CrewAI: Framework for orchestrating role-playing, autonomous AI agents

Gemini 3 Flash

原文链接: https://developers.googleblog.com/gemini-3-flash-is-now-available-in-gemini-cli/

英文原文

crewAIInc/crewAI: Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

原文链接: https://github.com/crewAIInc/crewAI

https://github.com/crewAIInc/crewAI https://trendshift.io/repositories/11239 Homepage · Docs · Start Cloud Trial · Blog · Forum https://github.com/crewAIInc/crewAIhttps://github.com/crewAIInc/crewAI/network/membershttps://github.com/crewAIInc/crewAI/issueshttps://github.com/crewAIInc/crewAI/pullshttps://opensource.org/licenses/MIT https://pypi.org/project/crewai/https://pypi.org/project/crewai/https://twitter.com/crewAIInc

Fast and Flexible Multi-Agent Automation Framework

#fast-and-flexible-multi-agent-automation-framework

CrewAI is a lean, lightning-fast Python framework built entirely from scratch—completely independent of LangChain or other agent frameworks. It empowers developers with both high-level simplicity and precise low-level control, ideal for creating autonomous AI agents tailored to any scenario.

With over 100,000 developers certified through our community courses at learn.crewai.com, CrewAI is rapidly becoming the standard for enterprise-ready AI automation.

• CrewAI Crews: Optimize for autonomy and collaborative intelligence.
• CrewAI Flows: The enterprise and production architecture for building and deploying multi-agent systems. Enable granular, event-driven control, single LLM calls for precise task orchestration and supports Crews natively

CrewAI AMP Suite

#crewai-amp-suite CrewAI AMP Suite is a comprehensive bundle tailored for organizations that require secure, scalable, and easy-to-manage agent-driven automation. You can try one part of the suite the Crew Control Plane for free

Crew Control Plane Key Features:

#crew-control-plane-key-features

CrewAI AMP is designed for enterprises seeking a powerful, reliable solution to transform complex business processes into efficient, intelligent automations.

• Tracing & Observability: Monitor and track your AI agents and workflows in real-time, including metrics, logs, and traces.
• Unified Control Plane: A centralized platform for managing, monitoring, and scaling your AI agents and workflows.
• Seamless Integrations: Easily connect with existing enterprise systems, data sources, and cloud infrastructure.
• Advanced Security: Built-in robust security and compliance measures ensuring safe deployment and management.
• Actionable Insights: Real-time analytics and reporting to optimize performance and decision-making.
• 24/7 Support: Dedicated enterprise support to ensure uninterrupted operation and quick resolution of issues.
• On-premise and Cloud Deployment Options: Deploy CrewAI AMP on-premise or in the cloud, depending on your security and compliance requirements.

Table of contents

#table-of-contents

• Build with AI
• Why CrewAI?
• Getting Started
• Key Features
• Understanding Flows and Crews
• CrewAI vs LangGraph
• Examples
• Quick Tutorial
• Write Job Descriptions
• Trip Planner
• Stock Analysis
• Using Crews and Flows Together
• Connecting Your Crew to a Model
• How CrewAI Compares
• Frequently Asked Questions (FAQ)
• Contribution
• Telemetry
• License

Build with AI

#build-with-ai Using an AI coding agent? Teach it CrewAI best practices in one command: Claude Code: /plugin marketplace add crewAIInc/skills /plugin install crewai-skills@crewai-plugins /reload-plugins Four skills that activate automatically when you ask relevant CrewAI questions: Skill When it runs getting-started Scaffolding new projects, choosing between LLM.call() / Agent / Crew / Flow, wiring crew.py / main.py design-agent Configuring agents — role, goal, backstory, tools, LLMs, memory, guardrails design-task Writing task descriptions, dependencies, structured output (output_pydantic, output_json), human review ask-docs Querying the live CrewAI docs MCP server for up-to-date API details Cursor, Codex, Windsurf, and others (skills.sh): npx skills add crewaiinc/skills This installs the official CrewAI Skills — structured instructions that teach coding agents how to scaffold Flows, configure Crews, design agents and tasks, and follow CrewAI patterns.

Why CrewAI?

#why-crewai /crewAIInc/crewAI/blob/main/docs/images/asset.png CrewAI unlocks the true potential of multi-agent automation, delivering the best-in-class combination of speed, flexibility, and control with either Crews of AI Agents or Flows of Events:

CrewAI empowers developers and enterprises to confidently build intelligent automations, bridging the gap between simplicity, flexibility, and performance.

• Standalone Framework: Built from scratch, independent of LangChain or any other agent framework.
• High Performance: Optimized for speed and minimal resource usage, enabling faster execution.
• Flexible Low Level Customization: Complete freedom to customize at both high and low levels - from overall workflows and system architecture to granular agent behaviors, internal prompts, and execution logic.
• Ideal for Every Use Case: Proven effective for both simple tasks and highly complex, real-world, enterprise-grade scenarios.
• Robust Community: Backed by a rapidly growing community of over 100,000 certified developers offering comprehensive support and resources.

Getting Started

#getting-started Setup and run your first CrewAI agents by following this tutorial. https://www.youtube.com/watch?v=-kSOTtYzgEw "CrewAI Getting Started Tutorial" Learning Resources Learn CrewAI through our comprehensive courses:

• Multi AI Agent Systems with CrewAI - Master the fundamentals of multi-agent systems
• Practical Multi AI Agents and Advanced Use Cases - Deep dive into advanced implementations

Understanding Flows and Crews

#understanding-flows-and-crews CrewAI offers two powerful, complementary approaches that work seamlessly together to build sophisticated AI applications: 1. Crews: Teams of AI agents with true autonomy and agency, working together to accomplish complex tasks through role-based collaboration. Crews enable:

2. Flows: Production-ready, event-driven workflows that deliver precise control over complex automations. Flows provide:

The true power of CrewAI emerges when combining Crews and Flows. This synergy allows you to:

• Natural, autonomous decision-making between agents
• Dynamic task delegation and collaboration
• Specialized roles with defined goals and expertise
• Flexible problem-solving approaches
• Fine-grained control over execution paths for real-world scenarios
• Secure, consistent state management between tasks
• Clean integration of AI agents with production Python code
• Conditional branching for complex business logic
• Build complex, production-grade applications
• Balance autonomy with precise control
• Handle sophisticated real-world scenarios
• Maintain clean, maintainable code structure

Getting Started with Installation

#getting-started-with-installation To get started with CrewAI, follow these simple steps:

1\. Installation

#1-installation Ensure you have Python >=3.10 <3.14 installed on your system. CrewAI uses UV for dependency management and package handling, offering a seamless setup and execution experience. First, install CrewAI: uv pip install crewai If you want to install the 'crewai' package along with its optional features that include additional tools for agents, you can do so by using the following command: uv pip install 'crewai\[tools\]' The command above installs the basic package and also adds extra components which require more dependencies to function.

