Lists (1)
Stars
A self-hosted non-invasive single-binary photo gallery with a focus on speed and simplicity.
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
The official CLI and Python client for the Hugging Face Hub.
A Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
Zoo Code gives you a whole dev team of AI agents in your code editor.
LLM Frontend for Power Users.
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
A latent text-to-image diffusion model
Docker container for sending Gotify notifications to iOS devices (bridge to gotify websocket)
An app for creating push notifications for new messages posted to gotify/server.
A simple server for sending and receiving messages in real-time per WebSocket. (Includes a sleek web-ui)
竹知了 —— 一转就哇哇叫的传统玩具，Web 模拟版。零依赖单文件，真实录音采样，移动端优先。
LSPosed module for per-app background media playback and auto-next protection
这个项目想做的，不只是让原版 Smartisan Launcher 重新运行起来，而是希望在今天越来越复杂、花哨的 Android 系统上，让人们重新看见 Smartisan OS 那套简洁、精致、统一，并始终认真对待细节的设计美学。
[验证码识别-训练] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the model.
Dual-control Android management for Windows — ADB Mode (scrcpy GUI mirroring & control) and App Mode (calls, media, notifications, Audio Cast).
🩵 A free, open-source app store for developers' releases on GitHub, Codeberg & Forgejo — browse, discover, and install apps with one click. Formerly GitHub Store.
Enable a full desktop experience from any Android device over Wi‑Fi. No root, scrcpy-powered, Flutter desktop app with wireless ADB, per‑app audio, and quick controls.
audio.cpp with a full-task WebUI - pure C++ audio-model inference engine powered by ggml. TTS, ASR/STT, VAD, voice conversion, speaker diarization, music generation. No Python dependency.
Local-first speech-to-text: no cloud, no telemetry, fail-closed by design. One CLI, seven model families, signed model catalog, OpenAI-compatible local API.
MOSS-Transcribe-Diarize 0.9B is an open-source SOTA end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps, and acoustic event awareness.