Alternatives and similar repositories for Cosmos

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

• 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…
  ☆3,644Updated 3 weeks ago
• NVIDIA / Cosmos-Tokenizer
  A suite of image and video neural tokenizers
  ☆1,679Updated 9 months ago
• manycore-research / SpatialLM
  [NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling
  ☆4,080Updated last month
• openvla / openvla
  OpenVLA: An open-source vision-language-action model for robotic manipulation.
  ☆4,415Updated 7 months ago
• facebookresearch / vjepa2
  PyTorch code and models for VJEPA2 self-supervised learning from video.
  ☆2,399Updated 2 months ago
• microsoft / Magma
  [CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents
  ☆1,844Updated last month
• Physical-Intelligence / openpi
  ☆8,700Updated 3 weeks ago
• ByteDance-Seed / Bagel
  Open-source unified multimodal model
  ☆5,282Updated 2 weeks ago
• Genesis-Embodied-AI / Genesis
  A generative world for general-purpose robotics & embodied AI learning.
  ☆27,568Updated last week
• NVIDIA / Isaac-GR00T
  NVIDIA Isaac GR00T N1.5 - A Foundation Model for Generalist Robots.
  ☆5,322Updated last week
• SandAI-org / MAGI-1
  MAGI-1: Autoregressive Video Generation at Scale
  ☆3,534Updated 4 months ago
• deepseek-ai / Janus
  Janus-Series: Unified Multimodal Understanding and Generation Models
  ☆17,608Updated 9 months ago
• StarsfieldAI / R1-V
  Witness the aha moment of VLM with less than $3.
  ☆3,980Updated 5 months ago
• huggingface / nanoVLM
  The simplest, fastest repository for training/finetuning small-sized VLMs.
  ☆4,229Updated 2 weeks ago
• Jiayi-Pan / TinyZero
  Minimal reproduction of DeepSeek R1-Zero
  ☆12,383Updated 6 months ago
• NVlabs / Sana
  SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
  ☆4,689Updated last week
• huggingface / lerobot
  🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
  ☆19,188Updated last week
• QwenLM / Qwen3-VL
  Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
  ☆16,124Updated 2 weeks ago
• apple / ml-depth-pro
  Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.
  ☆4,975Updated 6 months ago
• facebookresearch / dinov3
  Reference PyTorch implementation and models for DINOv3
  ☆8,214Updated last week
• MoonshotAI / Kimi-k1.5
  ☆3,468Updated 8 months ago
• OpenDriveLab / AgiBot-World
  [IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
  ☆2,596Updated 2 weeks ago
• huggingface / open-r1
  Fully open reproduction of DeepSeek-R1
  ☆25,629Updated 2 months ago
• MiniMax-AI / MiniMax-01
  The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention
  ☆3,236Updated 4 months ago
• Tencent-Hunyuan / HunyuanVideo
  HunyuanVideo: A Systematic Framework For Large Video Generation Model
  ☆11,254Updated 2 months ago
• stepfun-ai / Step-Video-T2V
  ☆3,129Updated 7 months ago
• QwenLM / Qwen2.5-Omni
  Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and pe…
  ☆3,770Updated 5 months ago
• facebookresearch / sapiens
  High-resolution models for human tasks.
  ☆5,207Updated 11 months ago
• eloialonso / diamond
  DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 S…
  ☆1,891Updated 11 months ago
• facebookresearch / jepa
  PyTorch code and models for V-JEPA self-supervised learning from video.
  ☆3,270Updated 8 months ago