Troubleshooting Dependencies

#troubleshooting-dependencies If you encounter issues during installation or usage, here are some common solutions:

Common Issues

#common-issues 1. ModuleNotFoundError: No module named 'tiktoken'

2. Failed building wheel for tiktoken

• Install tiktoken explicitly: uv pip install 'crewai[embeddings]'
• If using embedchain or other tools: uv pip install 'crewai[tools]'
• Ensure Rust compiler is installed (see installation steps above)
• For Windows: Verify Visual C++ Build Tools are installed
• Try upgrading pip: uv pip install --upgrade pip
• If issues persist, use a pre-built wheel: uv pip install tiktoken --prefer-binary

2\. Setting Up Your Crew with the YAML Configuration

#2-setting-up-your-crew-with-the-yaml-configuration To create a new CrewAI project, run the following CLI (Command Line Interface) command: crewai create crew <project\_name\> This command creates a new project folder with the following structure:

my_project/
├── .gitignore
├── pyproject.toml
├── README.md
├── .env
└── src/
    └── my_project/
        ├── __init__.py
        ├── main.py
        ├── crew.py
        ├── tools/
        │   ├── custom_tool.py
        │   └── __init__.py
        └── config/
            ├── agents.yaml
            └── tasks.yaml

You can now start developing your crew by editing the files in the src/my_project folder. The main.py file is the entry point of the project, the crew.py file is where you define your crew, the agents.yaml file is where you define your agents, and the tasks.yaml file is where you define your tasks.

To customize your project, you can:

#to-customize-your-project-you-can

• Modify src/my_project/config/agents.yaml to define your agents.
• Modify src/my_project/config/tasks.yaml to define your tasks.
• Modify src/my_project/crew.py to add your own logic, tools, and specific arguments.
• Modify src/my_project/main.py to add custom inputs for your agents and tasks.
• Add your environment variables into the .env file.

Example of a simple crew with a sequential process:

#example-of-a-simple-crew-with-a-sequential-process Instantiate your crew: crewai create crew latest-ai-development Modify the files as needed to fit your use case: agents.yaml

src/my\_project/config/agents.yaml

researcher: role: \> {topic} Senior Data Researcher goal: \> Uncover cutting-edge developments in {topic} backstory: \> You're a seasoned researcher with a knack for uncovering the latest developments in {topic}. Known for your ability to find the most relevant information and present it in a clear and concise manner. reporting\_analyst: role: \> {topic} Reporting Analyst goal: \> Create detailed reports based on {topic} data analysis and research findings backstory: \> You're a meticulous analyst with a keen eye for detail. You're known for your ability to turn complex data into clear and concise reports, making it easy for others to understand and act on the information you provide. tasks.yaml

src/my\_project/config/tasks.yaml

research\_task: description: \> Conduct a thorough research about {topic} Make sure you find any interesting and relevant information given the current year is 2025. expected\_output: \> A list with 10 bullet points of the most relevant information about {topic} agent: researcher reporting\_task: description: \> Review the context you got and expand each topic into a full section for a report. Make sure the report is detailed and contains any and all relevant information. expected\_output: \> A fully fledge reports with the mains topics, each with a full section of information. Formatted as markdown without '\\\`' agent: reporting\_analyst output\_file: report.md crew.py \# src/my\_project/crew.py from crewai import Agent, Crew, Process, Task from crewai.project import CrewBase, agent, crew, task from crewai\_tools import SerperDevTool from crewai.agents.agent\_builder.base\_agent import BaseAgent from typing import List @CrewBase class LatestAiDevelopmentCrew(): """LatestAiDevelopment crew""" agents: List\[BaseAgent\] tasks: List\[Task\] @agent def researcher(self) \-> Agent: return Agent( config\=self.agents\_config\['researcher'\], verbose\=True, tools\=\[SerperDevTool()\] ) @agent def reporting\_analyst(self) \-> Agent: return Agent( config\=self.agents\_config\['reporting\_analyst'\], verbose\=True ) @task def research\_task(self) \-> Task: return Task( config\=self.tasks\_config\['research\_task'\], ) @task def reporting\_task(self) \-> Task: return Task( config\=self.tasks\_config\['reporting\_task'\], output\_file\='report.md' ) @crew def crew(self) \-> Crew: """Creates the LatestAiDevelopment crew""" return Crew( agents\=self.agents, \# Automatically created by the @agent decorator tasks\=self.tasks, \# Automatically created by the @task decorator process\=Process.sequential, verbose\=True, ) main.py

!/usr/bin/env python

\# src/my\_project/main.py import sys from latest\_ai\_development.crew import LatestAiDevelopmentCrew def run(): """ Run the crew. """ inputs \= { 'topic': 'AI Agents' } LatestAiDevelopmentCrew().crew().kickoff(inputs\=inputs)

3\. Running Your Crew

#3-running-your-crew Before running your crew, make sure you have the following keys set as environment variables in your .env file:

Lock the dependencies and install them by using the CLI command but first, navigate to your project directory: cd my\_project crewai install (Optional) To run your crew, execute the following command in the root of your project: crewai run or python src/my\_project/main.py If an error happens due to the usage of poetry, please run the following command to update your crewai package: crewai update You should see the output in the console and the report.md file should be created in the root of your project with the full final report. In addition to the sequential process, you can use the hierarchical process, which automatically assigns a manager to the defined crew to properly coordinate the planning and execution of tasks through delegation and validation of results. See more about the processes here.

• An OpenAI API key (or other LLM API key): OPENAI_API_KEY=sk-...
• A Serper.dev API key: SERPER_API_KEY=YOUR_KEY_HERE

Key Features

#key-features CrewAI stands apart as a lean, standalone, high-performance multi-AI Agent framework delivering simplicity, flexibility, and precise control—free from the complexity and limitations found in other agent frameworks.

Choose CrewAI to easily build powerful, adaptable, and production-ready AI automations.

• Standalone & Lean: Completely independent from other frameworks like LangChain, offering faster execution and lighter resource demands.
• Flexible & Precise: Easily orchestrate autonomous agents through intuitive Crews or precise Flows, achieving perfect balance for your needs.
• Seamless Integration: Effortlessly combine Crews (autonomy) and Flows (precision) to create complex, real-world automations.
• Deep Customization: Tailor every aspect—from high-level workflows down to low-level internal prompts and agent behaviors.
• Reliable Performance: Consistent results across simple tasks and complex, enterprise-level automations.
• Thriving Community: Backed by robust documentation and over 100,000 certified developers, providing exceptional support and guidance.

Examples

#examples You can test different real life examples of AI crews in the CrewAI-examples repo:

• Landing Page Generator
• Having Human input on the execution
• Trip Planner
• Stock Analysis

Quick Tutorial

#quick-tutorial https://www.youtube.com/watch?v=tnejrr-0a94 "CrewAI Tutorial"

Write Job Descriptions

#write-job-descriptions Check out code for this example or watch a video below: https://www.youtube.com/watch?v=u98wEMz-9to "Jobs postings"

Trip Planner

#trip-planner Check out code for this example or watch a video below: https://www.youtube.com/watch?v=xis7rWp-hjs "Trip Planner"

Stock Analysis

#stock-analysis Check out code for this example or watch a video below: https://www.youtube.com/watch?v=e0Uj4yWdaAg "Stock Analysis"

Using Crews and Flows Together

#using-crews-and-flows-together CrewAI's power truly shines when combining Crews with Flows to create sophisticated automation pipelines. CrewAI flows support logical operators like or_ and and_ to combine multiple conditions. This can be used with @start, @listen, or @router decorators to create complex triggering conditions.

