NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI · #798 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 today
02 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4 versions withdrawn
withdrawn after publishing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
457 releases · first in 2023
Adding OPENAI_BASE_URL as fallback
Small bug fix for support future CrewAI deploy
New LLM class to interact with LLMs (leveraging LiteLLM)
kickoff_for_each_asyncOne column per month.
Printing max rpm message in different color
Removing LangChain and Rebuilding Executor
Adding ability for auto complete
crewai install CLIcrewai deploy CLIplanning_llmNothing published for this version
Nothing published for this version
Nothing published for this version
crewAI Testing / Evaluation - https://docs.crewai.com/core-concepts/Testing/
- Fix bug with planning feature
[Breaking Change] Type Safe output
Nothing published for this version
Adding new ability to return a tool results as an agent result
fixing embechain dependency issue
New @composiohq integration is out
Nothing published for this version
Nothing published for this version
Updating crewai create CLI to use the new version
Bumping version of crewai-tools
Your agents can now execute code
crewai train -n XUpdating crewai create CLI to use the new version
crewai create CLI to use the new versionNothing published for this version
New kickoff_for_each, kickoff_async and kickoff_for_each_async methods for better control over the kickoff process
kickoff_for_each, kickoff_async and kickoff_for_each_async methods for better control over the kickoff processusage_metrics to full output or a crewUpdating project generation template
Nothing published for this version
Small bug fixes on crewAI project structure
Making agent delegation more versatile for smaller models
Docs Update will follow sorry about that and thank you for bearing with me, we are launching new docs soon!
Docs Update will follow sorry about that and thank you for bearing with me, we are launching new docs soon!
➿ Fixing task callback 🧙 Ability to set a specific agent as manager instead of having crew create your one 📄 Ability to set system, prompt and response templates, so it works more reliable with opensource models (works better with smaller models) 👨💻 Improving json and pydantic output (works better with smaller models) 🔎 Improving tool name recognition (works better with smaller models) 🧰 Improvements for tool usage (works better with smaller models) 📃 Initial support to bring your own prompts 2️⃣ Fixing duplicating token calculator metrics 🪚 Adding couple new tools, Browserbase and Exa Search 📁 Ability to create directory when saving as file 🔁 Updating dependencies - double check tools 📄 Overall small documentation improvements 🐛 Smaller bug fixes (typos and such) 👬 Fixing co-worker / coworker issues 👀 Smaller Readme Updates
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
updating version used on crewai CLI
Updating crewAI tool version with bug fixes
Nothing published for this version
Major Long term memory interpolation issue
Nothing published for this version
Nothing published for this version
Nothing published for this version
Updating crewai-tools to 0.1.15
Adding max_execution_time support
max_execution_time supportNothing published for this version
Nothing published for this version
🧠 Memory (shared crew memory) - To enable it just add memory=True to your crew, it will work transparently and make outcomes better and more reliable,
memory=True to your crew, it will work transparently and make outcomes better and more reliable, it's disable by default for nowNothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Other minor import issues on the new templates
Nothing published for this version
Nothing published for this version
Fixing bug on the new cli template
Adding initial CLI crewai create command
crewai create commandYour coding agent can read these notes before it upgrades. Set up the MCP server →