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
333 repos
-
reproducing the flapping airplanes megakernel, in collab with magni
-
Simple, typographic beamer theme
-
An NES CPU compiled into the weights of a stock Qwen3.5 model
-
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
-
Garry's Opinionated OpenClaw/Hermes Agent Brain
-
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
-
The official TypeScript SDK for the SpaceXAI API
-
Open ML Compiler Foundation
-
Prototyping on AI Foundry's ET-SoC-1 (1088-core RISC-V): sys_emu setup, hello world, tensor-unit matmul FLOPs/W vs A100
-
Beautiful, Modern & Opinionated Linux
-
A simple python wrapper for using the Caddy API
-
The official Unity plugin for Sprite Fusion
-
The official Godot plugin for Sprite Fusion
-
Small browser games as isometric pixel dioramas. No build step, no dependencies.
-
Learn harness engineering by building Claude Code from scratch. Free, open-source course: 8 articles, 6 videos, 1 codebase.
-
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
-
A benchmark for evaluating AI agents on realistic business workflows
-
Skills for the Gemini API, SDK and model/agent interactions
-
Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one
-
Implement one small API on SQLite in any language; we benchmark it on a $12 server (1 vCPU, 2 GB)
-
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.
-
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
-
Public repository for Agent Skills
-
Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust
-
Create delightful software with Jupyter Notebooks
-
Rendered episodes and shorts for simgrammar.com, held as release assets. Kept apart from the main repository so Zenodo archives only the paper.
-
Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research
-
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.
-
A framework for building decision-model harnesses for any kind of task. Your program offers the model a short list of next steps, and the model picks one at a time until it can answer.
-
Pi coding agent extension: llama.cpp provider with dynamic model + context window discovery
-
An open protocol and client for what your coding agents are doing: hooks for every harness, four privacy tiers, any sink.
-
An open source multi-tool for exploring and publishing data
-
The Actor-Gatherer framework: a context management framework for AI agents.
-
Exact probabilistic inference by compilation into tree decision diagrams
-
Open Machine Learning Compiler Framework
-
A local coding agent with a web UI that builds itself while it runs, on Pi Durable
-
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
-
Portable SOL visual policy evaluation, empirical latency profiles, and research evidence
-
nnScaler: Compiling DNN models for Parallel Training
-
Tree Decision Diagrams for Rust, Python and C: canonical circuits for Boolean functions, with model counting and weighted evaluation
-
Let's compose rich plans together
-
A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.
-
🪨 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.
-
Backend that powers the dataset viewer on Hugging Face dataset pages through a public API.
-
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
-
Lectures given in the department's Advanced Topics in Machine Learning
-
Lectures given in the departments Advanced Topics in Machine Learning or NLP Module
-
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
-
Rails as a specification; the deployment target is a build flag
-
A delightful and complete interface to GitHub's amazing API