Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

CrewAI

A Python framework for orchestrating teams of role-playing agents (crews) and event-driven workflows (flows).

Agent frameworks and SDKs Multi-agent frameworkOpen source · MITFree to startUp Live status

Use it in: API / SDK Works with: MCP Local models Multi-agent

Price
Free
free tier available
Popularity
#18 in Frameworks
Gid Score 50 / 100 · #18 of 50 ranked frameworks and SDKs
Trend
Steady
downloads 0.0% over 30 days · down 2.3% last week
Development
Actively updated
latest 1.15.43, yesterday
Community
61.1K GitHub stars
608K package downloads a week

Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number

What CrewAI does

CrewAI is a multi-agent framework from CrewAI, first released in November 2023. You use it through a Python library. Its documentation covers MCP servers, subagents or parallel agents and local models. It can run models from OpenAI and any OpenAI-compatible endpoint. It is used from Python. It is free and open source (MIT); you pay only for the models it calls.

Key facts

MakerCrewAI
TypeMulti-agent framework
First releasedNovember 2023
LicenseMIT
InterfacesPython library
Main languagePython
Open issues and PRs1,270

Pricing

CrewAI is an open-source framework that remains free. The company also offers a hosted CrewAI Studio platform with a Free plan (50 workflow executions/month, visual editor, GitHub integration) and a custom-priced Enterprise plan for production deployments with governance, SSO, RBAC, and dedicated support.

Source: official pricing page, checked Oct 10, 2026. Prices change often; confirm before you buy.

CrewAI pricing history since 2024 · Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (MIT)
  • Where you use itPython library
  • Supports MCP?Yes
  • Model providersopenai, any OpenAI-compatible, local
  • Subagents / multi-agent?Yes
  • Feature comparisonAll agents
  • Closest alternativeLangChain · all alternatives

What's new in CrewAI: November 2026 so far

Full monthly summary

November brought significant improvements to agent capabilities and infrastructure, with better support for standalone agents, improved file handling, and refined API key management across various LLM providers.

Action needed: ChromaDB is now an optional extra; Knowledge defaults to local Qdrant for storage.
  • Conversational agent sessions are now available in experimental form.
  • Standalone agent projects can now be scaffolded and loaded as JSON.
  • GPT-6-Luna is now the default model everywhere in CrewAI.
  • Spreadsheet reading capability added for agents with file tools.

10 releases this month · summarised from the official release notes · all months

AgentGid articles about CrewAI

All guides

Get started with CrewAI

PyPIpip install crewai

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Add-ons for CrewAI: save tokens, add memory and tools

All agent tooling

Listed because each tool documents support for CrewAI or for agent frameworks in general. Savings and results depend on your workload.

Compare CrewAI with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
1
LangChainLangChain
79 41.1M up 5.7% down 2.7% 150K+76/day 1.5.22d ago Free (OSS)
2
LangGraphLangChain
75 20.1M up 5.5% up 29.2% 45.1K+48/day 1.2.23yesterday Free (OSS)
3
AI SDKVercel
68 47.2M up 3.9% up 38.4% 28.1K+30/day 7.0.1772d ago Free (OSS)
4 64 29.3M up 5.9% up 37.6% 8,588+9/day 0.2.185yesterday Free (OSS)
5
MastraMastra
63 3.7M up 14.9% up 49.9% 29.6K+23/day 1.84.02d ago Free (OSS)
6 62 7.2M up 4.8% up 38.9% 30.8K+21/day 0.25.02d ago Free (OSS)

Head to head: CrewAI vs LangGraph · CrewAI vs n8n · CrewAI vs OpenAI Agents SDK

Tools used with CrewAI

All tools

What 365 public GitHub projects that depend on CrewAI use with it, from their dependency files.

  1. python-dotenv78.9%
  2. LangChain72.3%
  3. Pydantic59.2%
  4. OpenAI Python Library54.8%
  5. Requests50.7%
  6. CrewAI Tools48.2%
  7. FastAPI47.7%
  8. Uvicorn45.2%
  9. NumPy44.9%
  10. pandas42.7%

Used far more often here than in AI-built projects overall: what sets CrewAI projects apart.

  1. Instructor29.6% · 462.6×
  2. Kubernetes Python Client28.2% · 160.4×
  3. oauthlib28.2% · 147.1×
  4. FlatBuffers27.9% · 134.4×
  5. LangSmith31.0% · 96.8×
  6. gRPC28.2% · 80.2×
  7. OpenTelemetry OTLP gRPC Exporter28.5% · 68.5×
  8. fsspec27.9% · 62.4×

Ratings from people who use CrewAI

No ratings yet. Used CrewAI? Rate it and say what it is good and bad at.

CrewAI news

All AI agent news

  1. Release GitHub Releases

    CrewAI 1.15.43 released

    Fix detection of multimodal support for Claude 5.; Update snapshot and changelog for v1.15.42.

