Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
2,235
repos tracked
175
surfaced this week
194
created < 30d
Python
top language
23 repos
-
Open Source Continuous Inference Benchmark Research Platform — Kimi K3 2.8T, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3 | 开源持续推理基准研究平台 — Kimi K2.7-Code、MiniMax M3、DeepSeekv4、GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72，即将推出™ TPUv6e/v7/Trainium2/3
-
the LLM vulnerability scanner
-
FlashInfer: Kernel Library for LLM Serving
-
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
-
NVSentinel detects and remediates GPU faults on Kubernetes nodes
-
NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the effective training time by minimizing the downtime due to failures and interruptions.
-
GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.
-
Communication patterns for AI, built on top of NCCL device and host APIs
-
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
-
Apple Silicon (Metal) backend for Triton: write standard @triton.jit kernels on your Mac GPU. The same source runs bit-identical on NVIDIA and AMD, so you develop kernel logic locally and rent a datacenter GPU only for the perf pass.
-
An agentic-first RL framework for research (9k lines).
-
A Python DSL to write Nvidia PTX for Hopper and Blackwell in JAX and PyTorch
-
Scalable toolkit for efficient model reinforcement
-
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
-
Working recipe to serve DeepSeek-V4-Flash across two NVIDIA DGX Spark (GB10) nodes with vLLM (TP=2, FP8 KV, MTP) over a RoCE/RDMA link — Docker image, launch scripts, RDMA/NCCL setup, and the gotchas.
-
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.
-
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
-
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
-
Port of Nvidia LocateAnything-3B on ggml
-
NVIDIA FastGen: Fast Generation from Diffusion Models
-
NVIDIA Cosmos-Dreams (fka NVIDIA OmniDreams) is a world model that generates photorealistic video for autonomous-driving simulation in real time.
-
high-performance inference and serving library for interactive autoregressive video and world models