CrewAI
Open-source artificial intelligence agent framework
From Wikipedia, the free encyclopedia
CrewAI is an open-source software framework and platform for building AI agents and multi-agent systems. Written primarily in Python, it is used to define artificial-intelligence agents, assign tasks to them, and coordinate their work through agent teams and workflows.[1][2] The framework is associated with CrewAI Inc., a startup developing enterprise tools for automating business workflows with large language model-based agents.[3]
| CrewAI | |
|---|---|
 | |
| Original author | João Moura |
| Developers | CrewAI Inc. and contributors |
| Initial release | December 4, 2023 |
| Stable release | 1.14.3
/ April 24, 2026 |
| Written in | Python |
| Type | Software framework for AI agents |
| License | MIT License |
| Website | crewai |
| Repository | github |
History
CrewAI was first released on the Python Package Index in December 2023.[4] The project was created by João Moura and later developed by CrewAI Inc. and open-source contributors.[2]
In October 2024, TechCrunch reported that CrewAI had raised $18 million across seed and Series A funding rounds from investors including Boldstart Ventures, Craft Ventures, Earl Grey Capital, and Insight Partners. The report also stated that Andrew Ng and HubSpot co-founder Dharmesh Shah had invested in the company.[3] SiliconANGLE described the company as the developer of an open-source framework for building artificial-intelligence agents and reported that the funding consisted of a seed round led by Boldstart Ventures and a Series A led by Insight Partners.[5]
By late 2024, CrewAI had introduced commercial enterprise products built on top of its open-source components. TechCrunch reported that the company's enterprise offering added access controls, analytics, support, and templates for workflow automation.[3]
Features
CrewAI is designed around groups of agents, sometimes called "crews", that can be assigned roles, goals, and tasks. The framework supports agent collaboration, task delegation, tool use, memory, and knowledge sources for retrieval-augmented generation workflows.[6] The project describes two main building blocks: "Crews", which are used for autonomous agent collaboration, and "Flows", which are used for more controlled event-driven workflows.[2]
The framework is independent of LangChain and is released under the MIT License.[1] It can be installed as a Python package and is commonly used with external large language model APIs or local models, depending on the developer's configuration.[2]