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
71 repos
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
JAX/Equinox implementation of ProteinMPNN and LigandMPNN for protein sequence design
-
An open-source execution engine for AI-SQL and LLM-powered dataflow
-
MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute
-
Skills for Real Engineers. Straight from my .agents directory.
-
Open-source data movement for ELT pipelines and AI agents — from APIs, databases & files to warehouses, lakes, and AI applications. Both self-hosted and Cloud.
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
-
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
-
AI Tensor Engine for ROCm
-
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
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.
-
A simple template language that turns data into Markdown.
-
NetHack as-a-library. Semantic world exploration engine.
-
The batteries-included agent harness.
-
QuickJS, the Next Generation: a mighty JavaScript engine
-
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
-
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, quality deltas. Signatures at 74.7% fewer bytes than bodies; every guess labelled, every loss published. Paddle out with a map.
-
Grimoire's Tome & The Grim Council. A Prompt Spellbook of /skills. The #1 Coding Wizard 🧙♂️📖
-
Agent skill that removes signs of AI-generated writing from text
-
SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning interface in a unified simulation platform, with VR-based teleoperation and additional capabilities planned for future releases.
-
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
-
Powerful web graphics runtime built on WebGL, WebGPU, WebXR and glTF
-
A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.
-
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
-
💫 Toolkit to help you get started with Spec-Driven Development
-
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Claude Code / Kiro / Cursor / Cline 等代码 AI 客户端
-
Open source re-implementation of Tomb Raider I, Tomb Raider II and Tomb Raider III, along with additional enhancements and bugfixes
-
The procedural generation voxel engine
-
Nix-powered agentic reverse engineering environment
-
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
-
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
-
A library of creative canvas components. Real HTML with WebGL effects running over it. React, Vue, Svelte, vanilla.
-
🛡️ Protect your Minecraft server and lets players claim areas
-
A Datacenter Scale Distributed Inference Serving Framework
-
AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.
-
Analysis engine for big-data astrophysics
-
An analysis engine for big-data astronomy. Empowers astronomers to think about their science, not data management.
-
🐎 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.
-
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
-
Measuring frontier coding agents on original, long-horizon engineering tasks
-
javascript for 🐜's, a tiny runtime with big ambitions