FareedKhan-dev/multi-agent-training-grpo

A multi-agent system trained with GRPO for reliable long-horizon task planning and execution.

by Fareed Khan Jupyter Notebook MIT licence 13 forks Created Feb 2026 View on GitHub

Stars
66
<1% of FareedKhan-dev's stars
Rank
#674,860
of 852,045 repos, top 80%
In Jupyter Notebook
#16,562
of 21,671 repos, top 77%

Among 852,045 repos

Compare with

63–100 stars: 217,624 repos, including multi-agent-training-grpo

Stars along the bottom, and repos in each band on a log scale

Quick stats

Next rank
+1 star to reach #666,981
Next milestone
+12 stars to reach the top 70%

Stars counted Recounted daily Next count around