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
82 repos
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
★ 0 davidbau/NetHackOfficial NetHack Git Repository
-
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
-
Unofficial personal Wear OS app and tile for UK ADT Smart Services, using a paired Android phone.
-
Official NetHack Git Repository
-
Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!
-
Official Python client library for the OpenReview API
-
Small reproducible problems for Sutro Group's energy-efficient learning research
-
Official CLI and Python SDK for Prime Intellect - access GPU compute, remote sandboxes, RL environments, and distributed training infrastructure for AI development at scale.
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
Open ABI and FFI for Machine Learning Systems
-
Highlight and capture the web in your favorite browser. The official Web Clipper extension for Obsidian.
-
TVM FFI
-
📺 Homebrew's official macOS GUI
-
Office Open XML client
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
DeepGEMM: clean and efficient BLAS kernel library on GPU
-
SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses
-
The official project website for Datasette
-
Python and Julia in harmony.
-
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
-
Official Implementation for WorldSculpt: Generating Compositional Worlds from Grounded Videos
-
Apache Iggy: Hyper-Efficient Message Streaming at Laser Speed
-
Enable AI agents to efficiently explore and edit source code, improving token efficiency, cost and speed.
-
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
-
Official Code Repository for the ICLR 2026 Paper "Human Behavior Atlas: Benchmarking Unified Psychological and Social Behavior Understanding" & ICML 2026 Paper "Omnisapiens: A foundation model for social behavior processing via heterogeneity-aware relative policy optimization"
-
Efficient optimizers
-
dInfer: An Efficient Inference Framework for Diffusion Language Models
-
Official OpenClaw DingTalk channel plugin | 钉钉官方 OpenClaw 插件
-
Unofficial source-oriented reconstruction and extension of Grok Bot 0.18.0 for macOS
-
[ECCV 2026] Official code for ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video
-
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
-
Official AMD catalog of AI agent skills. Empower your AI agents with AMD's optimized SW stack.
-
Bento, the office suite that fits in a file
-
Empowering everyone to host fast and efficient Minecraft servers
-
Puffing up reinforcement learning
-
AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He
-
The official CLI and Python client for the Hugging Face Hub.
-
Official code release for the ECCV 2026 paper 𝗧𝗲𝗮𝗰𝗵𝗶𝗻𝗴 𝗮𝗻 𝗔𝗴𝗲𝗻𝘁 𝘁𝗼 𝗦𝗸𝗲𝘁𝗰𝗵 𝗢𝗻𝗲 𝗣𝗮𝗿𝘁 𝗮𝘁 𝗮 𝗧𝗶𝗺𝗲 (arXiv:2603.19500)
-
Official repository of B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations.
-
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
-
Official implementation paper OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields
-
Offical repo for the paper "LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow"
-
★ 1 neubig/playbooksOfficial repository of AMD Playbooks
-
llama.cpp's official website
-
🚀 Efficient implementations for emerging model architectures
-
Run OpenClaw in Vercel Sandbox from its official image in Vercel Container Registry
-
Official implementation of ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation (SIGGRAPH 2026).
-
Official eval scripts for JobBench