Here's how you can orchestrate multiple Crews within a Flow: from crewai.flow.flow import Flow, listen, start, router, or\_ from crewai import Crew, Agent, Task, Process from pydantic import BaseModel \# Define structured state for precise control class MarketState(BaseModel): sentiment: str \= "neutral" confidence: float \= 0.0 recommendations: list \= \[\] class AdvancedAnalysisFlow(Flow\[MarketState\]): @start() def fetch\_market\_data(self): \# Demonstrate low-level control with structured state self.state.sentiment \= "analyzing" return {"sector": "tech", "timeframe": "1W"} \# These parameters match the task description template @listen(fetch\_market\_data) def analyze\_with\_crew(self, market\_data): \# Show crew agency through specialized roles analyst \= Agent( role\="Senior Market Analyst", goal\="Conduct deep market analysis with expert insight", backstory\="You're a veteran analyst known for identifying subtle market patterns" ) researcher \= Agent( role\="Data Researcher", goal\="Gather and validate supporting market data", backstory\="You excel at finding and correlating multiple data sources" ) analysis\_task \= Task( description\="Analyze {sector} sector data for the past {timeframe}", expected\_output\="Detailed market analysis with confidence score", agent\=analyst ) research\_task \= Task( description\="Find supporting data to validate the analysis", expected\_output\="Corroborating evidence and potential contradictions", agent\=researcher ) \# Demonstrate crew autonomy analysis\_crew \= Crew( agents\=\[analyst, researcher\], tasks\=\[analysis\_task, research\_task\], process\=Process.sequential, verbose\=True ) return analysis\_crew.kickoff(inputs\=market\_data) \# Pass market\_data as named inputs @router(analyze\_with\_crew) def determine\_next\_steps(self): \# Show flow control with conditional routing if self.state.confidence \> 0.8: return "high\_confidence" elif self.state.confidence \> 0.5: return "medium\_confidence" return "low\_confidence" @listen("high\_confidence") def execute\_strategy(self): \# Demonstrate complex decision making strategy\_crew \= Crew( agents\=\[ Agent(role\="Strategy Expert", goal\="Develop optimal market strategy") \], tasks\=\[ Task(description\="Create detailed strategy based on analysis", expected\_output\="Step-by-step action plan") \] ) return strategy\_crew.kickoff() @listen(or\_("medium\_confidence", "low\_confidence")) def request\_additional\_analysis(self): self.state.recommendations.append("Gather more data") return "Additional analysis required" This example demonstrates how to: 1. Use Python code for basic data operations 2. Create and execute Crews as steps in your workflow 3. Use Flow decorators to manage the sequence of operations 4. Implement conditional branching based on Crew results

• or_: Triggers when any of the specified conditions are met.
• and_Triggers when all of the specified conditions are met.

Connecting Your Crew to a Model

#connecting-your-crew-to-a-model CrewAI supports using various LLMs through a variety of connection options. By default your agents will use the OpenAI API when querying the model. However, there are several other ways to allow your agents to connect to models. For example, you can configure your agents to use a local model via the Ollama tool. Please refer to the Connect CrewAI to LLMs page for details on configuring your agents' connections to models.

How CrewAI Compares

#how-crewai-compares CrewAI's Advantage: CrewAI combines autonomous agent intelligence with precise workflow control through its unique Crews and Flows architecture. The framework excels at both high-level orchestration and low-level customization, enabling complex, production-grade systems with granular control.

_P.S. CrewAI demonstrates significant performance advantages over LangGraph, executing 5.76x faster in certain cases like this QA task example (see comparison) while achieving higher evaluation scores with faster completion times in certain coding tasks, like in this example (detailed analysis)._

• LangGraph: While LangGraph provides a foundation for building agent workflows, its approach requires significant boilerplate code and complex state management patterns. The framework's tight coupling with LangChain can limit flexibility when implementing custom agent behaviors or integrating with external systems.
• Autogen: While Autogen excels at creating conversational agents capable of working together, it lacks an inherent concept of process. In Autogen, orchestrating agents' interactions requires additional programming, which can become complex and cumbersome as the scale of tasks grows.
• ChatDev: ChatDev introduced the idea of processes into the realm of AI agents, but its implementation is quite rigid. Customizations in ChatDev are limited and not geared towards production environments, which can hinder scalability and flexibility in real-world applications.

Contribution

#contribution CrewAI is open-source and we welcome contributions. If you're looking to contribute, please:

• Fork the repository.
• Create a new branch for your feature.
• Add your feature or improvement.
• Send a pull request.
• We appreciate your input!

Installing Dependencies

#installing-dependencies uv lock uv sync

Virtual Env

#virtual-env uv venv

Pre-commit hooks

#pre-commit-hooks pre-commit install

Running Tests

#running-tests uv run pytest .

Running static type checks

#running-static-type-checks uvx mypy src

Packaging

#packaging uv build

Installing Locally

#installing-locally uv pip install dist/\*.tar.gz

Telemetry

#telemetry CrewAI uses anonymous telemetry to collect usage data with the main purpose of helping us improve the library by focusing our efforts on the most used features, integrations and tools. It's pivotal to understand that NO data is collected concerning prompts, task descriptions, agents' backstories or goals, usage of tools, API calls, responses, any data processed by the agents, or secrets and environment variables, with the exception of the conditions mentioned. When the share_crew feature is enabled, detailed data including task descriptions, agents' backstories or goals, and other specific attributes are collected to provide deeper insights while respecting user privacy. Users can disable telemetry by setting the environment variable OTEL\_SDK\_DISABLED to true. Data collected includes:

Users can opt-in to Further Telemetry, sharing the complete telemetry data by setting the share_crew attribute to True on their Crews. Enabling share_crew results in the collection of detailed crew and task execution data, including goal, backstory, context, and output of tasks. This enables a deeper insight into usage patterns while respecting the user's choice to share.

• Version of CrewAI
• So we can understand how many users are using the latest version
• Version of Python
• So we can decide on what versions to better support
• General OS (e.g. number of CPUs, macOS/Windows/Linux)
• So we know what OS we should focus on and if we could build specific OS related features
• Number of agents and tasks in a crew
• So we make sure we are testing internally with similar use cases and educate people on the best practices
• Crew Process being used
• Understand where we should focus our efforts
• If Agents are using memory or allowing delegation
• Understand if we improved the features or maybe even drop them
• If Tasks are being executed in parallel or sequentially
• Understand if we should focus more on parallel execution
• Language model being used
• Improved support on most used languages
• Roles of agents in a crew
• Understand high level use cases so we can build better tools, integrations and examples about it
• Tools names available
• Understand out of the publicly available tools, which ones are being used the most so we can improve them

License

#license CrewAI is released under the MIT License.

Frequently Asked Questions (FAQ)

#frequently-asked-questions-faq

General

#general

• What exactly is CrewAI?
• How do I install CrewAI?
• Does CrewAI depend on LangChain?
• Is CrewAI open-source?
• Does CrewAI collect data from users?

Features and Capabilities

#features-and-capabilities

• Can CrewAI handle complex use cases?
• Can I use CrewAI with local AI models?
• What makes Crews different from Flows?
• How is CrewAI better than LangChain?
• Does CrewAI support fine-tuning or training custom models?

Resources and Community

#resources-and-community

• Where can I find real-world CrewAI examples?
• How can I contribute to CrewAI?

Enterprise Features

#enterprise-features

• What additional features does CrewAI AMP offer?
• Is CrewAI AMP available for cloud and on-premise deployments?
• Can I try CrewAI AMP for free?

Q: What exactly is CrewAI?

#q-what-exactly-is-crewai A: CrewAI is a standalone, lean, and fast Python framework built specifically for orchestrating autonomous AI agents. Unlike frameworks like LangChain, CrewAI does not rely on external dependencies, making it leaner, faster, and simpler.

