Shipped · AI and LLM tooling

What crewAIInc/crewAI shipped

The public repository of CrewAI · github.com/crewAIInc/crewAI

Written by FoxPlug from the repository's own releases; not affiliated with CrewAI. Paste your own repository in the box below and FoxPlug writes the same weekly update for your product. This page is an automatic summary of the releases, pull requests and commits in github.com/crewAIInc/crewAI; CrewAI did not write it and does not use or endorse FoxPlug. Every line links to the change it describes.

Get a weekly update like this for your product, free

Or Use it as a GitHub Action

Follow crewAI's weekly shipped digest

Week of October 5, 2026

What shipped

Why it matters

This week the release line moved through 1.15.24 to 1.15.27 with fixes that touch everyday work: locks that no longer misrelease, flows whose start steps honour their listeners, and evaluations that explain the gap between pressing a command and getting a verdict. Two new providers, deepinfra and OpenCLIP device options, widen what you can route and embed with, while security bumps clear flagged dependency versions. The result is quieter runs and less guesswork when something does not start.

Changelog entry

Week of September 28, 2026

What shipped

Why it matters

This week brings job coordination across conversational flows, model evaluation tooling for comparing performance, and fixes to human feedback integration and trace reporting. Stability improvements ensure crews run untraced when authentication expires rather than failing, and security updates address vulnerabilities in pypdf and litellm.

Changelog entry

Example posts FoxPlug drafted from these changes. Not written or posted by the project.

Post for X

V1.15.23: Job coordination in conversational flows, crewai eval --models for comparing model performance, human feedback in flow outputs, and tracing fixes. Security updates to pypdf and litellm.

Post for LinkedIn

V1.15.23 ships job coordination across conversational flow turns with retained typed state, crewai eval --models for comparing model performance on deployed systems, and human feedback integration in declarative flows. Stability improvements let crews run untraced when authentication lapses, span exports preserve complete tool outputs, and context windows are centralized across model providers. Security updates address pypdf and litellm vulnerabilities.

Week of September 21, 2026

What shipped

Why it matters

Evaluation is now integrated into the CLI workflow, making it easier to assess crew performance. Provider resilience improvements handle transient failures gracefully. Security and resource management fixes ensure reliability and proper cleanup.

Changelog entry

Example posts FoxPlug drafted from these changes. Not written or posted by the project.

Post for X

This week: automated retry logic for provider throttles, native evaluation through crewai eval, Bedrock fallback support, and better resource management across tools.

Post for LinkedIn

CrewAI shipped several reliability and usability improvements this week. Throttled provider calls now retry automatically without affecting agent iteration counts. The new crewai eval command lets you evaluate your last traced run directly from the CLI. Bedrock provider calls gracefully fall back to sync when async is unavailable. Plus fixes for resource cleanup in S3 operations and browser reuse in Selenium scraping.

Weeks with too little public activity are left out rather than filled in. Last updated 2026-10-12.

Is this your repo? Ask us to remove this page.