or newer, Jupyter Notebook, an API key from a model provider such as OpenAI, Anthropic or Cohere, and, for some examples, additional API keys for external tools such as SerperDev. Each quickstart directory is run independently by opening its notebook or Python file and following the instructions inside it. The project is maintained alongside CrewAI's official documentation, forum and cloud trial.

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.