Q: How do I install CrewAI?

#q-how-do-i-install-crewai A: Install CrewAI using pip: uv pip install crewai For additional tools, use: uv pip install 'crewai\[tools\]'

Q: Does CrewAI depend on LangChain?

#q-does-crewai-depend-on-langchain A: No. CrewAI is built entirely from the ground up, with no dependencies on LangChain or other agent frameworks. This ensures a lean, fast, and flexible experience.

Q: Can CrewAI handle complex use cases?

#q-can-crewai-handle-complex-use-cases A: Yes. CrewAI excels at both simple and highly complex real-world scenarios, offering deep customization options at both high and low levels, from internal prompts to sophisticated workflow orchestration.

Q: Can I use CrewAI with local AI models?

#q-can-i-use-crewai-with-local-ai-models A: Absolutely! CrewAI supports various language models, including local ones. Tools like Ollama and LM Studio allow seamless integration. Check the LLM Connections documentation for more details.

Q: What makes Crews different from Flows?

#q-what-makes-crews-different-from-flows A: Crews provide autonomous agent collaboration, ideal for tasks requiring flexible decision-making and dynamic interaction. Flows offer precise, event-driven control, ideal for managing detailed execution paths and secure state management. You can seamlessly combine both for maximum effectiveness.

Q: How is CrewAI better than LangChain?

#q-how-is-crewai-better-than-langchain A: CrewAI provides simpler, more intuitive APIs, faster execution speeds, more reliable and consistent results, robust documentation, and an active community—addressing common criticisms and limitations associated with LangChain.

Q: Is CrewAI open-source?

#q-is-crewai-open-source A: Yes, CrewAI is open-source and actively encourages community contributions and collaboration.

Q: Does CrewAI collect data from users?

#q-does-crewai-collect-data-from-users A: CrewAI collects anonymous telemetry data strictly for improvement purposes. Sensitive data such as prompts, tasks, or API responses are never collected unless explicitly enabled by the user.

Q: Where can I find real-world CrewAI examples?

#q-where-can-i-find-real-world-crewai-examples A: Check out practical examples in the CrewAI-examples repository, covering use cases like trip planners, stock analysis, and job postings.

Q: How can I contribute to CrewAI?

#q-how-can-i-contribute-to-crewai A: Contributions are warmly welcomed! Fork the repository, create your branch, implement your changes, and submit a pull request. See the Contribution section of the README for detailed guidelines.

Q: What additional features does CrewAI AMP offer?

#q-what-additional-features-does-crewai-amp-offer A: CrewAI AMP provides advanced features such as a unified control plane, real-time observability, secure integrations, advanced security, actionable insights, and dedicated 24/7 enterprise support.

Q: Is CrewAI AMP available for cloud and on-premise deployments?

#q-is-crewai-amp-available-for-cloud-and-on-premise-deployments A: Yes, CrewAI AMP supports both cloud-based and on-premise deployment options, allowing enterprises to meet their specific security and compliance requirements.

Q: Can I try CrewAI AMP for free?

#q-can-i-try-crewai-amp-for-free A: Yes, you can explore part of the CrewAI AMP Suite by accessing the Crew Control Plane for free.

Q: Does CrewAI support fine-tuning or training custom models?

#q-does-crewai-support-fine-tuning-or-training-custom-models A: Yes, CrewAI can integrate with custom-trained or fine-tuned models, allowing you to enhance your agents with domain-specific knowledge and accuracy.

Q: Can CrewAI agents interact with external tools and APIs?

#q-can-crewai-agents-interact-with-external-tools-and-apis A: Absolutely! CrewAI agents can easily integrate with external tools, APIs, and databases, empowering them to leverage real-world data and resources.

Q: Is CrewAI suitable for production environments?

#q-is-crewai-suitable-for-production-environments A: Yes, CrewAI is explicitly designed with production-grade standards, ensuring reliability, stability, and scalability for enterprise deployments.

Q: How scalable is CrewAI?

#q-how-scalable-is-crewai A: CrewAI is highly scalable, supporting simple automations and large-scale enterprise workflows involving numerous agents and complex tasks simultaneously.

Q: Does CrewAI offer debugging and monitoring tools?

#q-does-crewai-offer-debugging-and-monitoring-tools A: Yes, CrewAI AMP includes advanced debugging, tracing, and real-time observability features, simplifying the management and troubleshooting of your automations.

Q: What programming languages does CrewAI support?

#q-what-programming-languages-does-crewai-support A: CrewAI is primarily Python-based but easily integrates with services and APIs written in any programming language through its flexible API integration capabilities.

Q: Does CrewAI offer educational resources for beginners?

#q-does-crewai-offer-educational-resources-for-beginners A: Yes, CrewAI provides extensive beginner-friendly tutorials, courses, and documentation through learn.crewai.com, supporting developers at all skill levels.

Q: Can CrewAI automate human-in-the-loop workflows?

#q-can-crewai-automate-human-in-the-loop-workflows A: Yes, CrewAI fully supports human-in-the-loop workflows, allowing seamless collaboration between human experts and AI agents for enhanced decision-making.

中文翻译

中文翻译

crewAIInc/crewAI: Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

中文翻译

原文链接: https://github.com/crewAIInc/crewAI

中文翻译

https://github.com/crewAIInc/crewAI

中文翻译

https://trendshift.io/repositories/11239

中文翻译

Homepage · Docs · Start Cloud Trial · Blog · Forum

中文翻译

https://github.com/crewAIInc/crewAIhttps://github.com/crewAIInc/crewAI/network/membershttps://github.com/crewAIInc/crewAI/issueshttps://github.com/crewAIInc/crewAI/pullshttps://opensource.org/licenses/MIT

中文翻译

https://pypi.org/project/crewai/https://pypi.org/project/crewai/https://twitter.com/crewAIInc

中文翻译

Fast and Flexible Multi-Agent Automation Framework

中文翻译

#fast-and-flexible-multi-agent-automation-framework

中文翻译

CrewAI is a lean, lightning-fast Python framework built entirely from scratch—completely independent of LangChain or other agent frameworks. It empowers developers with both high-level simplicity and precise low-level control, ideal for creating autonomous AI agents tailored to any scenario.

中文翻译

• CrewAI Crews: Optimize for autonomy and collaborative intelligence.
• CrewAI Flows: The enterprise and production architecture for building and deploying multi-agent systems. Enable granular, event-driven control, single LLM calls for precise task orchestration and supports Crews natively

中文翻译

With over 100,000 developers certified through our community courses at learn.crewai.com, CrewAI is rapidly becoming the standard for enterprise-ready AI automation.

中文翻译

CrewAI AMP Suite

中文翻译

#crewai-amp-suite

中文翻译

CrewAI AMP Suite is a comprehensive bundle tailored for organizations that require secure, scalable, and easy-to-manage agent-driven automation.

中文翻译

You can try one part of the suite the Crew Control Plane for free

中文翻译

Crew Control Plane Key Features:

中文翻译

#crew-control-plane-key-features

中文翻译

• Tracing & Observability: Monitor and track your AI agents and workflows in real-time, including metrics, logs, and traces.
• Unified Control Plane: A centralized platform for managing, monitoring, and scaling your AI agents and workflows.
• Seamless Integrations: Easily connect with existing enterprise systems, data sources, and cloud infrastructure.
• Advanced Security: Built-in robust security and compliance measures ensuring safe deployment and management.
• Actionable Insights: Real-time analytics and reporting to optimize performance and decision-making.
• 24/7 Support: Dedicated enterprise support to ensure uninterrupted operation and quick resolution of issues.
• On-premise and Cloud Deployment Options: Deploy CrewAI AMP on-premise or in the cloud, depending on your security and compliance requirements.

