GitHub repo leaderboard by stars, growth rate and activity.

• NVIDIA

  #1NVIDIA/NemoClaw

  Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

  TypeScript22,424 starslast pushed 22 hours ago
• seerge

  #2seerge/g-helper

  Lightweight Armoury Crate alternative for Asus laptops with nearly the same functionality. Works with ROG Zephyrus, Flow, TUF, Strix, Scar, ProArt, Vivobook, Zenbook, Expertbook, ROG Ally, and more.

  C#15,101 starslast pushed 2 days ago
• OpenWhispr

  #3OpenWhispr/openwhispr

  Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

  JavaScript7,940 starslast pushed Yesterday
• NVIDIA-NeMo

  #4NVIDIA-NeMo/Guardrails

  NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

  Python7,096 starslast pushed Yesterday
• flashinfer-ai

  #5flashinfer-ai/flashinfer

  FlashInfer: Kernel Library for LLM Serving

  Cuda6,363 starslast pushed 23 hours ago
• Osmantic

  #6Osmantic/ODS

  Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.

  Python6,346 starslast pushed 23 hours ago
• Project-HAMi

  #7Project-HAMi/HAMi

  Heterogeneous GPU Sharing on Kubernetes

  Go4,567 starslast pushed 23 hours ago
• NVIDIA

  #8NVIDIA/cccl

  CUDA Core Compute Libraries

  C++2,510 starslast pushed 23 hours ago
• NVIDIA-NeMo

  #9NVIDIA-NeMo/DataDesigner

  🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

  Python2,206 starslast pushed Yesterday
• selkies-project

  #10selkies-project/selkies

  Low-Latency Accelerated Web Remote Desktop Streaming Platform for Self-Hosting, Containers, Kubernetes, or Cloud/HPC

  Python2,128 starslast pushed 22 hours ago

#	Repo	Language	Stars	30-day trend	Last updated
1	NVIDIA NVIDIA/NemoClaw Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference	TypeScript	22,424		last pushed 22 hours ago
2	seerge seerge/g-helper Lightweight Armoury Crate alternative for Asus laptops with nearly the same functionality. Works with ROG Zephyrus, Flow, TUF, Strix, Scar, ProArt, Vivobook, Zenbook, Expertbook, ROG Ally, and more.	C#	15,101		last pushed 2 days ago
3	OpenWhispr OpenWhispr/openwhispr Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.	JavaScript	7,940		last pushed Yesterday
4	NVIDIA-NeMo NVIDIA-NeMo/Guardrails NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.	Python	7,096		last pushed Yesterday
5	flashinfer-ai flashinfer-ai/flashinfer FlashInfer: Kernel Library for LLM Serving	Cuda	6,363		last pushed 23 hours ago
6	Osmantic Osmantic/ODS Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.	Python	6,346		last pushed 23 hours ago
7	Project-HAMi Project-HAMi/HAMi Heterogeneous GPU Sharing on Kubernetes	Go	4,567		last pushed 23 hours ago
8	NVIDIA NVIDIA/cccl CUDA Core Compute Libraries	C++	2,510		last pushed 23 hours ago
9	NVIDIA-NeMo NVIDIA-NeMo/DataDesigner 🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.	Python	2,206		last pushed Yesterday
10	selkies-project selkies-project/selkies Low-Latency Accelerated Web Remote Desktop Streaming Platform for Self-Hosting, Containers, Kubernetes, or Cloud/HPC	Python	2,128	—	last pushed 22 hours ago

All · 11,474