Basicper month
$0/month
- 50 workflow executions/month
Finding your next stop…
Loading the latest directory information.
Loading the latest directory information.
Start here for the decision-making essentials: what CrewAI does, who it is for, how it is accessed, and the first-party sources behind this profile.
$0/month
CrewAI is an enterprise multi-agent platform used by 65% of the Fortune 500. It unifies no-code and code-first agent building with centralized governance, human-in-the-loop controls, multi-LLM support, and integrations across cloud, on-prem, and evaluation tooling.
Read-only public captures of CrewAI’s homepage. Screenshots are dated, never live embeds, and open full-screen.
Short answers to the questions buyers and builders commonly ask about CrewAI. Each answer cites the shared ledger below, where every source is listed once.
Build automated multi-agent workflows via a no-code visual editor exportable to Python and · Centralized governance via a Control Plane with real-time tracing, RBAC, audit trails, Ent · Discovery matches observed patterns from billions of agent runs against tickets, chats, ap · Optimization turns production runs into training data and supports multi-LLM testing and e
No-code visual editor, exportable to Python
Enterprise teams building, running, and governing production AI agents; used by 65% of the
Used by 65% of the Fortune 500.
Automating long-horizon operational work via role-based multi-agent orchestration
Build complex operational agents that automate long horizon work using simple prompt and canvas style builder
Basic plan capped at 50 workflow executions per month
50 workflow executions/month
Basic | Free | Visual editor, AI copilot, GitHub integration, 50 workflow executions/month · Enterprise | custom | Scale agentic AI across the organization with centralized governance
Basic Free Build an agentic workflow today, and see what's possible with collaborative AI agents.
Native evaluation integrations with Arize, Galileo, DataDog, and Patronus · GitHub integration included on the Basic plan
Evaluation for native tracking with expanded sophistication powered by Arize, Galileo, DataDog, and Patronus
This profile connects the jobs CrewAI is described as handling with its delivery model, access options and the subjects used to match it to related products in this directory.
Each fact points to a recorded source, making it easy to distinguish verified product information from claims that need checking.
HTTP 200 verified twice
CrewAI
Application type: Multi-agent platform / Enterprise Agent Build & Runtime · Capability: Build automated multi-agent workflows via a no-code visual editor exportable t · Capability: Centralized governance via a Control Plane with real-time tracing, RBAC, audit
CrewAI
Multi-agent platform / Enterprise Agent Build & Runtime
Build automated multi-agent workflows via a no-code visual editor exportable to Python and a code-first API
Centralized governance via a Control Plane with real-time tracing, RBAC, audit trails, Enterprise IAM, human-in-the-loop approval gates, and runtime hooks for PII redaction and policy checks
Discovery matches observed patterns from billions of agent runs against tickets, chats, apps, and workflows to surface ranked automation opportunities
Optimization turns production runs into training data and supports multi-LLM testing and evaluation
Automating long-horizon operational work via role-based multi-agent orchestration
Enterprise teams building, running, and governing production AI agents; used by 65% of the Fortune 500
Web-based platform with visual editor and code-first Python API
A concise view of the jobs, capabilities and integrations described in the recorded product sources.
Documented product formats, platforms and official distribution destinations. Availability can vary by region and plan.
A concise history of software releases and material product changes. Events appear only when a dated source supports what changed.
Showing the newest updates and meaningful milestones. Open an entry for its summary and source.
Fix detection of Anthropic preview tool-use blocks. · Preserve strict tool schema property names. · Dispatch executionend hook on failed crew and flow executions.
View source [2]Authenticate skill registry downloads · Update snapshot and changelog for v1.15.4
View source [2]Promote Skills Repository out of experimental status · Add Flows in Studio documentation · @jessemiller, @joaomdmoura, @vinibrsl
View source [2]Add organization ID parameter to PlusAPI client · Add step interception points and rework execution hooks documentation around @on · Wire execution-boundary interception points
View source [2]Pull latest LLM models dynamically in the crew wizard. · Support inline skill definitions. · Add generated Flow Definition authoring skill.
View source [2]Track conversational flow turn usage in telemetry Support conversational flows in the CLI TUI
View source [2]Add checkpoint list/info CLI commands Add guardrailtype and name to distinguish traces
View source [2]Add RuntimeState RootModel for unified state serialization Enhance event listener with new telemetry spans for skill and memory events
View source [2]Facts, answers, structured details, milestones and primary resource links cite this shared ledger. Each external page appears once; release tags from the same GitHub project are grouped under one release history.
These tools share a workflow, capability or audience with CrewAI. They may complement it rather than replace it, and are not presented as integrations or endorsements.
