Alternatives and similar repositories for RLFromScratch

Users that are interested in RLFromScratch are comparing it to the libraries listed below

• McGill-NLP / nano-aha-moment
  Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
  ☆593Updated 4 months ago
• changjonathanc / flex-nano-vllm
  FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
  ☆334Updated 3 months ago
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆286Updated 4 months ago
• facebookresearch / PhysicsLM4
  Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality
  ☆317Updated last month
• brendanhogan / DeepSeekRL-Extended
  Exploring Applications of GRPO
  ☆251Updated 5 months ago
• shangshang-wang / Tina
  [ICLR 2026] Tina: Tiny Reasoning Models via LoRA
  ☆319Updated 4 months ago
• wolfecameron / nanoMoE
  An extension of the nanoGPT repository for training small MOE models.
  ☆236Updated 11 months ago
• joey00072 / nanoGRPO
  nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)
  ☆143Updated 9 months ago
• huggingface / picotron_tutorial
  ☆232Updated 2 months ago
• thinking-machines-lab / batch_invariant_ops
  ☆961Updated 3 months ago
• ServiceNow / PipelineRL
  A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
  ☆362Updated this week
• axon-rl / gem
  A Gym for Agentic LLMs
  ☆444Updated 3 weeks ago
• JinjieNi / MegaDLMs
  GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 tr…
  ☆322Updated 3 months ago
• open-thought / tiny-grpo
  Minimal hackable GRPO implementation
  ☆323Updated last year
• aakaran / reasoning-with-sampling
  ☆388Updated 3 months ago
• fangyuan-ksgk / Tiny-GRPO
  minimal GRPO implementation from scratch
  ☆102Updated 10 months ago
• test-time-training / discover
  ☆394Updated 2 weeks ago
• test-time-training / e2e
  Official JAX implementation of End-to-End Test-Time Training for Long Context
  ☆520Updated 2 weeks ago
• meta-pytorch / torchforge
  PyTorch-native post-training at scale
  ☆613Updated this week
• marin-community / marin
  Open-source framework for the research and development of foundation models.
  ☆752Updated this week
• stanford-cs336 / assignment5-alignment
  ☆105Updated 6 months ago
• SakanaAI / DroPE
  Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding
  ☆203Updated last month
• open-tinker / OpenTinker
  OpenTinker is an RL-as-a-Service infrastructure for foundation models
  ☆625Updated 2 weeks ago
• JinjieNi / dlms-are-super-data-learners
  The official github repo for "Diffusion Language Models are Super Data Learners".
  ☆221Updated 3 months ago
• radixark / miles
  Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
  ☆858Updated this week
• NVlabs / GatedDeltaNet
  [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
  ☆452Updated 4 months ago
• thinking-machines-lab / tinker-project-ideas
  Ideas for projects related to Tinker
  ☆164Updated 3 months ago
• yihedeng9 / rlhf-summary-notes
  A brief and partial summary of RLHF algorithms.
  ☆144Updated 11 months ago
• NVlabs / RLP
  [ICLR 2026] Official PyTorch Implementation of RLP: Reinforcement as a Pretraining Objective
  ☆232Updated 2 weeks ago
• lmgame-org / GRL
  Multi-Turn RL Training System with AgentTrainer for Language Model Game Reinforcement Learning
  ☆59Updated last month