LangGraph vs CrewAI
LangGraph (LangChain) and CrewAI (CrewAI) side by side on public data, as of Oct 6, 2026.
LangGraph has 26.4x the weekly package downloads of CrewAI (16.1M against 611K). CrewAI has 1.4x the GitHub stars of LangGraph (59.4K against 42.7K). LangGraph shipped 5 stable releases in the past 90 days. CrewAI shipped 22 stable releases in the past 90 days.
Side-by-side numbers
| Metric | LangGraph | CrewAI |
|---|---|---|
| Pulse Score | 69 | 52 |
| Overall rank | #10 | #33 |
| Downloads, last 7 days | 16.1M | 611K |
| Downloads, 7-day change | up 11.4% | up 7.2% |
| Downloads, 30-day change | down 21.8% | — |
| VS Code installs | — | — |
| Marketplace rating | — | — |
| GitHub stars | 42.7K | 59.4K |
| Homebrew installs, 30 days | — | — |
| Hacker News mentions, 30 days | 74 | 9 |
| Latest stable release | 1.2.13 · yesterday | 1.15.23 · 8d ago |
| Stable releases, 90 days | 5 | 22 |
| Terminal-Bench (best run) | — | — |
| Price | Free (OSS) | Free (OSS) |
| License | MIT | MIT |
| First released | — | — |
| Interfaces | Python library, JavaScript library | Python library |
| Models |
Trends
LangGraph
A low-level orchestration framework for building stateful agents as graphs, with durable execution, persistence and human-in-the-loop steps. Available for Python and JavaScript.
Pricing: LangGraph is open source and free to use; you pay only for the models and infrastructure it runs on.
Latest release 1.2.13:
- fix(langgraph): fork before replaying an update checkpoint the thread moved past
- fix(langgraph): keep an updatestate on an older checkpoint out of its other branches
- fix(langgraph): keep DeltaChannel counters on every updatestate path
- release(langgraph): 1.2.13
CrewAI
A Python framework for orchestrating teams of role-playing agents (crews) and event-driven workflows (flows).
Pricing: The CrewAI framework is open source and free. The company also sells a hosted platform with paid plans, which is separate from the library.
Latest release 1.15.23:
- Add support for native Gemini 3.8 Flash
- Implement evaluation of the last traced run through AMP in crewai eval
- Record the last traced run for crewai eval instead of printing it
- Improve platform integration setup UX