← 트렌딩

Tangerine Index는 ChatGPT 이후 나온 프로덕트와 사람들의 반응을 싣습니다.

axrl

github.com

AxisRL is an agentic RL post-training framework built on SGLang rollout, Megatron training, and real-world agent workflows.

라이브러리오픈소스

github.com 방문외부 사이트GitHub612 스타외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. AgileRL

    The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.

    GitHub스타 966github.com오픈소스최근 반응

  2. OpenRLHF

    An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

    GitHub스타 10,146github.com라이브러리오픈소스최근 반응

  3. ToolOrchestra

    ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.

    GitHub스타 771github.com라이브러리오픈소스최근 반응

  4. verl

    verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

    GitHub스타 24,174github.com라이브러리오픈소스최근 반응

  5. RunRL (YC X25)

    Reinforcement learning as a service

    Hacker News71점runrl.com최근 반응