Basic | Free | Visual editor, AI copilot, GitHub integration, 50 workflow executions/month
Enterprise | custom | Scale agentic AI across the organization with centralized governance
Native evaluation integrations with Arize, Galileo, DataDog, and Patronus
GitHub integration included on the Basic plan
Google user data is never used for advertising or for training AI models
Google-derived data is removed or irreversibly anonymized within 30 days after account deactivation or unlinking; encrypted backups may persist up to 180 days
Official profiles at https://x.com/crewaiinc, https://www.linkedin.com/company/crewai-inc/, and https://github.com/crewaiinc/
Basic plan capped at 50 workflow executions per month
Multi-agent platform · Enterprise agent build and runtime platform · No-code visual editor for multi-agent workflows, exportable to Python
Multi-agent platform
Enterprise agent build and runtime platform
No-code visual editor for multi-agent workflows, exportable to Python
Code-first API for full programmatic control
Control Plane with real-time tracing, RBAC, audit, and human-in-the-loop approval gates
Runtime hooks inject PII redaction and policy checks at every LLM and tool call
Multi-LLM testing for swapping models at runtime
GitHub, Arize, Galileo, DataDog, and Patronus
Used by 65% of the Fortune 500
Basic | $0/month | 50 workflow executions/month
https://x.com/crewaiinc, https://www.linkedin.com/company/crewai-inc/, https://github.com/crewaiinc/
Application type: Agent platforms — The Leading Multi-Agent Platform · Unified build and runtime platform that is centrally governed for multi-agent workflows · No-code visual editor, exportable to Python
Agent platforms
Unified build and runtime platform that is centrally governed for multi-agent workflows
No-code visual editor exportable to Python for building agents
Code-first API built for total control over agent orchestration
Role-based agents with deterministic agent workflows
RBAC, immutable audit trails, and Enterprise IAM for governance
Human-in-the-loop approval gates and intervention during execution
CrewAI launched Discovery, an engine that identifies automation use cases by matching patterns from prior agent runs against a company's tickets, chats, and workflows.
View source [5]Add support for custom persistence key in @persist · Add Responses API support for Azure OpenAI provider · Forward credentialscopes to Azure AI Inference client
View source [2]Add lifecycle events for checkpoint operations · Add support for e2b · Fall back to DefaultAzureCredential when no API key is provided in Azure integration
View source [2]Add checkpoint resume, diff, and prune commands with improved discoverability. · Add fromcheckpoint parameter to Agent.kickoff and related methods. · Add template management commands for project templates.
View source [2]Add async checkpoint TUI browser · Add aclose()/close() and async context manager to streaming outputs · Fix regex for template pyproject.toml version bumps
View source [2]Add enterprise release phase to devtools release · Preserve method return value as flow output for @humanfeedback with emit · Update changelog and version for v1.12.1
View source [2]Add requestid to HumanFeedbackRequestedEvent · Add Qdrant Edge storage backend for memory system · Add docs-check command to analyze changes and generate docs with translations
View source [2]Add Qdrant Edge storage backend for memory system Add docs-check command to analyze changes and generate docs with translations
View source [2]Add flowstructure() serializer for Flow class introspection. · Fix security vulnerabilities by bumping pypdf, tinytag, and langchain-core. · Preserve full LLM config across HITL resume for non-OpenAI providers.
View source [2]Update changelog and version for v1.11.0rc2
View source [2]Upgrade Gemini GenAI · Adjust executor listener value to avoid recursion · Group parallel function response parts in a single Content object in Gemini
View source [2]Enhance MCP tool resolution and related events Update lancedb version and add lance-namespace packages
View source [2]feat: add a2a liteagent, auth, transport negotiation, and file support · fix: improve output handling and response model integration in agents
View source [2]fix: ensure verbosity flag is applied b · fix: use responsejsonschema · fix: tool response pt2
View source [2]Implement before and after tool call hooks in CrewAgentExecutor · Add structured outputs and responseformat support across providers · Correct tool-calling content handling and schema serialization
View source [2]Add structured outputs and responseformat support across providers Add responseid in streaming response
View source [2]Add A2A task execution utilities · Add A2A server configuration and agent card generation · Add additional A2A transports
View source [2]Add native async chain for a2a Add a2a update mechanisms (poll/stream/push) with handlers and config
View source [2]Resolve connection issues (4129) · Update api-reference/status docs page · @greysonlalonde, @heitorado, @lorenzejay, @lucasgomide
View source [2]Add --no-commit flag to bump command · Use JSON schema for tool argument serialization · Fix error message display from response when tool repository login fails
View source [2]Add async flow kickoff Add async crew support
View source [2]Fix ChatCompletionsClient call to ensure proper functionality (3910) · Ensure async methods are executable for annotations · Fix parameters in RagTool.add, add typing, and tests (3979)
View source [2]Add streaming result support to flows and crews Add gemini-3-pro-preview
View source [2]chore: update hotfix crewAI version 0.203.1 - 0.203.2 by @lorenzejay in https://github.com/crewAIInc/crewAI/pull/3963
View source [2]Add a2a trust remote completion status flag Fetch and store more data about Okta authorization server
View source [2]Fix handling of agent max iterations · Resolve routing issues for LLM model syntax to respected providers
View source [2]Add support for non-AST plot routes Implement first-class support for MCP
View source [2]Refactor flow handling, typing, and logging Enhance QdrantVectorSearchTool
View source [2]
