A · leads
anything-llm
97.7
68,366 stars · MIT
AI Agents
anything-llm leads by 1.5 · narrow
A · leads
97.7
68,366 stars · MIT
B
96.2
61,027 stars · MIT
anything-llm versus CrewAI is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. anything-llm is written mainly in JavaScript; CrewAI is written mainly in Python. The composite score is 97.7 for anything-llm and 96.2 for CrewAI.
anything-llm has 68,366 GitHub stars to CrewAI's 61,027, a gap of 7,339 (1.12×). Forks are 7,723 for anything-llm and 9,211 for CrewAI. On the log scale used inside this pair, adoption is 100 versus 99, and the fork community is 98 versus 100.
Push history: anything-llm was last pushed on 17 November 2026 (0 days ago), and CrewAI was last pushed on 17 November 2026 (0 days ago). Open issues stand at 358 for anything-llm (0.005 per star) and 1,276 for CrewAI (0.021 per star). Issue-health scores are 84 and 70; activity scores are 100 and 100.
Both anything-llm and CrewAI 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 anything-llm (68,366 stars) and CrewAI (61,027 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: anything-llm is open source, CrewAI is open source.
The lead is split. anything-llm is furthest ahead on issue health (84 to 70), while CrewAI is furthest ahead on fork community (100 to 98). Choose the dimension a rollout cannot compromise on.
anything-llm finishes ahead at 97.7 against CrewAI at 96.2, a 1.5 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 | anything-llm | CrewAI |
|---|---|---|
| GitHub stars | 68,366 | 61,027 |
| Forks | 7,723 | 9,211 |
| Open issues | 358 | 1,276 |
| Adoption | 100 | 99 |
| Activity | 100 | 100 |
| Community | 98 | 100 |
| Issue health | 84 | 70 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.7 | 96.2 |
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
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.
anything-llm has more GitHub stars: 68,366 versus 61,027 for CrewAI. The gap is 7,339 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both anything-llm and CrewAI as self-hostable. Confirm each project's deploy docs before you plan a migration.
anything-llm 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. 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. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
anything-llm scores 97.7 and CrewAI scores 96.2. This page calls that a narrow lead for anything-llm.