Lists (4)
Starred repositories
Beautiful, AI-native markdown IDE and LLM wiki
Track GitHub files, directories, commits, pull requests, and agent skills like dependencies.
AI-safe .env files: Schemas for agents, Secrets for humans.
Create an open letter and get people to sign it
Project Context Records (PCR) gives autonomous AI work durable, reviewable memory in the repository.
Inspect the intermediate state of Vite plugins
A free, open source, and extensible speech-to-text application that works completely offline.
Mock API requests in Storybook with Mock Service Worker.
Mealdrop-themed UI components for building accessible web apps and design systems. Used by Mealdrop.
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
A typescript-shaped drop-in backed by typescript-go (tsgo) over an in-process cgo NAPI/FFI bridge — no IPC.
A composite GitHub Action that turns conventional commits into a draft release PR, tags the PR on merge, and stages publishing to npm via OIDC trusted publishing.
Anti-AI-slop design skill for Claude Code, Cursor, and Codex.
An agent reads your design system through the components manifest, not through your docs. Oversight lints the manifest and tells you what didn't make it in.
Open-source Reflect rewrite: A local-first AI agent-friendly Markdown note-taking app
OpenWiki is a CLI that writes and maintains agent documentation for your codebase.
A lightweight, dependency-free JavaScript library for guiding user focus across the page.
A beautiful, zero-config terminal system monitor for macOS
The Vue framework for terminal UIs. SFC & JSX, Yoga flexbox, HMR, and testing out of the box.
Use your most capable model to audit your codebase and write plans for cheaper models to execute.
Free and open source database client built natively for developers
A macOS menu bar app that highlights your clicks for demos, recordings, UX reviews, and better click visibility.
A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.