Python · Apache-2.0
redai-studio/Relax
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
★ 668
Stars
192 forks · 128 open issues
+1.0/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
28.8
Momentum / 100
see the breakdown below
6mo ago
Created
last push 4d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 5.8 | +1.0/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.96× the monthly pace |
| Freshness | 15 | 14.8 | last push 4d ago; decays to zero at 180 days |
| Scale | 15 | 8.2 | 668 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 28.8 | sum of the above |
Detail
| Topics | agentic-rldistributed-traininggrpomulti-agentmultimodalpost-trainingray-servereinforcement-learningrlhf |
| Matched on | AI Agents (multi-agent) |
| Short window | +7 stars over 7 days = 1.0/day |
| Long window | +27 stars over 26 days = 1.0/day |
| Lifetime average | 3.24 stars/day over 206 days |
| First seen here | 2026-10-11 |
| Last read | 4d ago |