Provides a frontend-design skill plus 20 steering commands and curated anti-patterns to steer LLMs toward clearer, accessible UI designs. Designed to plug into AI harnesses (Cursor, Claude/Gemini CLI, code agents) for auditing, critiquing, and polishing interfaces.
Wraps LangGraph in an opinionated harness giving an agent planning, file read/write, sub-agent delegation, and persistent memory out of the box. Aimed at long-horizon work where plain ReAct loops exhaust their context window.
Embeds into an app like SQLite, persisting to a local file with no server or separate process. Combines dense and sparse vectors, full-text search, and scalar filters in one hybrid query; C++ core with Python, Node, Go, Rust, and Dart bindings.
Normalizes wearable data — heart rate, sleep, activity, steps — from Garmin, Whoop, Apple Health and more behind one self-hosted API, so you write one integration instead of one per provider. Natural-language AI health automations are planned.
Enables parallel speculative decoding by using a lightweight block-diffusion draft model to produce multi-token drafts for faster, high-quality generation. Integrates with vLLM, SGLang and Transformers backends and ships draft models on Hugging Face.
Provides a customizable React-based design system and component library designed for people and AI assistants to build together. Ships 150+ accessible components, a theme system, and a CLI; supports swizzling to eject source and className overrides so projects avoid styling lock-in.
Provides an installable library of 1,340+ SKILL.md playbooks for AI coding assistants, with an installer CLI, bundles, workflows and plugin-friendly distributions for Claude Code, Cursor, Codex, Gemini CLI and more.
Models an AI agent's context as a file system, unifying memory, resources, and skills instead of flat vector RAG. Uses L0/L1/L2 tiered loading to cut tokens, directory-recursive plus semantic retrieval, and visualized retrieval traces for debugging.
Rust library for fast PDF classification and position-aware text extraction that converts native-text PDFs to structured Markdown without OCR. Offers per-page OCR routing, multi-column and table detection, and Python/Node.js/WebAssembly bindings for low-latency local pipelines.
A fast, local document parser that extracts spatial text with bounding boxes from PDFs and other formats. Bundles Tesseract OCR and supports HTTP OCR servers, multi-language bindings (Rust, Node, Python, WASM) and screenshot generation; best for lightweight local pipelines but less suited to very complex or heavily scanned documents.
Measures multiline text layout and block height without triggering browser reflow: it measures text segments once via Canvas+Intl.Segmenter and caches widths, then computes line breaks with pure arithmetic. Useful for streaming AI text, virtualization, and custom per-line rendering.
Generates 48kHz multilingual speech from text using a tokenizer-free diffusion-autoregressive TTS architecture, supporting natural-language voice design, controllable cloning, and low-latency streaming. Notable for a 2B-parameter backbone and built-in AudioVAE super-resolution (16k→48k).