A
CrewAI
95.1
61,027 stars · MIT
AI Agents
deer-flow leads by 2.8 · narrow
A
95.1
61,027 stars · MIT
B · leads
97.9
85,441 stars · MIT
CrewAI versus deer-flow is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. Both projects are written mainly in Python. The composite score is 95.1 for CrewAI and 97.9 for deer-flow.
deer-flow has 85,441 GitHub stars to CrewAI's 61,027, a gap of 24,414 (1.40×). Forks are 9,211 for CrewAI and 12,046 for deer-flow. On the log scale used inside this pair, adoption is 97 versus 100, and the fork community is 97 versus 100.
Push history: CrewAI was last pushed on 17 November 2026 (0 days ago), and deer-flow was last pushed on 17 November 2026 (0 days ago). Open issues stand at 1,276 for CrewAI (0.021 per star) and 1,117 for deer-flow (0.013 per star). Issue-health scores are 70 and 84; activity scores are 100 and 100.
Both CrewAI and deer-flow 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 deer-flow (85,441 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, deer-flow is open source.
deer-flow is ahead on every scored dimension that is not level. Level dimensions: recent activity, license flexibility, self-hosting. The widest gap is issue health at 14 points (70 vs 84), and the tightest is self-hosting at 0 points (100 vs 100).
deer-flow finishes ahead at 97.9 against CrewAI at 95.1, a 2.8 point narrow 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 | deer-flow |
|---|---|---|
| GitHub stars | 61,027 | 85,441 |
| Forks | 9,211 | 12,046 |
| Open issues | 1,276 | 1,117 |
| Adoption | 97 | 100 |
| Activity | 100 | 100 |
| Community | 97 | 100 |
| Issue health | 70 | 84 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 95.1 | 97.9 |
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.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
deer-flow has more GitHub stars: 85,441 versus 61,027 for CrewAI. The gap is 24,414 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both CrewAI and deer-flow 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. deer-flow 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.
deer-flow scores 97.9 and CrewAI scores 95.1. This page calls that a narrow lead for deer-flow.