中文翻译

CrewAI AMP is designed for enterprises seeking a powerful, reliable solution to transform complex business processes into efficient, intelligent automations.

中文翻译

Table of contents

中文翻译

#table-of-contents

中文翻译

• Build with AI
• Why CrewAI?
• Getting Started
• Key Features
• Understanding Flows and Crews
• CrewAI vs LangGraph
• Examples
• Quick Tutorial
• Write Job Descriptions
• Trip Planner
• Stock Analysis
• Using Crews and Flows Together
• Connecting Your Crew to a Model
• How CrewAI Compares
• Frequently Asked Questions (FAQ)
• Contribution
• Telemetry
• License

中文翻译

Build with AI

中文翻译

#build-with-ai

中文翻译

Using an AI coding agent? Teach it CrewAI best practices in one command:

中文翻译

Claude Code:

中文翻译

/plugin marketplace add crewAIInc/skills /plugin install crewai-skills@crewai-plugins /reload-plugins

中文翻译

Four skills that activate automatically when you ask relevant CrewAI questions:

中文翻译

Skill

中文翻译

When it runs

中文翻译

getting-started

中文翻译

Scaffolding new projects, choosing between LLM.call() / Agent / Crew / Flow, wiring crew.py / main.py

中文翻译

design-agent

中文翻译

Configuring agents — role, goal, backstory, tools, LLMs, memory, guardrails

中文翻译

design-task

中文翻译

Writing task descriptions, dependencies, structured output (output_pydantic, output_json), human review

中文翻译

ask-docs

中文翻译

Querying the live CrewAI docs MCP server for up-to-date API details

中文翻译

Cursor, Codex, Windsurf, and others (skills.sh):

中文翻译

npx skills add crewaiinc/skills

中文翻译

This installs the official CrewAI Skills — structured instructions that teach coding agents how to scaffold Flows, configure Crews, design agents and tasks, and follow CrewAI patterns.

中文翻译

Why CrewAI?

中文翻译

#why-crewai

中文翻译

/crewAIInc/crewAI/blob/main/docs/images/asset.png

中文翻译

CrewAI unlocks the true potential of multi-agent automation, delivering the best-in-class combination of speed, flexibility, and control with either Crews of AI Agents or Flows of Events:

中文翻译

• Standalone Framework: Built from scratch, independent of LangChain or any other agent framework.
• High Performance: Optimized for speed and minimal resource usage, enabling faster execution.
• Flexible Low Level Customization: Complete freedom to customize at both high and low levels - from overall workflows and system architecture to granular agent behaviors, internal prompts, and execution logic.
• Ideal for Every Use Case: Proven effective for both simple tasks and highly complex, real-world, enterprise-grade scenarios.
• Robust Community: Backed by a rapidly growing community of over 100,000 certified developers offering comprehensive support and resources.

中文翻译

CrewAI empowers developers and enterprises to confidently build intelligent automations, bridging the gap between simplicity, flexibility, and performance.

中文翻译

Getting Started

中文翻译

#getting-started

中文翻译

Setup and run your first CrewAI agents by following this tutorial.

中文翻译

https://www.youtube.com/watch?v=-kSOTtYzgEw "CrewAI Getting Started Tutorial"

中文翻译

Learning Resources

中文翻译

Learn CrewAI through our comprehensive courses:

中文翻译

• Multi AI Agent Systems with CrewAI - Master the fundamentals of multi-agent systems
• Practical Multi AI Agents and Advanced Use Cases - Deep dive into advanced implementations

中文翻译

Understanding Flows and Crews

中文翻译

#understanding-flows-and-crews

中文翻译

CrewAI offers two powerful, complementary approaches that work seamlessly together to build sophisticated AI applications:

中文翻译

1. Crews: Teams of AI agents with true autonomy and agency, working together to accomplish complex tasks through role-based collaboration. Crews enable:

中文翻译

2. Flows: Production-ready, event-driven workflows that deliver precise control over complex automations. Flows provide:

• Natural, autonomous decision-making between agents
• Dynamic task delegation and collaboration
• Specialized roles with defined goals and expertise
• Flexible problem-solving approaches

中文翻译

• Fine-grained control over execution paths for real-world scenarios
• Secure, consistent state management between tasks
• Clean integration of AI agents with production Python code
• Conditional branching for complex business logic

中文翻译

The true power of CrewAI emerges when combining Crews and Flows. This synergy allows you to:

中文翻译

• Build complex, production-grade applications
• Balance autonomy with precise control
• Handle sophisticated real-world scenarios
• Maintain clean, maintainable code structure

中文翻译

Getting Started with Installation

中文翻译

#getting-started-with-installation

中文翻译

To get started with CrewAI, follow these simple steps:

中文翻译

1\. Installation

中文翻译

#1-installation

中文翻译

Ensure you have Python >=3.10 <3.14 installed on your system. CrewAI uses UV for dependency management and package handling, offering a seamless setup and execution experience.

中文翻译

First, install CrewAI:

中文翻译

uv pip install crewai

中文翻译

If you want to install the 'crewai' package along with its optional features that include additional tools for agents, you can do so by using the following command:

中文翻译

uv pip install 'crewai\[tools\]'

中文翻译

The command above installs the basic package and also adds extra components which require more dependencies to function.

中文翻译

Troubleshooting Dependencies

中文翻译

#troubleshooting-dependencies

中文翻译

If you encounter issues during installation or usage, here are some common solutions:

中文翻译

Common Issues

中文翻译

#common-issues

中文翻译

1. ModuleNotFoundError: No module named 'tiktoken'

中文翻译

2. Failed building wheel for tiktoken

• Install tiktoken explicitly: uv pip install 'crewai[embeddings]'
• If using embedchain or other tools: uv pip install 'crewai[tools]'

中文翻译

• Ensure Rust compiler is installed (see installation steps above)
• For Windows: Verify Visual C++ Build Tools are installed
• Try upgrading pip: uv pip install --upgrade pip
• If issues persist, use a pre-built wheel: uv pip install tiktoken --prefer-binary

中文翻译

2\. Setting Up Your Crew with the YAML Configuration

中文翻译

#2-setting-up-your-crew-with-the-yaml-configuration

中文翻译

To create a new CrewAI project, run the following CLI (Command Line Interface) command:

中文翻译

crewai create crew <project\_name\>

中文翻译

This command creates a new project folder with the following structure:

中文翻译

my_project/
├── .gitignore
├── pyproject.toml
├── README.md
├── .env
└── src/
    └── my_project/
        ├── __init__.py
        ├── main.py
        ├── crew.py
        ├── tools/
        │   ├── custom_tool.py
        │   └── __init__.py
        └── config/
            ├── agents.yaml
            └── tasks.yaml

中文翻译

You can now start developing your crew by editing the files in the src/my_project folder. The main.py file is the entry point of the project, the crew.py file is where you define your crew, the agents.yaml file is where you define your agents, and the tasks.yaml file is where you define your tasks.

