Lists (3)
Starred repositories
EmDash is a full-stack TypeScript CMS based on Astro; the spiritual successor to WordPress
Fast, accurate & comprehensive text measurement & layout
Lightpanda: the headless browser designed for AI and automation
Ο RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection β all without a single pixel of video.
Official inference framework for 1-bit LLMs
Open-source orchestration for zero-human companies
AI agents running research on single-GPU nanochat training automatically
Google Workspace CLI β one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
The easiest, most secure way to use WireGuard and 2FA.
Nightshift uses your leftover Claude / Codex budget to surprise you with useful PRs. Love them or leave them.
Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM β deploy anywhere, swap anything π¦
TinyAGI is the agent teams orchestrator for One Person Company. (fka TinyClaw)
Control Obsidian from Claude Code via the Obsidian CLI
2
Updated Feb 10, 2026
The backend for selling things on the internet.
π ESPectre π» - Motion detection system based on Wi-Fi spectre analysis (CSI), with Home Assistant integration.
Render markdown on the CLI, with pizzazz! π π»
A payments protocol for the internet. Built on HTTP.
An open-source vibe coding platform that helps you build your own vibe-coding platform, built entirely on Cloudflare stack
A set of beautifully-designed, accessible components and a code distribution platform. Works with your favorite frameworks. Open Source. Open Code.
A tool for creating and running Linux containers using lightweight virtual machines on a Mac. It is written in Swift, and optimized for Apple silicon.
A fast, Unix-style CLI tool for semantic prompt compression. Cuts LLM prompt tokens by 10-20x with >90% fidelity, saving costs and latency.
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
π° Must-read papers and blogs on LLM based Long Context Modeling π₯
Toolkit for Prompt Compression
Open Source Alternative to Vercel, Netlify and Heroku.
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI