NVIDIA/cosmos-framework
Our inference and training framework to run on the Cosmos Models
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.
The project lists 54 contributors on GitHub.
Use Cases & Benefits
- Provides an end-to-end Python framework for training and serving NVIDIA Cosmos world models including the Cosmos3 model family.
- Enables unified multi-modal model training and inference with distributed parallelism and flexible input-output configurations.
- Use for training large-scale multi-modal AI models with distributed GPU parallelism and mixed precision.
- Use for running inference on omnimodal models supporting language, images, video, audio, and actions with various backend integrations.
- Use for deploying policy servers and agent skills to enable interactive AI agents and task-specific automation workflows.
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
- Contributing guide: present
Watch-outs
- License not identified by GitHub; read the LICENSE file before depending on it.
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
Cosmos 3 is our newest model family [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. For a guided experience to test out Cosmos3, please visit [Cosmos].
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
187+89
Open issues
47+28
Compared with peers in Machine Learning
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| photoprism/photoprism | 40.4K | — | 65 | 1 day ago |
| huggingface/diffusers | 34.8K | — | 65 | 3 days ago |
| onnx/onnx | 21.6K | — | 63 | 31 days ago |
| lukas-blecher/LaTeX-OCR | 16.6K | — | 18 | — |
| milesial/Pytorch-UNet | 11.7K | — | 18 | — |
| NVIDIA/cosmos-framework | 588 | — | 40 | — |
| Category median | 21.6K | — | 63 | — |
Also by NVIDIA
Other repositories from this maintainer that GStars tracks
- Python24.5K 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.
- TypeScript22.8K stars
NemoClaw
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
- Rust21.2K stars
OpenShell
OpenShell is the safe, private runtime for autonomous AI agents.
- Python18.3K stars
Megatron-LM
Ongoing research training transformer models at scale
- Python15.0K 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