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.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
121 repos
-
The official TypeScript SDK for the SpaceXAI API
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
Open ABI and FFI for Machine Learning Systems
-
The official Unity plugin for Sprite Fusion
-
The official Godot plugin for Sprite Fusion
-
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
-
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)
-
Gaussian processes framework in python
-
Local-first lab for testing AI agent workflows end to end: emulated Slack (signed events, buttons), local S3/SQS, deterministic authorization, and independent evidence instead of self-grading. Optional Google AX (Agent Executor) + Agent Substrate lane on GKE/gVisor, reported per assertion. Independent; not affiliated with Google.
-
llama.cpp's official website
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
Small reproducible problems for Sutro Group's energy-efficient learning research
-
Official repository for BrickWright, a framework that enables LLM agents to create physically feasible LEGO® builds from text or image prompts.
-
We're rebuilding and open-sourcing the world’s software from scratch.
-
DeepEP: an efficient expert-parallel communication library
-
Official implementation of MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives (SIGGRAPH 2026)
-
TVM FFI
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
Manage your employees easily with a robust and efficient Human Resource Management System
-
Collection of jupyter notebooks for demonstrating software.
-
Official CLI and Python SDK for Prime Intellect - access GPU compute, remote sandboxes, RL environments, and distributed training infrastructure for AI development at scale.
-
Share to Spacesheep (Unofficial) — Third-party Android share-target app and macOS CLI companion for spacesheep.dev
-
GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.
-
Official Code for "Video Diffusion Avatars: Taming Video Diffusion Models into Controllable 3D Avatars"
-
Official Python client library for the OpenReview API
-
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
-
Official, Anthropic-managed directory of high quality Claude Code Plugins.
-
Highlight and capture the web in your favorite browser. The official Web Clipper extension for Obsidian.
-
Python and Julia in harmony.
-
A Difficulty-Calibrated Benchmark for Building Terminal Agents
-
Official implementation of "Correction Training for Diffusion Models"
-
☤ The official plugins for Hermes Agent, built and maintained by Nous Research: Home Assistant, Spotify, Claude Subscription DirectSDK and more, one install away from the Hermes plugin catalog.
-
Moved to NousResearch/hermes-official-plugins/spotify, the home of Nous Research's official Hermes Agent plugins.
-
Moved to NousResearch/hermes-official-plugins/homeassistant, the home of Nous Research's official Hermes Agent plugins.
-
Moved to NousResearch/hermes-official-plugins/claude-subscription-directsdk, the home of Nous Research's official Hermes Agent plugins.
-
☤ The official plugins for Hermes Agent, built and maintained by Nous Research: Home Assistant, Spotify, Claude Subscription DirectSDK and more, one install away from the Hermes plugin catalog.
-
MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents. Accepted at ICLR 2026; Best Paper Award at the NeurIPS 2025 MTI-LLM Workshop.
-
Code and data for ICMI-010: Moral Compactness — Scripture as a Kolmogorov-Efficient Constraint for LLM Scheming
-
Official code for the SEAR benchmark
-
Moved to NousResearch/hermes-official-plugins/blender
-
Official NetHack Git Repository
-
llama.cpp's official website
-
An unofficial packaging of the J programming language
-
Official implementation of FlowHMR, a generative model for physically plausible motion capture from monocular video.
-
Office Open XML client
-
The official CLI and Python client for the Hugging Face Hub.
-
Official repository for "RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies".
-
Official repository for "Context Language Models"
-
llama.cpp's official website