Releasesby GlyphCrewAI 1.15.35
Documentation Update litellm model catalog for v1.15.35 Add snapshot and changelog for v1.15.34 Contributors @github-actions[bot], @joaomdmoura, @lorenzejay
Also shipped Nov 3, 2026CrewAI in November 2026 →
Gemini Enterprise: Salesforce federated data store
Connecting a Salesforce data source with Gemini Enterprise using data federation is generally available (GA). You can use the Gemini Enterprise app assistant to search across your Salesforce accounts, contacts, opportunities, cases, leads, and custom objects, get answers grounded in that content, and create, update, and delete records without needing to...
[In preview] Public Preview: Extend immutability for PITR backups for Azure SQL Database and Azure SQL Managed Instance
With this enhancement, you have the ability to lock your retention to the configured PITR retention, beyond the default 7 days of immutable backups that are already available. This is especially useful for financial customers who typically have 35 days of
UI improvements now generally available for PD Reliability Platform customers
Customers on PD Reliability Platform now have an improved UI experience, including: Consolidated settings: Brings all your configuration and admin settings together in one place. New nav: Provides streamlined access to your most important capabilities. Your Subscription: Shows where the opportunities are to shift work off humans and onto AI and automation.
Claude auto-connect (beta) for PagerDuty MCP Server now in Early Access
With Claude auto-connect, members with a matching PagerDuty account are connected to PagerDuty in Claude automatically, with no sign-in screen and no identity provider (IdP) configuration. Members act as themselves in PagerDuty, with the permissions they already have there.
In BigQuery Studio , the left pane has been updated with new tab names
In BigQuery Studio , the left pane has been updated with new tab names. The Classic Explorer tab has been renamed to the Data tab, and the Repository tab has been renamed to the Source control tab. The Data tab now includes the Add data button and focuses on data hierarchies. These changes are generally available (GA).
Dependabot version updates support Agent Package Manager
You can now keep your AI agent skills, prompts, and instructions up to date with Dependabot version updates for Agent Package Manager (APM) . Dependabot opens pull requests to update supported git dependencies declared in apm.yml and regenerates apm.lock.yaml when it’s present. This support covers version updates, not security updates.
More from CrewAIEvery CrewAI release →
CrewAI 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.
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...