What's Changed

Features

Pull latest LLM models dynamically in the crew wizard.

Support inline skill definitions.

Add generated Flow Definition authoring skill.

Support templated Flow action inputs.

Add text helper for flow CEL prompts.

Add text helper to flow skill example.

Implement message setup and feedback handling in AgentExecutor.

Add repository agents to flow definitions.

Define stream frame protocol for flows.

Type tool and app in CrewDefinition.

Repoint template commands to crewAIInc-fde org.

Bug Fixes

Key model-catalog cache by exact API key, shorten TTL, and skip Ollama.

Unify crewai run flow input resolution and prompt from the state schema.

Resolve pip-audit failures for onnx 1.22.0 and nltk PYSEC-2026-597.

Ensure we are writing version for flows.

Include aiobotocore in the bedrock extra.

Reject self-listening flow methods.

Cut docs version nav from Edge so new pages aren't dropped.

Documentation

Update language from Rules to Policies to match new dashboard changes.

Document flow agent options.

Add streaming docs to the navigation.

Document Cost Limit rule type in Agent Control Plane.

Drop CREWAI_LOG_FORMAT references from Datadog guide.

Contributors

@akaKuruma, @danielfsbarreto, @github-code-quality[bot], @joaomdmoura, @lorenzejay, @lucasgomide, @manisrinivasan2k1, @renatonitta, @vinibrsl

What's Changed

Features

• Repoint template commands to crewAIInc-fde org
• Support inline skill definitions
• Define stream frame protocol for flows
• Add type tool and app in CrewDefinition
• Add generated Flow Definition authoring skill

Bug Fixes

• Cut docs version navigation from Edge to prevent new pages from being dropped

Documentation

• Document Cost Limit rule type in Agent Control Plane
• Drop CREWAI_LOG_FORMAT references from Datadog guide

Contributors

@danielfsbarreto, @joaomdmoura, @lorenzejay, @lucasgomide, @vinibrsl

What's Changed

Features

• Initialize Git repositories for generated projects (#6364)
• Require explicit CrewAI project definitions (#6358)
• Open deployment page after CLI deploy (#6343)

Bug Fixes

• Fix deployment page link ID resolution (#6365)
• Fix JSON crew template rendering (#6359)
• Fix JSON crew version pin (#6342)
• Fix SSRF redirect bypass in scraping fetches (#6331)

Documentation

• Improve open source positioning in README (#6363)
• Improve coding agent setup call-to-action (#6344)
• Add snapshot and changelog for version 1.15.1a1 (#6362)

Contributors

@joaomdmoura, @lorenzejay, @oalami, @theCyberTech, @vinibrsl

What's Changed

Features

• Track conversational flow turn usage in telemetry
• Support conversational flows in the CLI TUI
• Add unified declarative flow loading
• Add declarative Flow CLI support
• Add optional if expression to each.do steps
• Add single agent action to Flow definitions
• Add crew actions to FlowDefinition
• Add inline crew definition loading
• Add each composite action to FlowDefinition
• Implement DMN mode support in crew creation and execution

Bug Fixes

• Fix owner-only permissions enforcement on credential files
• Fix JSON schema flow state kickoff inputs
• Fix symlink path traversal in skill archive extraction
• Aggregate token usage across all LLM calls
• Remove duplicated Exa tool
• Resolve JSON crew issues
• Fix JSON crew handling and enhance memory reset functionality

Documentation

• Update installation and quickstart documentation for JSON-first crew projects
• Add Datadog integration guide with importable operations dashboard
• Add "One Card per Step" Studio page
• Add snapshots and changelogs for previous versions leading to v1.15.0

Performance

• Improve crewai run startup UX
• Keep flow method progress visible for nested crews

Refactoring

• Remove StateProxy from flow state access
• Consolidate crewai run and crewai flow kickoff
• Discriminate FlowDefinition state types
• Wire config and persistence from FlowDefinition into the runtime

Contributors

@gabemilani, @github-code-quality[bot], @greysonlalonde, @iris-clawd, @jessemiller, @joaomdmoura, @lorenzejay, @lucasgomide, @theCyberTech, @vinibrsl