  2. Release GitHub Releases

    CrewAI 1.15.42 released

    Make ChromaDB an optional extra; Default Knowledge to local Qdrant and decouple storage from ChromaDB; Pick tools for standalone agents and add them later

What changed: recent CrewAI releases

26 stable releases in the last 90 days · Monthly summary · Full changelog

1.15.43
  • Fix detection of multimodal support for Claude 5.
  • Update snapshot and changelog for v1.15.42.
1.15.42
  • Make ChromaDB an optional extra
  • Default Knowledge to local Qdrant and decouple storage from ChromaDB
  • Pick tools for standalone agents and add them later
  • Store output_json values as JSON to prevent date issues in .json and output_file
  • Give each Flow its own ID from an initial_state instance
  • Honor max_execution_time without waiting for the worker
Earlier releases
1.15.41
  • Allow approved private URL hosts.
  • Fix projects to depend on PyMuPDF 2.x.
  • Drop a real storage URL from the URL read tests.
  • Keep earlier step outputs across a human-feedback resume.
  • Strip cache_breakpoint marker on the LiteLLM path.
  • Snapshot and changelog for v1.15.40.
1.15.40
  • Remove chromadb from the embedding function layer.
  • Add exact historical state lookup by row id.
  • Wire jsonl into rag data type discovery.
  • Scaffold standalone agents as JSON by default.
  • Add backend record lifecycle and pagination tests.
  • Run after_llm_call hooks on async calls.
1.15.39
  • Document the apps_not_connected error on /kickoff and /status
1.15.38
  • Make gpt-6-luna crewAI's default model everywhere
  • Read spreadsheet URLs in an agent's input with tools over every row
  • Tag eval usage spans with target and a per-evaluation id
  • Add --no-open to crewai eval for headless use
  • Count a crewai eval run that exits with an error as run_failed
  • Create the project .env owner-only when crewai eval turns tracing on

CrewAI prices over time

Full pricing history →

CrewAI plan pricesfrom archived copies of the official pricing page
Cheapest paid planMost expensive self-serve plan
Token prices of OpenAI modelsnewest OpenAI model in each family, output price per 1M tokens
OpenAI FlagshipOpenAI Mini

CrewAI popularity and usage data

CrewAI was downloaded 608K times from PyPI in the week ending Nov 17, 2026, down 2.3% on the week before and down 0.0% over the last 30 days compared with the 30 before. The GitHub repository has 61.1K stars, 1,338 of them added in the last 30 days. The latest stable release is 1.15.43, published Nov 19, 2026; there were 15 stable releases in the past 30 days. It was mentioned in 5 Hacker News posts and comments over the last 30 days.

Downloads per dayPyPI, 7-day average 86.8K/day
GitHub starsrunning total 61.1K
Hacker News mentionsposts and comments, rolling 7-day total 1 this week

Download the raw daily series: crewai.csv

Gid Score breakdown

Adoption62
Community74
Attention0
Momentum50

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsNov 17, 2026Nov 19, 06:24 UTC
GitHub starsNov 19, 2026Nov 19, 06:26 UTC
Hacker News mentionsNov 18, 2026Nov 19, 06:26 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

Reliability

From the vendor's public status page · now: All Systems Operational

1 incidents reported in the last 30 days, 0.5 hours in total from report to resolution.

Incidents per monthfrom the official status page

Each bar is one month; the last one is the month so far. Vendors post even short slowdowns, so read this as how often something was reported, not as downtime. Compare with other agents →

Oct 29, 2026, 12:53 UTCAutomations failing to be created/updated · minor
Sep 15, 2026, 01:37 UTCCrew Deployments Failure · major

CrewAI FAQ

How much does CrewAI cost?

CrewAI is an open-source framework that remains free. The company also offers a hosted CrewAI Studio platform with a Free plan (50 workflow executions/month, visual editor, GitHub integration) and a custom-priced Enterprise plan for production deployments with governance, SSO, RBAC, and dedicated support.

Is CrewAI open source?

Yes. CrewAI is open source, released under the MIT license.

How popular is CrewAI?

CrewAI was downloaded 608K times from PyPI in the week ending Nov 17, 2026, down 2.3% on the week before and down 0.0% over the last 30 days compared with the 30 before. The GitHub repository has 61.1K stars, 1,338 of them added in the last 30 days. The latest stable release is 1.15.43, published Nov 19, 2026; there were 15 stable releases in the past 30 days.

What is the latest version of CrewAI?

The latest stable release we track is 1.15.43, published on Nov 19, 2026.

What are the alternatives to CrewAI?

The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.

For the makers of CrewAI badges, corrections

Add a live badge to your README or site:

AgentGid: #18 in Frameworks Gid Score: 50/100 downloads: 608K/week ▶ 30d status: operational

[![AgentGid: #18 in Frameworks](https://agentgid.com/badges/crewai-rank.svg)](https://agentgid.com/agents/crewai/)
[![Gid Score: 50/100](https://agentgid.com/badges/crewai-score.svg)](https://agentgid.com/agents/crewai/)
[![downloads: 608K/week ▶ 30d](https://agentgid.com/badges/crewai-downloads.svg)](https://agentgid.com/agents/crewai/)
[![status: operational](https://agentgid.com/badges/crewai-status.svg)](https://agentgid.com/agents/crewai/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

PyPI: crewai. GitHub: crewAIInc/crewAI. See data sources for how each one is collected.