NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
☆11,881Sep 21, 2026Updated this week
Alternatives and similar repositories for Cosmos
Users that are interested in Cosmos are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Simulation platform for general-purpose robotics & embodied AI learning.☆29,971Updated this week
- A suite of image and video neural tokenizers☆1,729Feb 11, 2025Updated last year
- ☆13,931Aug 24, 2026Updated 3 weeks ago
- Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals☆2,663Apr 19, 2026Updated 5 months ago
- NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.☆8,104Aug 20, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Our inference and training framework to run on the Cosmos Models☆536Updated this week
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆825Jun 7, 2026Updated 3 months ago
- SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer☆9,125Updated this week
- [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer☆14,421May 19, 2026Updated 4 months ago
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆4,669Mar 23, 2026Updated 5 months ago
- [RSS 2026] Causal video-action world model for generalist robot control☆1,906Jul 9, 2026Updated 2 months ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆1,371Jun 8, 2026Updated 3 months ago
- Open-source unified multimodal model☆6,179May 4, 2026Updated 4 months ago
- OpenVLA: An open-source vision-language-action model for robotic manipulation.☆7,060Mar 23, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning☆27,682Updated this week
- A unified inference and post-training framework for accelerated video generation.☆4,494Updated this week
- Advancing Open-source World Models☆4,475Jul 9, 2026Updated 2 months ago
- [IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems☆3,188May 29, 2026Updated 3 months ago
- Reference PyTorch implementation and models for DINOv3☆11,425Jul 15, 2026Updated 2 months ago
- code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"☆1,294Jul 6, 2026Updated 2 months ago
- Wan: Open and Advanced Large-Scale Video Generative Models☆17,019Mar 5, 2026Updated 6 months ago
- The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained mode…☆19,906May 30, 2026Updated 3 months ago
- [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control☆1,425Jun 15, 2026Updated 3 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ViPE: Video Pose Engine for Geometric 3D Perception☆2,122Sep 10, 2026Updated last week
- [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning☆2,172Jul 3, 2026Updated 2 months ago
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆793Oct 29, 2025Updated 10 months ago
- Official implementation of Continuous 3D Perception Model with Persistent State☆1,492Aug 27, 2025Updated last year
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆19,978Jan 30, 2026Updated 7 months ago
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆962Jun 7, 2026Updated 3 months ago
- Cosmos Policy☆874Jan 23, 2026Updated 7 months ago
- Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)☆3,517Sep 12, 2025Updated last year
- [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision☆2,962Sep 9, 2026Updated last week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Native Multimodal Models are World Learners☆1,556Dec 30, 2025Updated 8 months ago
- Depth Anything 3☆6,382Jul 27, 2026Updated last month
- Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?☆1,506Aug 20, 2026Updated last month
- RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning☆1,862Updated this week
- Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"☆1,386Jun 16, 2025Updated last year
- Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"☆2,019Feb 25, 2026Updated 6 months ago
- Unified framework for robot learning with multi-physics/renderer support☆8,187Updated this week