NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI · #2572 most downloaded on PyPI
Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Last release 2 days ago
03 Oct 2026
Ships on a steady schedule
a new release about every 8 days
Nearly every release is documented
notes for 60 of the last 60 stable releases
4 versions withdrawn
withdrawn after publishing
3 years old
458 releases · first in 2023
Adding initial CLI crewai create command
crewai create commandEfficiency in tool usage +1023.21%
function_calling_llm to Agent or Crewkickoff with crew.usage_metricscrew.kickoff(inputs: {'key': 'value})One column per month.
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Making sure code is backwards compatible
Nothing published for this version
Nothing published for this version
Removing lingering crewai_tools dependency
crewai_tools dependencyMaking agents memory-less by default for token count reduction (breaking change for people counting on this previously)
Adding support for agents without tools
Nothing published for this version
All improvements from the v0.14.0rc.
All improvements from the v0.14.0rc.
Nothing published for this version
Adding support to format tasks output as Pydantic Objects Or JSON
Adding further error logging so users understand what is happening if a tool fails
It fixes a bug on the tool usage logic that was early caching the result even if there was an error on the usage, preventing it from using the tool ag
Ability to set function_calling_llm on both the entire crew and individual agents
function_calling_llm on both the entire crew and individual agentsAbility to get full_ouput from crew kickoff with all tasks outputs
full_ouput from crew kickoff with all tasks outputsstep_callback function for both Agents and Crews so you can get all intermediate stepsmax_inter bug now properly forcing llm to answer as it gets to thatCrewAgentOutputParserOverall doc + readme improvements
quick Fix for hierarchical manager
Adding manager_llm for hierarchical process
manager_llm for hierarchical processmax_inter and max_rpm logicThis new version bring a lot of new features and improvements to the library.
This new version bring a lot of new features and improvements to the library.
Adding ability to limit maximum number of iterations for an agent
Nothing published for this version
Initial changes for supporting multiple languages
Nothing published for this version
Nothing published for this version
Nothing published for this version
Adding tool caching a loop execution prevention. (@joaomdmoura)
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Adding ability to use other LLMs, not OpenAI
Crew Verbose Mode: Now allowing you to inspect a the tasks are being executed.
Crew Verbose Mode: Now allowing you to inspect a the tasks are being executed.
README and Docs Updates: A series of minor updates on the docs
We are thrilled to announce the initial release of CrewAI, version 0.1.0! CrewAI is a framework designed to facilitate the orchestration of autonomous
We are thrilled to announce the initial release of CrewAI, version 0.1.0! CrewAI is a framework designed to facilitate the orchestration of autonomous AI agents capable of role-playing and collaboration to accomplish complex tasks more efficiently.
Initial Launch: CrewAI is now officially in the wild! This foundational release lays the groundwork for AI agents to work in tandem, each with its own specialized role and objectives.
Role-Based Agent Design: Define and customize agents with specific roles, goals, and the tools they need to succeed.
Inter-Agent Delegation: Agents are now equipped to autonomously delegate tasks, enabling dynamic distribution of workload among the team.
Task Management: Create and assign tasks dynamically with the flexibility to specify the tools needed for each task.
Sequential Processes: Set up your agents to tackle tasks one after the other, ensuring organized and predictable workflows.
Documentation: Start exploring CrewAI with our initial documentation that guides you through the setup and use of the framework.
Agent, Task, Crew, and Process classes.Your coding agent can read these notes before it upgrades. Set up the MCP server →