CAMEL
π« CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
CAMEL scores 7.3/10 (Strong) in Agent Frameworks.
Language Python License Apache-2.0 Stars 17.3kβ
Type library Self-host Yes Repo camel-ai/camel Homepage https://www.camel-ai.org
Quality
Strong 7.3
Adoption 56
Activity 75
Maturity 97
Community 58
Capability 70
Show the math
Overall 7.3/10
value = 7.3/10
score = value
Adoption 6/10
value = 56/100
score = 1 + 9 * value / 100
Activity 7.8/10
value = 75/100
score = 1 + 9 * value / 100
Maturity 9.8/10
value = 97.4/100
score = 1 + 9 * value / 100
Community 6.2/10
value = 58.1/100
score = 1 + 9 * value / 100
Capability 7.3/10
value = 69.7/100
score = 1 + 9 * value / 100
Key metrics
17.3kβ
GitHub stars
85/90d Recent commits
30 devs/90d Recent contributors
GAIA 69.7% GAIA (open-source SOTA) CAMEL-AI's Workforce/OWL multi-agent system achieves 69.70% on the GAIA benchmark, reported as open-source state-of-the-art. Source: arXiv 2505.23885 (OWL: Optimized Workforce Learning), abstract: "Workforce achieves open-source state-of-the-art performance (69.70%)" on GAIA. https://arxiv.org/abs/2505.23885
3.3y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
python multi-agent role-playing simulation research