axrl
AxisRL is an agentic RL post-training framework built on SGLang rollout, Megatron training, and real-world agent workflows.
XYZ-AI-Lab/axrl
View on GitHub ↗AxisRL is an agentic RL post-training framework built on SGLang rollout, Megatron training, and real-world agent workflows.
axrl grew -37.6% in the last 30 days, ranks 23rd of 82 in Reinforcement Learning / RLHF, last commit 80 days ago.
Star trajectory
86 days tracked2026-07-29612 stars today2026-10-23
Momentum
-37.6% in 30d, below the Reinforcement Learning / RLHF median of +1.1%.
Maintenance
Last commit 80 days ago, staler than the median of 44d.
How it compares in Reinforcement Learning / RLHF
axrl
612
stars
-37.6% 30d
commit 80 days ago
Reinforcement Learning / RLHF median
306
stars
+1.1% 30d
commit ~44d ago
Leader · OpenRLHF
10.1k
stars
+0.7% 30d
commit 17 days ago
Ranked 23rd of 82 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 2
- Forks
- 16
- Watchers
- 8
- Open issues
- 0
- Releases
- 0
- Created
- 2026-07-23
- Stars this week
- +0
You've seen where axrl stands today.
Get the moves before everyone else: the 5 Reinforcement Learning / RLHF repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.