Alternatives and similar repositories for Cosmos

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

• manycore-research / SpatialLM
  SpatialLM: Training Large Language Models for Structured Indoor Modeling
  ☆3,352Updated last week
• QwenLM / Qwen2.5-VL
  Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
  ☆11,094Updated last month
• Wan-Video / Wan2.1
  Wan: Open and Advanced Large-Scale Video Generative Models
  ☆12,263Updated last week
• Physical-Intelligence / openpi
  ☆3,660Updated this week
• Genesis-Embodied-AI / Genesis
  A generative world for general-purpose robotics & embodied AI learning.
  ☆25,315Updated this week
• NVIDIA / Cosmos-Tokenizer
  A suite of image and video neural tokenizers
  ☆1,638Updated 4 months ago
• MoonshotAI / Kimi-k1.5
  ☆3,363Updated 3 months ago
• NVIDIA / Isaac-GR00T
  NVIDIA Isaac GR00T N1.5 is the world's first open foundation model for generalized humanoid robot reasoning and skills.
  ☆4,174Updated last week
• openvla / openvla
  OpenVLA: An open-source vision-language-action model for robotic manipulation.
  ☆3,077Updated 2 months ago
• OpenDriveLab / AgiBot-World
  The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
  ☆2,115Updated this week
• Lightricks / LTX-Video
  Official repository for LTX-Video
  ☆6,745Updated 3 weeks ago
• ByteDance-Seed / Bagel
  Open-source unified multimodal model
  ☆4,204Updated this week
• huggingface / lerobot
  🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
  ☆15,086Updated this week
• microsoft / Magma
  [CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents
  ☆1,712Updated 3 weeks ago
• yangchris11 / samurai
  Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
  ☆6,846Updated 3 months ago
• facebookresearch / vjepa2
  PyTorch code and models for VJEPA2 self-supervised learning from video.
  ☆1,331Updated this week
• NVlabs / Sana
  SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
  ☆4,279Updated 2 weeks ago
• microsoft / TRELLIS
  Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
  ☆9,828Updated 3 weeks ago
• NVlabs / VILA
  VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and clou…
  ☆3,344Updated this week
• huggingface / nanoVLM
  The simplest, fastest repository for training/finetuning small-sized VLMs.
  ☆3,418Updated this week
• Saiyan-World / goku
  [CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/
  ☆2,853Updated 4 months ago
• deepseek-ai / Janus
  Janus-Series: Unified Multimodal Understanding and Generation Models
  ☆17,380Updated 4 months ago
• simplescaling / s1
  s1: Simple test-time scaling
  ☆6,447Updated last month
• oumi-ai / oumi
  Easily fine-tune, evaluate and deploy Qwen3, DeepSeek-R1, Llama 4 or any open source LLM / VLM!
  ☆8,187Updated this week
• Jiayi-Pan / TinyZero
  Minimal reproduction of DeepSeek R1-Zero
  ☆11,909Updated last month
• test-time-training / ttt-video-dit
  Official PyTorch implementation of One-Minute Video Generation with Test-Time Training
  ☆1,620Updated 2 weeks ago
• stepfun-ai / Step-Video-T2V
  ☆3,025Updated 3 months ago
• isaac-sim / IsaacLab
  Unified framework for robot learning built on NVIDIA Isaac Sim
  ☆3,929Updated this week
• Deep-Agent / R1-V
  Witness the aha moment of VLM with less than $3.
  ☆3,768Updated last month
• gradio-app / fastrtc
  The python library for real-time communication
  ☆4,037Updated last week