中文翻译

To customize your project, you can:

中文翻译

#to-customize-your-project-you-can

中文翻译

• Modify src/my_project/config/agents.yaml to define your agents.
• Modify src/my_project/config/tasks.yaml to define your tasks.
• Modify src/my_project/crew.py to add your own logic, tools, and specific arguments.
• Modify src/my_project/main.py to add custom inputs for your agents and tasks.
• Add your environment variables into the .env file.

中文翻译

Example of a simple crew with a sequential process:

中文翻译

#example-of-a-simple-crew-with-a-sequential-process

中文翻译

Instantiate your crew:

中文翻译

crewai create crew latest-ai-development

中文翻译

Modify the files as needed to fit your use case:

中文翻译

agents.yaml

中文翻译

src/my\_project/config/agents.yaml

researcher: role: \> {topic} Senior Data Researcher goal: \> Uncover cutting-edge developments in {topic} backstory: \> You're a seasoned researcher with a knack for uncovering the latest developments in {topic}. Known for your ability to find the most relevant information and present it in a clear and concise manner. reporting\_analyst: role: \> {topic} Reporting Analyst goal: \> Create detailed reports based on {topic} data analysis and research findings backstory: \> You're a meticulous analyst with a keen eye for detail. You're known for your ability to turn complex data into clear and concise reports, making it easy for others to understand and act on the information you provide.

中文翻译

tasks.yaml

中文翻译

src/my\_project/config/tasks.yaml

research\_task: description: \> Conduct a thorough research about {topic} Make sure you find any interesting and relevant information given the current year is 2025. expected\_output: \> A list with 10 bullet points of the most relevant information about {topic} agent: researcher

中文翻译

reporting\_task: description: \> Review the context you got and expand each topic into a full section for a report. Make sure the report is detailed and contains any and all relevant information. expected\_output: \> A fully fledge reports with the mains topics, each with a full section of information. Formatted as markdown without '\\\`' agent: reporting\_analyst output\_file: report.md

中文翻译

crew.py

中文翻译

\# src/my\_project/crew.py from crewai import Agent, Crew, Process, Task from crewai.project import CrewBase, agent, crew, task from crewai\_tools import SerperDevTool from crewai.agents.agent\_builder.base\_agent import BaseAgent from typing import List

中文翻译

@CrewBase class LatestAiDevelopmentCrew(): """LatestAiDevelopment crew""" agents: List\[BaseAgent\] tasks: List\[Task\]

中文翻译

@agent def researcher(self) \-> Agent: return Agent( config\=self.agents\_config\['researcher'\], verbose\=True, tools\=\[SerperDevTool()\] )

中文翻译

@agent def reporting\_analyst(self) \-> Agent: return Agent( config\=self.agents\_config\['reporting\_analyst'\], verbose\=True )

中文翻译

@task def research\_task(self) \-> Task: return Task( config\=self.tasks\_config\['research\_task'\], )

中文翻译

@task def reporting\_task(self) \-> Task: return Task( config\=self.tasks\_config\['reporting\_task'\], output\_file\='report.md' )

中文翻译

@crew def crew(self) \-> Crew: """Creates the LatestAiDevelopment crew""" return Crew( agents\=self.agents, \# Automatically created by the @agent decorator tasks\=self.tasks, \# Automatically created by the @task decorator process\=Process.sequential, verbose\=True, )

中文翻译

main.py

中文翻译

!/usr/bin/env python

\# src/my\_project/main.py import sys from latest\_ai\_development.crew import LatestAiDevelopmentCrew

中文翻译

def run(): """ Run the crew. """ inputs \= { 'topic': 'AI Agents' } LatestAiDevelopmentCrew().crew().kickoff(inputs\=inputs)

中文翻译

3\. Running Your Crew

中文翻译

#3-running-your-crew

中文翻译

Before running your crew, make sure you have the following keys set as environment variables in your .env file:

中文翻译

• An OpenAI API key (or other LLM API key): OPENAI_API_KEY=sk-...
• A Serper.dev API key: SERPER_API_KEY=YOUR_KEY_HERE

中文翻译

Lock the dependencies and install them by using the CLI command but first, navigate to your project directory:

中文翻译

cd my\_project crewai install (Optional)

中文翻译

To run your crew, execute the following command in the root of your project:

中文翻译

crewai run

中文翻译

or

中文翻译

python src/my\_project/main.py

中文翻译

If an error happens due to the usage of poetry, please run the following command to update your crewai package:

中文翻译

crewai update

中文翻译

You should see the output in the console and the report.md file should be created in the root of your project with the full final report.

中文翻译

In addition to the sequential process, you can use the hierarchical process, which automatically assigns a manager to the defined crew to properly coordinate the planning and execution of tasks through delegation and validation of results. See more about the processes here.

中文翻译

Key Features

中文翻译

#key-features

中文翻译

CrewAI stands apart as a lean, standalone, high-performance multi-AI Agent framework delivering simplicity, flexibility, and precise control—free from the complexity and limitations found in other agent frameworks.

中文翻译

• Standalone & Lean: Completely independent from other frameworks like LangChain, offering faster execution and lighter resource demands.
• Flexible & Precise: Easily orchestrate autonomous agents through intuitive Crews or precise Flows, achieving perfect balance for your needs.
• Seamless Integration: Effortlessly combine Crews (autonomy) and Flows (precision) to create complex, real-world automations.
• Deep Customization: Tailor every aspect—from high-level workflows down to low-level internal prompts and agent behaviors.
• Reliable Performance: Consistent results across simple tasks and complex, enterprise-level automations.
• Thriving Community: Backed by robust documentation and over 100,000 certified developers, providing exceptional support and guidance.

中文翻译

Choose CrewAI to easily build powerful, adaptable, and production-ready AI automations.

中文翻译

Examples

中文翻译

#examples

中文翻译

You can test different real life examples of AI crews in the CrewAI-examples repo:

中文翻译

• Landing Page Generator
• Having Human input on the execution
• Trip Planner
• Stock Analysis

中文翻译

Quick Tutorial

中文翻译

#quick-tutorial

中文翻译

https://www.youtube.com/watch?v=tnejrr-0a94 "CrewAI Tutorial"

中文翻译

Write Job Descriptions

中文翻译

#write-job-descriptions

中文翻译

Check out code for this example or watch a video below:

中文翻译

https://www.youtube.com/watch?v=u98wEMz-9to "Jobs postings"

中文翻译

Trip Planner

中文翻译

#trip-planner

中文翻译

Check out code for this example or watch a video below:

中文翻译

https://www.youtube.com/watch?v=xis7rWp-hjs "Trip Planner"

中文翻译

Stock Analysis

中文翻译

#stock-analysis

中文翻译

Check out code for this example or watch a video below:

中文翻译

https://www.youtube.com/watch?v=e0Uj4yWdaAg "Stock Analysis"

中文翻译

Using Crews and Flows Together

中文翻译

#using-crews-and-flows-together

中文翻译

CrewAI's power truly shines when combining Crews with Flows to create sophisticated automation pipelines. CrewAI flows support logical operators like or_ and and_ to combine multiple conditions. This can be used with @start, @listen, or @router decorators to create complex triggering conditions.

中文翻译

• or_: Triggers when any of the specified conditions are met.
• and_Triggers when all of the specified conditions are met.

