Releasesby GlyphCrewAI 1.15.34
This update adds a standalone LiteLLM catalog, improves crewai run input handling, and introduces new deployment options. It also includes several bug fixes for tool call telemetry and API key validation.
Also shipped Nov 1, 2026CrewAI in November 2026 →
Kubernetes connector reaches end of life - 02-Nov-202
Snyk announced end-of-life support for the Kubernetes connector (kubernetes-scanner) for Insights, with data ingestion stopping on November 2, 2026.
Atlas Agent Engine in public preview
Atlas Agent Engine is now available in public preview. It provides a secure way to run AI agents at scale.
Qwen Code Release v0.26.5
Qwen Code v0.26.5 adds bounded SQL history queries for H2 and MySQL, enables Generated UI by default, and introduces Web Shell keyboard shortcuts and background agent tracking.
Qwen Code Desktop v0.26.5
Qwen Code Desktop v0.26.5 introduces bounded SQL history queries, enables Generated UI by default, and shows running background agent counts in the status bar.
feldera 0.374.0
This release adds support for STARTSWITH and ENDSWITH string functions, implements NULLIF for mixed-type arguments, and updates date and interval arithmetic to follow the SQL standard. It also includes improvements to the profiler and NATS connector.
More from CrewAIEvery CrewAI release →
CrewAI 1.15.33
CrewAI 1.15.33 adds skill search functionality, support for passing inputs to Python flows, and various bug fixes related to token usage reporting and JSON crew runners.
CrewAI 1.15.32
CrewAI released version 1.15.32, fixing flaky tests and updating documentation snapshots and changelogs.
CrewAI 1.15.31
CrewAI 1.15.31 adds support for conversational flow context compaction and includes various security patches for deserialization, SQL injection, and path traversal vulnerabilities. It also improves guardrail handling and dependency management.
CrewAI 1.15.30
CrewAI 1.15.30 includes a bug fix for the agent login process during evaluation.
CrewAI 1.15.29
CrewAI 1.15.29 adds support for LiteLLM-compatible kwargs, Azure DocumentDB vector search integration, and promotes AgentExecutor out of experimental status.
CrewAI 1.15.28
Features Add crewai eval command to report where a stopped model broke. Use LiteLLM catalog for context windows. Bug Fixes Fix flow to learn from resumed human feedback and preserve reviewed output types. Warn when non-empty apps resolve to zero platform tools. Fix flow add-crew to correctly find the package from pyproject.
CrewAI 1.15.27
Features Add XPU to OpenCLIP provider device options Add deepinfra as an OpenAI-compatible provider Record why an evaluation stopped before its verdict Record what the run app's Deploy met before an attempt Implement per-run cost and time tracking in crewai eval --models without repeated progress lines Bug Fixes Fix issue where stopSequences were sent to...
CrewAI 1.15.26
Bug Fixes Fix ownership retention of rwlock when acquisition is interrupted. Resolve issue with documentation site source URLs not being preserved. Fix task output display in log-tasks-outputs to show actual output. Documentation Update snapshot and changelog for version v1.15.25.