workflowstacks
multi-agent

crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
59,527 stars+219★ this week8,678 forksPythonInstall verified Sep 14Updated 10/9/2026100% free · open source
What it does

CrewAI enables the creation of autonomous AI agents that collaborate to solve complex tasks by role-playing and working together seamlessly.

When to use it
  • •When you need to simulate real-world scenarios with multiple interacting agents
  • •When your startup requires modeling complex systems with autonomous decision-making entities
  • •When you want to develop AI solutions that can adapt and learn from each other
Ready-to-paste prompt
python examples/basic_example.py -c examples/config.json -n 5 -t 10
Heads up: Ensure you have Python 3.8 or later installed, as CrewAI is not compatible with earlier Python versions
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box✓ Install verified 9/14/2026

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/crewai && curl -fsSL https://workflowstacks.com/api/skills/crewai/claude-skill -o ~/.claude/skills/crewai/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How crewAI works
Codeflow
Free to inspect

CrewAI is mostly documents (24148 doc files, 919 small scripts) — something you read, not something you run. You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, MIT license.

Size
Mostly documents
24148 documents · 919 small scripts · days to read — use, don't read
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 3 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Helper scripts use Python
Python 99%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    lib/cli/README.md
    Inside lib/ — the main logic begins here
What's in each folder
lib/Core code — the actual logic2067 files
docs/Documentation24267 files
scripts/Helper scripts4 files
.github/CI / automation (GitHub Actions)21 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
crewAIInc
Language
Python
Category
multi-agent
Published
10/27/2023

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/crewai.svg)](https://workflowstacks.com/skills/crewai?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Related skills

More multi-agent tools founders pair with this one.

multi-agent★ 110,457
TradingAgents
TradingAgents: Multi-Agents LLM Financial Trading Framework
multi-agent★ 10,716
Orchestrate AI Agents with Omnigent
Swap harnesses without rewriting code with Omnigent, a framework for startup founders. 5.6k+ GitHub stars
multi-agent★ 4,586
Council of High Intelligence: Informed Decisions
Get structured multi-round deliberation for your toughest decisions with Council of High Intelligence, ideal for startup founders, backed by 3.2k+ GitHub stars
multi-agent★ 18
vmux: Control coding agents
Monitor and respond to coding agents from your phone with vmux, for founders using tmux and coding agents.
multi-agent★ 3,887
LazyLLM: Build Multi‑Agent LLM Apps Quickly with Minimal Code
Launch multi‑agent LLM applications in minutes—perfect for founders who want AI power without complex setup. Backed by 3.9k+ GitHub stars.
multi-agent★ 76
AKO4X: Optimize GPU Kernels
Get optimized GPU kernels with AKO4X, a closed-loop multi-agent system for startup founders, currently with 58 GitHub stars.