Alternatives and similar repositories for continuous-thought-machines

Users that are interested in continuous-thought-machines are comparing it to the libraries listed below

• seal-rg / recurrent-pretraining
  Pretraining code for a large-scale depth-recurrent language model
  ☆760Updated last month
• groundlight / r1_vlm
  Build your own visual reasoning model
  ☆362Updated this week
• HKUNLP / Dream
  Dream 7B, a large diffusion language model
  ☆630Updated 2 weeks ago
• SakanaAI / self-adaptive-llms
  A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!
  ☆1,058Updated 3 months ago
• lucidrains / titans-pytorch
  Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch
  ☆1,323Updated last month
• KellerJordan / Muon
  Muon optimizer: +>30% sample efficiency with <3% wallclock overhead
  ☆623Updated last month
• facebookresearch / memory
  Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…
  ☆327Updated 5 months ago
• McGill-NLP / nano-aha-moment
  Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
  ☆450Updated this week
• facebookresearch / jepa-intuitive-physics
  This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"
  ☆154Updated 2 months ago
• facebookresearch / coconut
  Training Large Language Model to Reason in a Continuous Latent Space
  ☆1,109Updated 3 months ago
• SakanaAI / evo-memory
  Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.
  ☆307Updated 6 months ago
• SakanaAI / asal
  Automating the Search for Artificial Life with Foundation Models!
  ☆410Updated 4 months ago
• NVlabs / hymba
  ☆177Updated 5 months ago
• facebookresearch / blt
  Code for BLT research paper
  ☆1,587Updated this week
• Haiyang-W / TokenFormer
  [ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
  ☆555Updated 3 months ago
• open-thought / reasoning-gym
  procedural reasoning datasets
  ☆580Updated this week
• sail-sg / understand-r1-zero
  Understanding R1-Zero-Like Training: A Critical Perspective
  ☆925Updated last month
• ekinakyurek / marc
  Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"
  ☆307Updated 5 months ago
• MoonshotAI / Moonlight
  Muon is Scalable for LLM Training
  ☆1,044Updated last month
• kuleshov-group / bd3lms
  Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
  ☆595Updated last month
• KindXiaoming / grow-crystals
  Getting crystal-like representations with harmonic loss
  ☆183Updated last month
• policy-gradient / GRPO-Zero
  Implementing DeepSeek R1's GRPO algorithm from scratch
  ☆1,328Updated 3 weeks ago
• wbrickner / noise_step
  noise_step: Training in 1.58b With No Gradient Memory
  ☆219Updated 4 months ago
• qixucen / atom
  Atom of Thoughts for Markov LLM Test-Time Scaling
  ☆563Updated this week
• PrimeIntellect-ai / prime
  prime is a framework for efficient, globally distributed training of AI models over the internet.
  ☆743Updated last week
• ML-GSAI / LLaDA
  Official PyTorch implementation for "Large Language Diffusion Models"
  ☆1,592Updated last week
• huggingface / search-and-learn
  Recipes to scale inference-time compute of open models
  ☆1,071Updated last week
• microsoft / Samba
  [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
  ☆871Updated 2 weeks ago
• open-thought / system-2-research
  System 2 Reasoning Link Collection
  ☆833Updated 2 months ago
• PrimeIntellect-ai / prime-rl
  prime-rl is a codebase for decentralized RL training at scale
  ☆211Updated this week