中文翻译

Here's how you can orchestrate multiple Crews within a Flow:

中文翻译

from crewai.flow.flow import Flow, listen, start, router, or\_ from crewai import Crew, Agent, Task, Process from pydantic import BaseModel

中文翻译

\# Define structured state for precise control class MarketState(BaseModel): sentiment: str \= "neutral" confidence: float \= 0.0 recommendations: list \= \[\]

中文翻译

class AdvancedAnalysisFlow(Flow\[MarketState\]): @start() def fetch\_market\_data(self): \# Demonstrate low-level control with structured state self.state.sentiment \= "analyzing" return {"sector": "tech", "timeframe": "1W"} \# These parameters match the task description template

中文翻译

@listen(fetch\_market\_data) def analyze\_with\_crew(self, market\_data): \# Show crew agency through specialized roles analyst \= Agent( role\="Senior Market Analyst", goal\="Conduct deep market analysis with expert insight", backstory\="You're a veteran analyst known for identifying subtle market patterns" ) researcher \= Agent( role\="Data Researcher", goal\="Gather and validate supporting market data", backstory\="You excel at finding and correlating multiple data sources" )

中文翻译

analysis\_task \= Task( description\="Analyze {sector} sector data for the past {timeframe}", expected\_output\="Detailed market analysis with confidence score", agent\=analyst ) research\_task \= Task( description\="Find supporting data to validate the analysis", expected\_output\="Corroborating evidence and potential contradictions", agent\=researcher )

中文翻译

\# Demonstrate crew autonomy analysis\_crew \= Crew( agents\=\[analyst, researcher\], tasks\=\[analysis\_task, research\_task\], process\=Process.sequential, verbose\=True ) return analysis\_crew.kickoff(inputs\=market\_data) \# Pass market\_data as named inputs

中文翻译

@router(analyze\_with\_crew) def determine\_next\_steps(self): \# Show flow control with conditional routing if self.state.confidence \> 0.8: return "high\_confidence" elif self.state.confidence \> 0.5: return "medium\_confidence" return "low\_confidence"

中文翻译

@listen("high\_confidence") def execute\_strategy(self): \# Demonstrate complex decision making strategy\_crew \= Crew( agents\=\[ Agent(role\="Strategy Expert", goal\="Develop optimal market strategy") \], tasks\=\[ Task(description\="Create detailed strategy based on analysis", expected\_output\="Step-by-step action plan") \] ) return strategy\_crew.kickoff()

中文翻译

@listen(or\_("medium\_confidence", "low\_confidence")) def request\_additional\_analysis(self): self.state.recommendations.append("Gather more data") return "Additional analysis required"

中文翻译

This example demonstrates how to:

中文翻译

1. Use Python code for basic data operations 2. Create and execute Crews as steps in your workflow 3. Use Flow decorators to manage the sequence of operations 4. Implement conditional branching based on Crew results

中文翻译

Connecting Your Crew to a Model

中文翻译

#connecting-your-crew-to-a-model

中文翻译

CrewAI supports using various LLMs through a variety of connection options. By default your agents will use the OpenAI API when querying the model. However, there are several other ways to allow your agents to connect to models. For example, you can configure your agents to use a local model via the Ollama tool.

中文翻译

Please refer to the Connect CrewAI to LLMs page for details on configuring your agents' connections to models.

中文翻译

How CrewAI Compares

中文翻译

#how-crewai-compares

中文翻译

CrewAI's Advantage: CrewAI combines autonomous agent intelligence with precise workflow control through its unique Crews and Flows architecture. The framework excels at both high-level orchestration and low-level customization, enabling complex, production-grade systems with granular control.

中文翻译

• LangGraph: While LangGraph provides a foundation for building agent workflows, its approach requires significant boilerplate code and complex state management patterns. The framework's tight coupling with LangChain can limit flexibility when implementing custom agent behaviors or integrating with external systems.

中文翻译

_P.S. CrewAI demonstrates significant performance advantages over LangGraph, executing 5.76x faster in certain cases like this QA task example (see comparison) while achieving higher evaluation scores with faster completion times in certain coding tasks, like in this example (detailed analysis)._

中文翻译

• Autogen: While Autogen excels at creating conversational agents capable of working together, it lacks an inherent concept of process. In Autogen, orchestrating agents' interactions requires additional programming, which can become complex and cumbersome as the scale of tasks grows.
• ChatDev: ChatDev introduced the idea of processes into the realm of AI agents, but its implementation is quite rigid. Customizations in ChatDev are limited and not geared towards production environments, which can hinder scalability and flexibility in real-world applications.

中文翻译

Contribution

中文翻译

#contribution

中文翻译

CrewAI is open-source and we welcome contributions. If you're looking to contribute, please:

中文翻译

• Fork the repository.
• Create a new branch for your feature.
• Add your feature or improvement.
• Send a pull request.
• We appreciate your input!

中文翻译

Installing Dependencies

中文翻译

#installing-dependencies

中文翻译

uv lock uv sync

中文翻译

Virtual Env

中文翻译

#virtual-env

中文翻译

uv venv

中文翻译

Pre-commit hooks

中文翻译

#pre-commit-hooks

中文翻译

pre-commit install

中文翻译

Running Tests

中文翻译

#running-tests

中文翻译

uv run pytest .

中文翻译

Running static type checks

中文翻译

#running-static-type-checks

中文翻译

uvx mypy src

中文翻译

Packaging

中文翻译

#packaging

中文翻译

uv build

中文翻译

Installing Locally

中文翻译

#installing-locally

中文翻译

uv pip install dist/\*.tar.gz

中文翻译

Telemetry

中文翻译

#telemetry

中文翻译

CrewAI uses anonymous telemetry to collect usage data with the main purpose of helping us improve the library by focusing our efforts on the most used features, integrations and tools.

中文翻译

It's pivotal to understand that NO data is collected concerning prompts, task descriptions, agents' backstories or goals, usage of tools, API calls, responses, any data processed by the agents, or secrets and environment variables, with the exception of the conditions mentioned. When the share_crew feature is enabled, detailed data including task descriptions, agents' backstories or goals, and other specific attributes are collected to provide deeper insights while respecting user privacy. Users can disable telemetry by setting the environment variable OTEL\_SDK\_DISABLED to true.

中文翻译

Data collected includes:

中文翻译

• Version of CrewAI
• So we can understand how many users are using the latest version
• Version of Python
• So we can decide on what versions to better support
• General OS (e.g. number of CPUs, macOS/Windows/Linux)
• So we know what OS we should focus on and if we could build specific OS related features
• Number of agents and tasks in a crew
• So we make sure we are testing internally with similar use cases and educate people on the best practices
• Crew Process being used
• Understand where we should focus our efforts
• If Agents are using memory or allowing delegation
• Understand if we improved the features or maybe even drop them
• If Tasks are being executed in parallel or sequentially
• Understand if we should focus more on parallel execution
• Language model being used
• Improved support on most used languages
• Roles of agents in a crew
• Understand high level use cases so we can build better tools, integrations and examples about it
• Tools names available
• Understand out of the publicly available tools, which ones are being used the most so we can improve them

中文翻译

Users can opt-in to Further Telemetry, sharing the complete telemetry data by setting the share_crew attribute to True on their Crews. Enabling share_crew results in the collection of detailed crew and task execution data, including goal, backstory, context, and output of tasks. This enables a deeper insight into usage patterns while respecting the user's choice to share.

中文翻译

License

中文翻译

#license

中文翻译

CrewAI is released under the MIT License.

中文翻译

Frequently Asked Questions (FAQ)

中文翻译

#frequently-asked-questions-faq

中文翻译

General

中文翻译

#general

中文翻译

• What exactly is CrewAI?
• How do I install CrewAI?
• Does CrewAI depend on LangChain?
• Is CrewAI open-source?
• Does CrewAI collect data from users?

中文翻译

Features and Capabilities

中文翻译

#features-and-capabilities

中文翻译

• Can CrewAI handle complex use cases?
• Can I use CrewAI with local AI models?
• What makes Crews different from Flows?
• How is CrewAI better than LangChain?
• Does CrewAI support fine-tuning or training custom models?

中文翻译

Resources and Community

中文翻译

#resources-and-community

中文翻译

• Where can I find real-world CrewAI examples?
• How can I contribute to CrewAI?

中文翻译

Enterprise Features

中文翻译

#enterprise-features

中文翻译

• What additional features does CrewAI AMP offer?
• Is CrewAI AMP available for cloud and on-premise deployments?
• Can I try CrewAI AMP for free?

中文翻译

Q: What exactly is CrewAI?

中文翻译

#q-what-exactly-is-crewai

中文翻译

A: CrewAI is a standalone, lean, and fast Python framework built specifically for orchestrating autonomous AI agents. Unlike frameworks like LangChain, CrewAI does not rely on external dependencies, making it leaner, faster, and simpler.

中文翻译

Q: How do I install CrewAI?

中文翻译

#q-how-do-i-install-crewai

中文翻译

A: Install CrewAI using pip:

中文翻译

uv pip install crewai

中文翻译

For additional tools, use:

中文翻译

uv pip install 'crewai\[tools\]'

中文翻译

Q: Does CrewAI depend on LangChain?

中文翻译

#q-does-crewai-depend-on-langchain

中文翻译

A: No. CrewAI is built entirely from the ground up, with no dependencies on LangChain or other agent frameworks. This ensures a lean, fast, and flexible experience.

中文翻译

Q: Can CrewAI handle complex use cases?

中文翻译

#q-can-crewai-handle-complex-use-cases

中文翻译

A: Yes. CrewAI excels at both simple and highly complex real-world scenarios, offering deep customization options at both high and low levels, from internal prompts to sophisticated workflow orchestration.

中文翻译

Q: Can I use CrewAI with local AI models?

中文翻译

#q-can-i-use-crewai-with-local-ai-models

中文翻译

A: Absolutely! CrewAI supports various language models, including local ones. Tools like Ollama and LM Studio allow seamless integration. Check the LLM Connections documentation for more details.

中文翻译

Q: What makes Crews different from Flows?

中文翻译

#q-what-makes-crews-different-from-flows

中文翻译

A: Crews provide autonomous agent collaboration, ideal for tasks requiring flexible decision-making and dynamic interaction. Flows offer precise, event-driven control, ideal for managing detailed execution paths and secure state management. You can seamlessly combine both for maximum effectiveness.

中文翻译

Q: How is CrewAI better than LangChain?

中文翻译

#q-how-is-crewai-better-than-langchain

中文翻译

A: CrewAI provides simpler, more intuitive APIs, faster execution speeds, more reliable and consistent results, robust documentation, and an active community—addressing common criticisms and limitations associated with LangChain.

中文翻译

Q: Is CrewAI open-source?

中文翻译

#q-is-crewai-open-source

中文翻译

A: Yes, CrewAI is open-source and actively encourages community contributions and collaboration.

中文翻译

Q: Does CrewAI collect data from users?

中文翻译

#q-does-crewai-collect-data-from-users

中文翻译

A: CrewAI collects anonymous telemetry data strictly for improvement purposes. Sensitive data such as prompts, tasks, or API responses are never collected unless explicitly enabled by the user.

中文翻译

Q: Where can I find real-world CrewAI examples?

中文翻译

#q-where-can-i-find-real-world-crewai-examples

中文翻译

A: Check out practical examples in the CrewAI-examples repository, covering use cases like trip planners, stock analysis, and job postings.

中文翻译

Q: How can I contribute to CrewAI?

中文翻译

#q-how-can-i-contribute-to-crewai

中文翻译

A: Contributions are warmly welcomed! Fork the repository, create your branch, implement your changes, and submit a pull request. See the Contribution section of the README for detailed guidelines.

中文翻译

Q: What additional features does CrewAI AMP offer?

中文翻译

#q-what-additional-features-does-crewai-amp-offer

中文翻译

A: CrewAI AMP provides advanced features such as a unified control plane, real-time observability, secure integrations, advanced security, actionable insights, and dedicated 24/7 enterprise support.

中文翻译

Q: Is CrewAI AMP available for cloud and on-premise deployments?

中文翻译

#q-is-crewai-amp-available-for-cloud-and-on-premise-deployments

中文翻译

A: Yes, CrewAI AMP supports both cloud-based and on-premise deployment options, allowing enterprises to meet their specific security and compliance requirements.

中文翻译

Q: Can I try CrewAI AMP for free?

中文翻译

#q-can-i-try-crewai-amp-for-free

中文翻译

A: Yes, you can explore part of the CrewAI AMP Suite by accessing the Crew Control Plane for free.

中文翻译

Q: Does CrewAI support fine-tuning or training custom models?

中文翻译

#q-does-crewai-support-fine-tuning-or-training-custom-models

中文翻译

A: Yes, CrewAI can integrate with custom-trained or fine-tuned models, allowing you to enhance your agents with domain-specific knowledge and accuracy.

中文翻译

Q: Can CrewAI agents interact with external tools and APIs?

中文翻译

#q-can-crewai-agents-interact-with-external-tools-and-apis

中文翻译

A: Absolutely! CrewAI agents can easily integrate with external tools, APIs, and databases, empowering them to leverage real-world data and resources.

中文翻译

Q: Is CrewAI suitable for production environments?

中文翻译

#q-is-crewai-suitable-for-production-environments

中文翻译

A: Yes, CrewAI is explicitly designed with production-grade standards, ensuring reliability, stability, and scalability for enterprise deployments.

中文翻译

Q: How scalable is CrewAI?

中文翻译

#q-how-scalable-is-crewai

中文翻译

A: CrewAI is highly scalable, supporting simple automations and large-scale enterprise workflows involving numerous agents and complex tasks simultaneously.

中文翻译

Q: Does CrewAI offer debugging and monitoring tools?

中文翻译

#q-does-crewai-offer-debugging-and-monitoring-tools

中文翻译

A: Yes, CrewAI AMP includes advanced debugging, tracing, and real-time observability features, simplifying the management and troubleshooting of your automations.

中文翻译

Q: What programming languages does CrewAI support?

中文翻译

#q-what-programming-languages-does-crewai-support

中文翻译

A: CrewAI is primarily Python-based but easily integrates with services and APIs written in any programming language through its flexible API integration capabilities.

中文翻译

Q: Does CrewAI offer educational resources for beginners?

中文翻译

#q-does-crewai-offer-educational-resources-for-beginners

中文翻译

A: Yes, CrewAI provides extensive beginner-friendly tutorials, courses, and documentation through learn.crewai.com, supporting developers at all skill levels.

中文翻译

Q: Can CrewAI automate human-in-the-loop workflows?

中文翻译

#q-can-crewai-automate-human-in-the-loop-workflows

中文翻译

A: Yes, CrewAI fully supports human-in-the-loop workflows, allowing seamless collaboration between human experts and AI agents for enhanced decision-making.