Evidence-preserving singing transcription and score contracts

Search your Mac by what's in your files: photos, PDFs, recordings, videos and code. On-device, built on Google DeepMind's EmbeddingGemma 2.

Reverse engineer anything with agents, from app behavior down to native binaries.

Use the first-gen Apple Siri Remote (A1513/A1962) on Linux: unlock it, decode touch and buttons, tvOS-style gestures, a virtual keyboard. Pure-stdlib Python.

Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame extraction, runtime atlases. Codex/Claude skill.

AI 艺术创作引擎，专业的短视频，游戏3D资产，2D资产，广告创作工具

Open source inference engine for agents that optimizes itself for your exact hardware. Compiles and tunes its kernels on your device, so open models run up to 2x faster than llama.cpp. Works on App…

Train LoRAs for Qwen-Image 2.1, FLUX.2 Klein 9B, Krea 2, Z-Image, Ideogram 4, Anima, SDXL (Pony, Illustrious, NoobAI), LTX 2.3 and MiniMax-H3 on NVIDIA GPUs from 4–8 GB VRAM. One install, one launc…

检查第三方AI API是否掺假以及渠道一致|基于llm指纹的AI模型识别

Teaching claudes to paint

A lightweight macOS menu bar audio mixer.

Your always-on AI coworkers that move between text, calls, and Slack.

Free, Open Source, Self-Hosted WhatsApp API Gateway

Local typed decisions in one Python call. GemmaDecision-270M, native PydanticAI, Rust HTTP serving and optional vLLM.

Best headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust

从服装参考图生成整套与拆件资产板的 MIT Skill

Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.

ncnn implementation of Qwen-Image-2.1, with text-to-image, image editing, multi-reference image input and transparent RGBA output

Train a Jev-like multimodal model by yourself. System One Model, now with vision.

Local-first, lightweight, AI-native video workspace.

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, LTX-2, Qwen Image, Hunyuan Video, LTX Video and Flux.

AutoClip : AI-powered video clipping and highlight generation · 一款智能高光提取与剪辑的二创工具

Real-time talking character on a single RTX 5090 — LTX-2.5 22B + local LLM + TTS, fully local. First video ~2.6s after Enter.

Self-hosted iOS & Android simulator streaming for the whole team

VRChat 实时同声传译：语音 → chatbox 气泡 + SteamVR 手腕屏字幕（阿里百炼 qwen3.8-livetranslate 端到端）

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

歌詞から文字PVを自動で組み立てるブラウザアプリ