PHART: Python Hierarchical ASCII Rendering Tool - A Pure Python library and console CLI tool that renders graphs (NetworkX, GraphML, GraphViz/DOT) as diagrams/charts using 7-bit ASCII, (or 8-bit, U…

Polymathic's Large Omnimodal Model for Astronomy

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

Specification and documentation for Agent Skills

Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark

A deep learning framework for molecular docking

2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.

The open source coding agent.

OpenShell is the safe, private runtime for autonomous AI agents.

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Run Anything

Code for "SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes", ICML 2026 Spotlight

A Collection of Papers about Memory for Language Agents

Collect some related resources of NVIDIA Isaac Sim

Codebase for Kinova Gen3 training in Isaac Lab, sim2real transfer and ROS deployment.

Isaac Sim ROS Workspaces

A high performance general purpose code execution engine.

Build, run, and manage agent platforms.

The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.

SwinGNN: diffusion model for graph generation

Benchmarking Knowledge Transfer in Lifelong Robot Learning

Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you alre…

[CoRL '23] Dexterous piano playing with deep reinforcement learning.

[CoRL '23] Dexterous piano playing with deep reinforcement learning.

TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.