Alternatives and similar repositories for neural-os

Users that are interested in neural-os are comparing it to the libraries listed below

• sdan / vlm-gym
  RL gym for vision language models written in JAX
  ☆141Updated 2 months ago
• s-smits / grpo-optuna
  Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
  ☆59Updated 3 months ago
• ZihanWang314 / coeCheck
  ☆19Updated 10 months ago
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆175Updated last year
• GAIR-NLP / LIMI
  LIMI: Less is More for Agency
  ☆159Updated 3 months ago
• nahidalam / maya
  Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya
  ☆125Updated 5 months ago
• JoeLi12345 / nGPT
  an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)
  ☆109Updated 10 months ago
• facebookresearch / llm-speedrunner
  The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…
  ☆127Updated 3 months ago
• gkamradt / SnakeBench
  ☆99Updated last week
• collinear-ai / spider
  Streamline on-policy/off-policy distillation workflows in a few lines of code
  ☆91Updated this week
• google-deepmind / latent-multi-hop-reasoning
  [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?
  ☆88Updated 10 months ago
• huggingface / screensuite
  ScreenSuite - The most comprehensive benchmarking suite for GUI Agents!
  ☆135Updated 3 months ago
• microsoft / GRIN-MoE
  GRadient-INformed MoE
  ☆264Updated last year
• radi-cho / reasoning-diffusion
  ☆35Updated 10 months ago
• haizelabs / j1-micro
  j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.
  ☆101Updated 6 months ago
• StigLidu / DualDistill
  [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"
  ☆102Updated 4 months ago
• Tencent / Hunyuan-TurboS
  ☆88Updated 8 months ago
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated last year
• tiiuae / onebitllms
  Lightweight toolkit package to train and fine-tune 1.58bit Language models
  ☆107Updated 8 months ago
• exo-explore / gym
  EXO Gym is an open-source Python toolkit that facilitates distributed AI research.
  ☆93Updated last month
• SinatrasC / entropix
  Entropy Based Sampling and Parallel CoT Decoding
  ☆17Updated last year
• reka-ai / rekaquant
  ☆62Updated 6 months ago
• AK391 / dailypapersHN
  ☆87Updated last year
• impel-intelligence / dippy-bittensor-subnet
  ☆55Updated 4 months ago
• NousResearch / nomos
  ☆158Updated last month
• RWKV / ZeroCoT
  https://x.com/BlinkDL_AI/status/1884768989743882276
  ☆28Updated 8 months ago
• EduardTalianu / EntropixLab
  entropix style sampling + GUI
  ☆27Updated last year
• HarleyCoops / smolThinker-.5B
  A Qwen .5B reasoning model trained on OpenR1-Math-220k
  ☆14Updated 3 months ago
• microsoft / ArchScale
  Simple & Scalable Pretraining for Neural Architecture Research
  ☆306Updated last month
• KempnerInstitute / traveling-waves-integrate
  Repository to create traveling waves integrate special information through time
  ☆56Updated 5 months ago