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
38 repos
-
Scored tooling katas, habit rules, and pre-baked warm-start sessions for LLM coding agents
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
Convert your data to Markdown files you can use in Obsidian. Works with Apple Notes, OneNote, Evernote, Notion, Google Keep, and many other formats.
-
Get the main content of any page as Markdown.
-
Open Source Continuous Inference Benchmark Research Platform — Kimi K3 2.8T, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3 | 开源持续推理基准研究平台 — Kimi K2.7-Code、MiniMax M3、DeepSeekv4、GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72，即将推出™ TPUv6e/v7/Trainium2/3
-
Highlight and capture the web in your favorite browser. The official Web Clipper extension for Obsidian.
-
XHTML to docx conversion
-
Monkey patch, test, and trace Python by attaching bindings to call sites, without modifying the code being observed. Built on wrapt.
-
OpenMMLab Detection Toolbox and Benchmark
-
A simple template language that turns data into Markdown.
-
Python bindings for the fast integer compression library FastPFor.
-
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
-
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
-
Call commands safely by checking them rigorously against an allow-list
-
Markdown to mdhtml (HTML subset) convertor
-
[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model
-
Help documentation for Obsidian.
-
An agent skill that turns an architecture discussion into an explorable isometric atlas: one data file, an interactive map and a generated SYSTEM.md
-
A distraction-free and highly customizable theme for Obsidian.
-
Official AMD catalog of AI agent skills. Empower your AI agents with AMD's optimized SW stack.
-
Markdown to mdhtml (HTML subset) convertor
-
Apple Silicon (Metal) backend for Triton: write standard @triton.jit kernels on your Mac GPU. The same source runs bit-identical on NVIDIA and AMD, so you develop kernel logic locally and rent a datacenter GPU only for the perf pass.
-
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
-
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
-
★ 1 neubig/playbooksOfficial repository of AMD Playbooks
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Elixir State machine thin layer for structs
-
Random md website generator
-
HTML in. MD out. Blink-fast. The little helper that chomps HTML and spits pristine Markdown. Goodbye <div>, hello ##.
-
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)
-
Website for SOUL.md
-
Terminal emulator library for the BEAM — libghostty-vt NIFs with OTP integration
-
MDN's prototype MCP server
-
Smartthings plugin for StreamDeck
-
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
-
Create markdown-based reveal.js presentations in Obsidian
-
FastCrest Tether: the OSS edge-to-cloud AI deploy CLI. Optimize, verify, deploy across Jetson, RTX, Apple Silicon, AMD. Hybrid edge-cloud inference with parity certs.