Stars
Multi-backend GGUF vision-language inference engine (moondream3.1 · VideoChat3 · Qwen2.5-VL · MOSS-VL · VideoMAE/ViViT · SmolVLM) with a unified CLI, Web UI and an MCP server for agents.
Fast, resumable download manager with a browser extension. Many connections per file, instant resume, IDM-style download windows. Rust + Tauri.
Games, 3D worlds and web pages built with Claude Fable 5.2 that you can actually open — 229 live works (every link checked) + 148 video demos, each with a GIF preview and creator credit. Updated da…
This repository packages Karpathy-inspired coding guidelines as a Codex skill and a Codex plugin. It is designed for Codex CLI and the Codex app, with one canonical skill source under `.agents/skil…
Build modern, cross-platform applications entirely in Go. No browser runtime. No JavaScript. No HTML or CSS.
SyncUp: an open-source Syncthing client for iOS and Android, powered by react-native
Securely synchronize files with your devices on iOS using Syncthing
Obsidian on your iPhone, in sync with your own devices — device to device, without iCloud or a note cloud.
Remap your macOS keyboard with a simple SwiftUI frontend
面向中文母语者的 macOS 英语学习工具,可切换其他目标语言:读取中文拼音输入法的当前高亮候选,在候选栏旁显示对应译文。
misterdownloadmanager: The ultimate open-source, clean-room download manager written from scratch in pure Rust for Windows, Mac, and Linux
We're rebuilding and open-sourcing the world’s software from scratch.
#1 Persistent memory for AI coding agents based on real-world benchmarks
Cross-app window tabs for macOS: drop a window on another and pause to stack them under one strip of tabs
five markdown preview style themes for MarkEdit
A native macOS file browser with fast fuzzy filename search, powered by fsearch.
Develop desktop apps with native UI or web frontend in Go
panwudi / flyto-mlx
Forked from jundot/omlxFlyto MLX — Apple Silicon LLM server with audio chat / DFlash / Chinese model presets. Fork of @jundot/oMLX.
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.
实时交互数字人,可自定义形象与音色,支持音色克隆,对话延迟低至3s。Real-time voice interactive digital human, customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.
Official PyTorch+CUDA Full-functional Web Demo for MiniCPM-o 4.5
A comprehensive ComfyUI integration for Microsoft's VibeVoice text-to-speech model, enabling high-quality single and multi-speaker voice synthesis directly within your ComfyUI workflows.
ONLYOFFICE Personal 是一款基于wasm运行的Office办公套件,无需服务端直接运行。