A · leads
CrewAI
95.7
61,027 stars · MIT
AI Agents
CrewAI leads by 10.7 · clear
A · leads
95.7
61,027 stars · MIT
B
85.0
80,149 stars · MIT
CrewAI versus Prompt-Engineering-Guide is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. CrewAI is written mainly in Python; Prompt-Engineering-Guide is written mainly in MDX. The composite score is 95.7 for CrewAI and 85.0 for Prompt-Engineering-Guide.
Prompt-Engineering-Guide has 80,149 GitHub stars to CrewAI's 61,027, a gap of 19,122 (1.31×). Forks are 9,211 for CrewAI and 8,790 for Prompt-Engineering-Guide. On the log scale used inside this pair, adoption is 98 versus 100, and the fork community is 100 versus 100.
Push history: CrewAI was last pushed on 17 November 2026 (0 days ago), and Prompt-Engineering-Guide was last pushed on 11 March 2026 (250 days ago). Open issues stand at 1,276 for CrewAI (0.021 per star) and 300 for Prompt-Engineering-Guide (0.004 per star). Issue-health scores are 70 and 96; activity scores are 100 and 36.
Both CrewAI and Prompt-Engineering-Guide are listed as MIT. A permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. The license score is therefore level at 96 versus 96, and the decision moves to adoption, activity, and hosting. This is a procurement signal, not legal advice.
In AI Agents, both CrewAI (61,027 stars) and Prompt-Engineering-Guide (80,149 stars) are marked self-hostable. Deploy scores are 100 and 100. Running either one means you own upgrades, backups, and the license duties that follow a modified copy. Pricing labels on file: CrewAI is open source, Prompt-Engineering-Guide is open source.
The lead is split. CrewAI is furthest ahead on recent activity (100 to 36), while Prompt-Engineering-Guide is furthest ahead on issue health (96 to 70). Choose the dimension a rollout cannot compromise on.
CrewAI finishes ahead at 95.7 against Prompt-Engineering-Guide at 85.0, a 10.7 point clear margin under the published weights.
Scores are computed inside this pair only. Method and weights.
Bars are scaled within the row. Higher is stronger. Open issues are a raw count, so that row has no bar.
| Signal | CrewAI | Prompt-Engineering-Guide |
|---|---|---|
| GitHub stars | 61,027 | 80,149 |
| Forks | 9,211 | 8,790 |
| Open issues | 1,276 | 300 |
| Adoption | 98 | 100 |
| Activity | 100 | 36 |
| Community | 100 | 100 |
| Issue health | 70 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 95.7 | 85.0 |
CrewAI is a framework for multi-agent workflows where role-based agents delegate tasks. It is a code library first, used by teams building their own agent systems.
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
Prompt-Engineering-Guide has more GitHub stars: 80,149 versus 61,027 for CrewAI. The gap is 19,122 stars.
CrewAI was pushed more recently: 17 November 2026 versus 11 March 2026 for Prompt-Engineering-Guide. That is 250 days apart.
Yes. This catalog marks both CrewAI and Prompt-Engineering-Guide as self-hostable. Confirm each project's deploy docs before you plan a migration.
CrewAI is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Prompt-Engineering-Guide is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
CrewAI scores 95.7 and Prompt-Engineering-Guide scores 85.0. This page calls that a clear lead for CrewAI.