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
39 repos
-
An interactive HTML pretty-printer for machine learning research in IPython notebooks.
-
Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights'
-
Tensors and Dynamic neural networks in Python with strong GPU acceleration
-
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)
-
GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices.
-
Centralized network visibility and continuous asset discovery. Monitor devices, detect change, and stay aware across distributed networks.
-
Network Performance Analysis Course
-
Collaborative LaTeX editor you host yourself, for trusted networks and tailnets, with native agent integration
-
Machine Learning Engineering Open Book
-
JAX in JavaScript – ML library for the web, running on WebGPU & Wasm
-
A simple social network.
-
Deep Neural Networks Module
-
A scikit-learn compatible neural network library that wraps PyTorch
-
A shared, persistent world for people and AIs — the networking, persistence, and multi-participant layer over the eidoverse-video toolkit. Two planes: an append-only world log + lossy presence.
-
A simple yet fast user space network driver for Intel 10 Gbit/s NICs written from scratch
-
Message Passing Neural Networks for Molecule Property Prediction
-
★ 307 tscmoo/plutoStarCraft: Brood War AI — a neural network trained by self-play RL.
-
Morphology-adaptive muscle-driven locomotion via attention mechanisms
-
GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices.
-
Visualizer for neural network, deep learning and machine learning models
-
A multi-framework neural network compiler lowering PyTorch, JAX, Flax, and Keras models to portable, high-performance GGML execution
-
A MCP server that gives LLMs direct access to the AT Protocol ecosystem, enabling seamless interaction with Bluesky and other AT Protocol-based social networks.
-
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
-
Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/
-
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
-
Full-network archive and streaming service for atproto.
-
Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream, ICML 2025 Spotlight
-
Multimodal Scaling Laws for Task & Data-Optimized Models of Visual Cortex, ICML 2026
-
Empowering everyone to host fast and efficient Minecraft servers
-
Tensors and Dynamic neural networks in Python with strong GPU acceleration
-
The "Python Machine Learning (1st edition)" book code repository and info resource
-
Face recognition with deep neural networks.
-
WebKit compiled to WebAssembly: a full browser engine running inside a browser tab, rendering to canvas, networking over Wisp.
-
An Elixir client for the core of the RakNet networking protocol, useful for games and other latency-sensitive applications that typically rely on UDP
-
AI Engineer World Fair networking room app
-
A web-based framework to visualize dynamic networks in real-time.
-
AI Engineer World Fair networking room app
-
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
-
Noumena's internal version of your favorite coding tui but improved and optimized for our inference stack