๐ŸŽฏ

openclaw-rl-training

๐ŸŽฏSkill

from aradotso/trending-skills

VibeIndex|
What it does
|

Fully asynchronous reinforcement-learning framework that turns live multi-turn conversations into training signal for personalized agents, wrapping a self-hosted model as an OpenAI-compatible API via OpenClaw and continuously optimizing the policy in the background. Runs four independent loops (serving, rollout collection, PRM/judge evaluation, GRPO/OPD training via slime or Tinker) that never block each other.

๐Ÿ“ฆ

Same repository

aradotso/trending-skills(256 items)

openclaw-rl-training

Installation

Vibe Index InstallInstalls to .claude/skills/ - auto-recognized by Claude Code
npx vibeindex add aradotso/trending-skills --skill openclaw-rl-training
skills.sh Installโš  Installs to .agents/skills/ - may not be auto-recognized by Claude Code
npx skills add aradotso/trending-skills --skill openclaw-rl-training
Manual InstallCopy SKILL.md content and save to the path below
~/.claude/skills/openclaw-rl-training/SKILL.md

SKILL.md

1,036Installs
-
AddedApr 13, 2026