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.
1,506
repos tracked
254
surfaced this week
209
created < 30d
Python
top language
47 repos
-
A library of creative canvas components. Real HTML with WebGL effects running over it. React, Vue, Svelte, vanilla.
-
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
-
🛡️ Protect your Minecraft server and lets players claim areas
-
A Datacenter Scale Distributed Inference Serving Framework
-
AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
-
Analysis engine for big-data astrophysics
-
An analysis engine for big-data astronomy. Empowers astronomers to think about their science, not data management.
-
Agent skill that removes signs of AI-generated writing from text
-
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
🐎 Ryan Lopopolo’s anthology, field guide, and agent context bundle for harness engineering
-
Local-first active-learning photography taste engine with Elo ranking and a mobile PWA
-
An open-ended artificial-life substrate that runs entirely in your browser (WebGL2). Fuses mass conservation, an evolvable embedded genome, a metabolic economy, and a novelty drive into one world.
-
Machine Learning Engineering Open Book
-
Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]
-
WebKit compiled to WebAssembly: a full browser engine running inside a browser tab, rendering to canvas, networking over Wisp.
-
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
-
As-of macro forecast tournaments for testing LLM belief engines before HANK embedding.
-
Measuring frontier coding agents on original, long-horizon engineering tasks
-
javascript for 🐜's, a tiny runtime with big ambitions
-
Methodology for faithfully cloning any website (static / React / WebGL) — without copying AI-hallucinated code. Real source first.
-
Command & Conquer Generals: Zero Hour running natively on macOS, iPhone & iPad — real engine (EA GPL v3 source, via GeneralsX), DXVK/MoltenVK renderer, RTS touch controls. No game assets included.
-
Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
-
Benchmarking Goal-Oriented Software Engineering
-
The open-source AI workbench for scientific research
-
An Open-source Drug Discovery Engine
-
A Liquid template engine, 100% vibe coded by Claude Code against liquid-spec
-
[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)
-
AI Engineer World Fair networking room app
-
AI Engineer World Fair networking room app
-
Research-focused C++23 physics engine for robotics, animation, and machine learning, with Python bindings
-
Rojo enables Roblox developers to use professional-grade software engineering tools
-
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
-
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
-
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
-
Build configuration for Transformer Engine Torch
-
The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
-
★ 6.7k zai-org/GLM-5GLM-5: From Vibe Coding to Agentic Engineering
-
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
-
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.
-
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
-
Quality-Diversity (CMA-ME) experiments over a headless Micropolis (SimCity 1) engine
-
Production-Grade Autoresearch. Ideal for GPU kernels, ML model development, feature engineering, prompt engineering, and other optimizable code.
-
Skills for Real Engineers. Straight from my .agents directory.
-
Lobster is a Openclaw-native workflow shell: a typed, local-first “macro engine” that turns skills/tools into composable pipelines and safe automations—and lets Openclaw call those workflows in one step.
-
Rubric compiler and judge engine for LLM evaluation