Trending Repos

Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.

Win顺：免费开源的 Windows 快速搜索启动器。双击 Ctrl，拼音秒搜文件、全文搜索 Word/Excel/PDF、剪贴板历史（代替 Win+V）、对话框搜索、任务栏搜索、插件、AI 助手 MCP。Free Windows search launcher: pinyin file search, full-text search, clipboard history, MCP server. Everything/Listary alternative.

FLP binary parser for FL Studio project files

Run large AI models on your own PC: Qwen3.8-Flash-Next, GLM 5.3 Flash, Qwen3.6, Ornith 1.5 and Gemma 4. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost, image input. Built on Strata.

A free photo editor. No account, no subscription, no tracking. RAW, masks and on-device AI for macOS, Windows and Linux. Self-hostable.

llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): TurboQuant KV cache, MTP speculative decoding with a 64K draft-vocabulary shortlist, custom SM86 + Qwen kernels. 90 tok/s over a 100K-token generation at temperature 1.

Free tool for Serum 2 — unlock more possibilities with this powerful synthesizer. Download a free Serum 2 tool, presets, and useful settings for music production. Perfect for creating basses, leads, melodies, pads, and other sounds in modern music.

A full music studio and WebUI for YuE2. Score first (ABC/MIDI), LoRA training, stems, remaster, upscale, lyrics check, DAW export. Songs from words on your own GPU. yue2.cpp · 7 languages · OSEM: Open Source, Engaged & Musical

Yamaha MU2000 のソフトウェア音源。実機の firmware をそのまま走らせる VST3。非公式・ヤマハとは無関係

A WebSDR server: C++17 with no dependencies, a one-line install, and an admin panel for everything. Demo: demo.fernsdr.org

LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context

面向网易云音乐与 Twilight Echo 的 Windows 11 任务栏播放器，支持同步歌词、播放控制、封面、音频可视化与红心收藏。

An Unreal Engine plugin for automatic Blueprint graph formatting and clean/performant wire routing. Press F to tidy up your entire graph.

A software M-VAVE FM-1: FM synth app and VST3/AU plugin with two-way preset and pattern sync over the FM-1+VA firmware

Restore native AppleHDA on macOS Tahoe through OpenCore and Lilu

Faithful 64-bit port of SQ8L 0.91b, Siegfried Kullmann's Ensoniq SQ-80 emulation, for macOS and Windows (VST2/VST3/AU/CLAP)

A compiled systems language with Go's syntax and Zig's memory model. Nothing allocates behind your back, and the compiler refuses programs with data races.

llama.cpp optimized for NVIDIA Tesla V100 (Volta, SM70): 2–6 GPU tensor parallelism, Qwen3.8-27B Q8_0/Q4 with DFlash2 speculative decoding, up to 512K context, multimodal (image/PDF/video) and concurrent serving.

mcppls — a C++20/23 modules language server: one set of module semantics on GCC, Clang, MSVC and MinGW, for editors (VS Code, Zed, CLion, Neovim), AI Agents (MCP) and CI

Unofficial DLSS 5 Neural Rendering filter for OBS Studio. runs NVIDIA DLSS 5 NR (NGX feature 18) on any video source (Game Capture, Media Source, Webcam, …) with a Default / Natural / Cinematic style selector

braun rb-26 reverb

Native Windows music player: your Spotify library, played from YouTube. No ads, no Premium. C++ / Direct2D, 11 languages.

Pulsar (formerly fastkernel): the fastest inference engine for Qwen3.8-27B and Qwen3.6-35B-A3B on Apple Silicon

ИИ под названием Vortex для любых задач. Сейчас уже доступна рабочая версия проекта, которая ежедневно улучшается

fast decimal library for c++20 with ffi bindings for rust, java (project panama), and c#, which is pretty cool

🔥 Run large open language models on your phone. A C++20 GGUF inference engine that streams models larger than RAM from flash, paces itself by the device's thermal forecast, and powers a private on-device assistant. Android · iOS · macOS · Linux.

Batteries-included, model-agnostic coding agent with native performance and a small runtime footprint

Drag-and-drop MIDI cues for Quad Cortex, Kemper, Fractal, Helix, HeadRush, Darkglass, Strymon, Whammy & more amp modelers, effects & pedals, or any MIDI device (VST3 / AU / LV2 / Standalone)

Cardputer ADV groovebox: drums, FX, SD streaming, BLE MIDI.

A Multifunctional code editor library for compose multiplatfrom（It is not the BasicTextField enhancement）

Fast local AI decisions inside your application. A shared library and C API built on laya.cpp that runs the Laya typed-decision model in-process: no server, no Python. Windows, Linux and macOS, x64 and ARM64, CPU or GPU. An open-source alternative to Jev

A CMake template project for developing custom FMOD DSP plugins in C++.

C++L is C++ with Laws: an ambiguity-free, proof-carrying superset C++ based language in which humans or AIs can specify intent as machine-checkable Laws, implementations are accepted only when those Laws are proven, and all proof machinery erases to ordinary optimized C++ compiled by Clang/LLVM.

A truly native YouTube Music client for Linux, Windows and macOS.

Minimal bridge for sharing one clock between SuperCollider and openFrameworks over OSC. SuperCollider owns the clock and sends phase; openFrameworks subdivides it into a clickable beat grid and sends beats back. A small, readable starting point for getting the two languages talking cleanly.