NVIDIA/cosmos
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.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #558 of 2,794 repositories GStars tracks this week (top 20%).
No releases in the last 90 days; the most recent was 142 days ago, with 49 contributors on GitHub.
Use Cases & Benefits
- Enables building Physical AI by providing an open platform of world models, datasets, and tools for multimodal understanding and generation.
- Unifies language, vision, audio, video, and action modalities in a single Mixture-of-Transformers architecture for seamless multimodal reasoning and generation.
- Use for developing autonomous vehicle perception and decision-making systems with integrated world understanding and action prediction.
- Use for generating synthetic training data including images, videos, and sound to train and simulate robotic manipulation tasks.
- Use for creating embodied agent reasoning and task planning applications that require physical plausibility and next-action forecasting.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Other
GitHub could not identify this license; read the LICENSE file before depending on it.
Community files
- README: present
Watch-outs
- License not identified by GitHub; read the LICENSE file before depending on it.
General guidance from repository metadata, not legal advice. How we score
From the README
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.
Cosmos 3 is our newest model family [Models] [Report] [Website]. It is a suite of omnimodal world models designed to jointly process and generate language, images, video, audio, and action sequences within a unified Mixture-of-Transformers architecture. By supporting highly flexible input-output configurations, it seamlessly unifies critical modalities for Physical AI — effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
924+135
Open issues
68+38
Also by NVIDIA
Other repositories from this maintainer that GStars tracks
- TypeScript22.7K stars
NemoClaw
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
- Python20.5K stars
SkillSpector
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
- Python18.1K stars
Megatron-LM
Ongoing research training transformer models at scale
- Rust17.8K stars
OpenShell
OpenShell is the safe, private runtime for autonomous AI agents.
- Python14.9K stars
TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
Discover Repositories
Search across tracked repositories by name or description