NeuralDeskApp
Versatile Almost Local, Eventually Reasonable Assistant 🔫
HYSEN LABS DIRECTORY
Deployment tag · curated repositories and deep analysis.
Versatile Almost Local, Eventually Reasonable Assistant 🔫
A minimal yet powerful framework for creating AI agents with full control over tools, providers, and execution flow.
Classic grid bot: Extended / RISEx / Decibel / N1 / Phoenix
A Model Context Protocol (MCP) server that enables LLMs to interact with iOS simulators through natural language commands.
Karpathy LLM based claude harness for PenetrationTesting / Bugbounty using obsidian
Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.
Local-first knowledge-base desktop app: Markdown editor with full-text search, bidirectional links and a knowledge graph; multi-device sync via WebDAV/S3 with ZIP backup; AI Q&A (OpenAI-compatible/Ollama/custom providers); imports .md/.txt/.pdf/.docx; encrypted vault with PIN; cross-platform (Tauri 2.x, React 19, Rust, SQLite), zero cloud dependency.
A speech companion app built with Expo
Seedance 2.0 API — text-to-video and image-to-video examples
QA-Pilot is an interactive chat project that leverages online/local LLM for rapid understanding and navigation of GitHub code repository.
Record the talking head, Claude Code does the rest: the cut, the visuals, the voice, the sound effects, the thumbnail, and the YouTube upload. Every screen moment is built as Remotion TSX code, never screen-recorded.
Drawing toolbar for React.
Unified LLM API, structured data outputs with LLMs, and agent SDK - in PHP
A Claude Code skill that compiles vague requests into complete gpt-image-2 prompts - no negative prompts, outcome-based descriptions, validation scripts, C1-C10.
Unofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.
Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.
Reliable, minimal and scalable library for pretraining foundation and world models
RushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back — no schema, no migrations. Built on Neo4j.
Local-first AI image organizer and generative media library manager for ComfyUI, A1111, InvokeAI & more. Search huge output folders by prompt, model, LoRA, metadata or visual similarity.
Simple self-hosted web application, which can be used to convert audio to subtitles by OpenAI's Whisper model