RLHF Alignment Training LLM Tools

Tools and implementations for Reinforcement Learning from Human Feedback (RLHF), including reward modeling, policy optimization, and techniques for aligning LLMs with human preferences. Does NOT include general fine-tuning, inference optimization, or non-RLHF alignment methods.

There are 33 rlhf alignment training tools tracked. 1 score above 70 (verified tier). The highest-rated is hud-evals/hud-python at 78/100 with 316 stars and 355,753 monthly downloads. 1 of the top 10 are actively maintained.

Get all 33 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=llm-tools&subcategory=rlhf-alignment-training&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	hud-evals/hud-python OSS RL environment + evals toolkit	78	Verified	316	Python
2	hiyouga/EasyR1 EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL	61	Established	4,721	Python
3	OpenRL-Lab/openrl Unified Reinforcement Learning Framework	58	Established	822	Python
4	sail-sg/oat 🌾 OAT: A research-friendly framework for LLM online alignment, including...	53	Established	638	Python
5	opendilab/awesome-RLHF A curated list of reinforcement learning with human feedback resources...	50	Established	4,325	—
6	NVlabs/GDPO Official implementation of GDPO: Group reward-Decoupled Normalization Policy...	46	Emerging	413	Python
7	xrsrke/instructGOOSE Implementation of Reinforcement Learning from Human Feedback (RLHF)	41	Emerging	174	Jupyter Notebook
8	haoliuhl/chain-of-hindsight Simple next-token-prediction for RLHF	39	Emerging	229	Python
9	BaohaoLiao/SAGE Self-Hinting Language Models Enhance Reinforcement Learning	38	Emerging	24	Python
10	NJUNLP/GRRM A novel Group Relative Reward Model (GRRM) framework enhances machine...	35	Emerging	5	Python
11	LunjunZhang/ema-pg Code for "EMA Policy Gradient: Taming Reinforcement Learning for LLMs with...	31	Emerging	8	Python
12	WisdomShell/RewardAnything RewardAnything: Generalizable Principle-Following Reward Models	30	Emerging	45	Python
13	arunprsh/ChatGPT-Decoded-GPT2-FAQ-Bot-RLHF-PPO A Practical Guide to Developing a Reliable FAQ Chatbot with Reinforcement...	29	Experimental	14	Jupyter Notebook
14	Jayluci4/micro-rlhf RLHF in ~150 lines - understand how ChatGPT is aligned by building from scratch	28	Experimental	1	Python
15	AlignGPT-VL/AlignGPT Official repo for "AlignGPT: Multi-modal Large Language Models with Adaptive...	27	Experimental	34	Python
16	SagnikMukherjee/sparsity_in_rl Reinforcement Learning Finetunes Small Subnetworks in Large Language Models	27	Experimental	12	Python
17	GAIR-NLP/ReAlign Reformatted Alignment	26	Experimental	111	JavaScript
18	hggzjx/RewardAuditor Official Repo for Paper: "Reward Auditor: Inference on Reward Modeling...	26	Experimental	31	Python
19	Zh1yuShen/MemBuilder Code of "MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via...	26	Experimental	7	Python
20	zafstojano/policy-gradients A minimal hackable implementation of policy gradient methods (GRPO, PPO, REINFORCE)	24	Experimental	13	Python
21	anaezquerro/incpar Fully Incremental Neural Dependency and Constituency Parsing	23	Experimental	6	Python
22	ALucek/rl-for-llms Context & Guide For Reinforcement Learning with Verifiable Rewards with...	23	Experimental	12	Jupyter Notebook
23	GatlenCulp/embedding_translation Alignment across Deep Neural Network Language Models’ Representations	23	Experimental	1	HTML
24	nielsyA/Tree-GRPO 🌳 Enhance LLM agent performance with Tree-GRPO, leveraging tree search...	22	Experimental	—	Python
25	hc495/StaICC A standardized toolkit for classification task on In-context Learning....	22	Experimental	2	Python
26	rosinality/meshfn Framework for Human Alignment Learning	22	Experimental	7	Python
27	sailik1991/deal Decoding Time Alignment Search	19	Experimental	—	Python
28	herbitovich/ai-alignment Implementing the REINFORCE algorithm in the process of RLHF for LM alignment.	19	Experimental	—	Jupyter Notebook
29	psunlpgroup/FoVer This repository includes code and materials for the paper "Generalizable...	16	Experimental	11	Python
30	ikun-llm/ikun-GRPO 强化学习对齐 \| Group Relative Policy Optimization 🎮	14	Experimental	—	—
31	lgalke/easy2deeplearn Code for the paper "Deep neural networks and humans both benefit from...	13	Experimental	6	Python
32	safouaneelg/SRT2I Class-Conditional self-reward mechanism for improved Text-to-Image models	13	Experimental	7	Jupyter Notebook
33	aditi-bhaskar/multiturn-20q Multiturn RLHF applied to the 20 questions game through proxy rewards to...	11	Experimental	—	Jupyter Notebook