Rank of 2722
Known for
Splitting a task across specialised agents when one agent with many tools stops coping.
A multi-agent framework out of the CAMEL research line, built around role-specialised agents dividing a task. One of the few in this field with published benchmark standing rather than only a demo.
22.8index score · Open Source
Stars
27.8 ×0.25
Forks
31.5 ×0.33
Activity
13.0 ×0.42
Factors are percentiles within the 27-entry ranked cohort. Weights are renormalised across the factors that have data.