Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
CrewAI 1.5.0 adds LLM call hooks, exposes messages to task outputs, and improves A2A trust and Okta data.
$ git clone --branch 1.5.0 https://github.com/crewAIInc/crewAI.git # already have the repo? check out this version: $ git checkout 1.5.0
result = crew.kickoff()
for task_output in result.tasks_output:
print(task_output.messages) - ›Adds
beforeandafterLLM call hooks inCrewAgentExecutorfor observability and control around every LLM invocation. - ›Exposes messages to
TaskOutputandLiteAgentOutputs, giving callers access to the full message history from a task run. - ›Adds A2A trust remote completion status flag for agent-to-agent trust workflows.
- ›Fetches and stores richer data about Okta authorization servers for enhanced auth integrations.
- ›Enhances schema description of
QdrantVectorSearchToolfor improved usability and discoverability.