What's Changed

Features

• Add unified declarative flow loading
• Improve crewai run startup UX
• Consolidate crewai run and crewai flow kickoff
• Keep flow method progress visible for nested crews
• Add declarative Flow CLI support
• Allow @router() as start method of a flow
• Add typed output schemas for CrewAI tools

Bug Fixes

• Pin opentelemetry to ~=1.42.0

Documentation

• Add "One Card per Step" Studio page

Contributors

• @jessemiller, @joaomdmoura, @lucasgomide, @vinibrsl

What's Changed

Features

• Add script/code block action to FlowDefinition
• Add crew actions to FlowDefinition
• Add each composite action to FlowDefinition
• Implement DMN mode support in crew creation and execution
• Enhance memory reset functionality and JSON crew handling
• Add expressions to FlowDefinition actions
• Implement Flow definition run tools without Python code
• Drive human feedback from the flow definition
• Wire config and persistence from FlowDefinition into the runtime
• Add experimental crewai run --definition for flows
• Support ZIP deployment fallback and JSON crew project env runs
• Introduce JSON first crews

Bug Fixes

• Fix duplicated Exa tool
• Fix aggregate token usage across all LLM calls
• Resolve issues with crew loading and validation logic

Documentation

• Document FlowDefinition fields in the JSON schema
• Update installation and quickstart documentation for JSON-first crew projects
• Update changelog and version for v1.14.7

Contributors

• @gabemilani, @greysonlalonde, @iris-clawd, @joaomdmoura, @lorenzejay, @lucasgomide, @theCyberTech, @vinibrsl

What's Changed

Features

• Add pluggable default backends for memory, knowledge, rag, and flow.
• Surface real finish_reason, sampling params, and response.id on LLM events.
• Type DSL triggers as route-aware decorators.
• Add chat API for conversational flows.
• Make locking backend overridable.
• Build FlowDefinition from Flow DSL metadata.
• Add native Snowflake Cortex LLM provider.
• Add crew trained agents file support.

Bug Fixes

• Fix checkpoint to rebuild custom BaseLLM as concrete LLM on restore.
• Gate restore on a flag to prevent live snapshots from replaying as resume.
• Scope runtime state per run to bound growth and isolate concurrent runs.
• Fix telemetry setup on crewai-login.
• Respect suppress_flow_events for method-execution events.
• Restore [project.scripts] in crewai package for uv tool install.
• Resolve pip-audit CVEs for aiohttp, docling, and docling-core.
• Fix file input not working reliably.
• Fix Snowflake Claude incomplete tool result histories.

Documentation

• Update changelog and version for v1.14.7.
• Update OpenTelemetry collector documentation.
• Update NVIDIA Nemotron LLM guide.
• Add Databricks integration guide.
• Add Snowflake integration guide.

Performance

• Improve crewai import speed by lazy-loading docling imports.

Refactoring

• Simplify flow condition evaluation to be stateless per event.
• Decouple convo logic from runtime and add a conversational_definition.
• Split flow.py into DSL, definition, and runtime.

Contributors

@Luzk, @alex-clawd, @devin-ai-integration[bot], @greysonlalonde, @gvieira, @jessemiller, @lorenzejay, @lucasgomide, @mattatcha, @vinibrsl

What's Changed

Features

• Add reset_runtime_state to release accumulated bus state
• Handle supporting both custom prompts
• Decouple conversation logic from runtime and add a conversational_definition

Bug Fixes

• Fix scope of runtime state per run to bound growth and isolate concurrent runs
• Fix telemetry setup on crewai-login
• Fix respect for suppress_flow_events for method-execution events

Documentation

• Update OpenTelemetry images
• Update documentation to reflect new state of OpenTelemetry collector
• Update changelog and version for v1.14.7a4

Refactoring

• Simplify flow condition evaluation to be stateless per event
• Improve conversation routing cycle with one less route

Contributors

@greysonlalonde, @lorenzejay, @lucasgomide, @vinibrsl