# CrewAI OSS

## The open source, multi-agent orchestration framework

Empowering developers to orchestrate high-performing AI agents with ease and scale.

[Install CrewAI](https://docs.crewai.com/en/installation)  
[Run quickstart](https://docs.crewai.com/en/quickstart)

.webp)

Loved by AI builders. Trusted by AI leaders.

## Why Open Source

### CrewAI is built in the open to make multi-agent AI accessible to all. With no-code speed and full-code power, it gives developers and teams the freedom to create, orchestrate, and scale agents without barriers. Backed by a growing community, CrewAI sets the standard for transparent, reliable, and enterprise-ready AI.

## You define AI agents and tasks, CrewAI builds and orchestrates them

[Planning](/content/open-source#Planning/index.html)  
[Reasoning](/content/open-source#Reasoning/index.html)  
[Tools](/content/open-source#Tools/index.html)  
[Memory](/content/open-source#Memory/index.html)  
[Knowledge](/content/open-source#Knowledge/index.html)  
[Collaboration](/content/open-source#Collaboration/index.html)

### Planning

Crews of AI agents can take advantage of a specialized planning agent which will create a step-by-step plan for all tasks, and share it with the crew.

### Reasoning

AI agents, with reasoning enabled, will reflect on the current task objective, create and refine a structured plan to execute it and inject the plan into the task description.

### Tools

CrewAI provides AI agents with 100s of open-source tools out of the box to, for example, search the Internet, interact with websites, query vector databases and much more.

### Memory

CrewAI implements a sophisticated memory-management systems that provides AI agents with access to shared short-term, long-term, entity and contextual memory.

### Knowledge

Agentic RAG combines a broad range of knowledge sources, including files, websites and vector databases, with intelligent query rewriting to optimize retrieval.

### Collaboration

CrewAI transforms a set of AI agents into crew of AI agents that collaborate via context sharing and delegation to perform complex tasks.

## Build a crew of AI agents with abstraction

### Define AI agents

Simply describe an AI agent’s role, goal and backstory to get started. Optionally, you can specify its LLM, enable reasoning and memory, provide it tools and more.

### Define tasks

Then describe the tasks to be performed by AI agents by providing clear and concise descriptions of both the task and the expected output.

### Define the crew

Finally, bring together AI agents and tasks to create a crew which collaborates to perform tasks, optionally with planning and a manager agent.

## Traces are now available for local crews and flows.

[Learn more](https://docs.crewai.com/en/observability/tracing)

## Developers love CrewAI

Peter K.  
*Director of Client Services*  
From answering calls to sending reminders, Alice has completely modernized how we communicate.

Jason R, GM  
*Evergreen Auto Group*  
We went from missing 40% of inbound calls to converting them automatically with Alice. It follows up, qualifies, and even books test drives — all without lifting a finger.

Priya M.  
*Family Law Practitioner*  
Alice gave us the leverage we needed to grow without hiring more staff. It’s like adding a full-time receptionist who never sleeps.

## Be part of a global developer community

Connect with like-minded developers in our forum, contribute to the open-source project on GitHub, and collaborate on exciting AI automation projects. Together, we can accelerate the development of cutting-edge AI solutions.