caveman vs awesome-RLHF

A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.

cavemanawesome-RLHF
TaglineCuts 65% of tokens in AI coding agent responses.A curated list of reinforcement learning with human feedback resources
Stars86k4.4k
Forks4.8k254
Open issues3704
LanguageJavaScript-
LicenseMITApache-2.0
Last pushedJul 3, 2026May 20, 2026
CategoriesDeveloper Tools, LLM FrameworksDeveloper Tools

caveman

A skill/plugin for various AI agents, including Claude Code and other platforms, reducing output tokens for more concise, direct communication while maintaining accuracy.

JavaScript

awesome-RLHF

Repository containing research papers, codebases, datasets, and blogs related to Reinforcement Learning with Human Feedback (RLHF). It covers advancements in RLHF with an emphasis on large language models and video games.