crewai
Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Decision gist · record as of 2026-08-14
Yes, if you need to build multi-agent AI systems. CrewAI is actively maintained, widely adopted (12.3M monthly downloads, top 5000 packages), has no known vulnerabilities, and offers both high-level simplicity and low-level control. The main caveats are the unclear license (verify before commercial use), substantial dependency footprint, and the requirement for Python >=3.10 <3.14. Start with the free Crew Control Plane trial to evaluate the platform.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python >=3.10 <3.14; Rust compiler may be needed for some optional dependencies like tiktoken.
- Installation is straightforward with low friction; the package is actively maintained with a recent release and 57078 repository stars.
- The 31 runtime dependencies are substantial but typical for an agent framework, and the wheel distribution suggests good platform support.
License · maintenance · safety
(unclear) — License treatment is unclear—no SPDX identifier or raw license text is available in the package metadata. Verify the actual license at the repository or project homepage before adopting in proprietary or regulated contexts.
last release 2026-08-14 (0 days) · last repo commit 2026-08-14 · 57,078 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 12,349,909 downloads/mo, #1,324 on PyPI
Alternatives
Verify before relying
pip install crewai
from crewai import Agent, Task, Crew
agent = Agent(role="Analyst", goal="Analyze data")
task = Task(description="Analyze the dataset", agent=agent)
crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()- Whether the unclear license permits commercial use or has specific attribution requirements.
- Performance characteristics and scalability limits for large numbers of agents or complex workflows.
- Exact feature set and API stability guarantees across minor versions.
What it is and what it does
CrewAI is a framework for orchestrating autonomous AI agents that work together on complex tasks. It offers two complementary approaches: Crews, which are teams of agents with true autonomy and role-based collaboration, and Flows, which provide event-driven, production-ready workflows with fine-grained control. The framework is built independently from LangChain and other agent systems, emphasizing speed, flexibility, and low-level customization.
The package integrates with large language models (via openai and instructor), vector databases (chromadb, lancedb), document processing (pdfplumber), and observability tools (opentelemetry). It includes a CLI for project scaffolding and supports YAML-based configuration for agents and tasks. With 31 runtime dependencies, it provides a comprehensive toolkit for building production-grade agentic applications, though this also means a larger dependency footprint.
Use it for
- Build autonomous multi-agent systems where specialized agents collaborate to solve complex business problems or research tasks.
- Create event-driven workflows that combine AI agents with deterministic Python logic for production automation.
- Orchestrate document analysis, data extraction, or research tasks by delegating work across multiple agents with different expertise.
- Develop role-playing agent simulations or interactive AI systems where agents take on specific personas and responsibilities.
- Monitor and trace AI agent execution in real-time using the integrated observability and telemetry capabilities.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need to build multi-agent AI systems.
CrewAI is actively maintained, widely adopted (12.3M monthly downloads, top 5000 packages), has no known vulnerabilities, and offers both high-level simplicity and low-level control. The main caveats are the unclear license (verify before commercial use), substantial dependency footprint, and the requirement for Python >=3.10 <3.14. Start with the free Crew Control Plane trial to evaluate the platform.
Install
crewai on PyPI
Before you install
Installation is straightforward with low friction; the package is actively maintained with a recent release and 57078 repository stars. The 31 runtime dependencies are substantial but typical for an agent framework, and the wheel distribution suggests good platform support.
Requires Python >=3.10 <3.14; Rust compiler may be needed for some optional dependencies like tiktoken.
License in practice
License treatment is unclear—no SPDX identifier or raw license text is available in the package metadata. Verify the actual license at the repository or project homepage before adopting in proprietary or regulated contexts.
Quickstart
pip install crewai
from crewai import Agent, Task, Crew
agent = Agent(role="Analyst", goal="Analyze data")
task = Task(description="Analyze the dataset", agent=agent)
crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()Verify before relying
- Whether the unclear license permits commercial use or has specific attribution requirements.
- Performance characteristics and scalability limits for large numbers of agents or complex workflows.
- Exact feature set and API stability guarantees across minor versions.
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release <3.14,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 31 packagesaiofilesaiosqliteappdirscel-pythonchromadbclickcrewai-clicrewai-corehttpxinstructorjson-repairjson5jsonreflancedbmcpopenaiopenpyxlopentelemetry-apiopentelemetry-exporter-otlp-proto-httpopentelemetry-sdkpdfplumberportalockerpydantic-settingspydanticpyjwtpython-dotenvpyyamlregextokenizerstomli-w |
| Maintenance | Actively maintained 0 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 12,349,909 / month, #1,324 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: crewai-1.15.16-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “AI agent collaboration”
- crewaiCrewAI is a Python framework for building multi-agent AI systems…
- autogenA framework for building AI agents that communicate with each other…
- opencode-agent-hubCoordinates communication between multiple AI agents running in…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also crewai-core · crewai-files · crewai-cli · crewai-tools · openinference-instrumentation-crewai · datarobot-genai · camel-ai · copilotkit · PraisonAI · praisonaiagents