caveman vs OpenRLHF

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

cavemanOpenRLHF
TaglineCuts 65% of tokens in AI coding agent responses.An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray
Stars86k9.8k
Forks4.8k981
Open issues370342
LanguageJavaScriptPython
LicenseMITApache-2.0
Last pushedJul 3, 2026Jul 6, 2026
CategoriesLLM Frameworks, Developer ToolsModel Training, Developer 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

OpenRLHF

OpenRLHF is an open-source framework for reinforcement learning from human feedback. It combines Ray and vLLM distributed architecture with a unified agent-based design paradigm, offering high performance and scalability.

Python