Stars
Bare-metal x86-64 machine-code viewer and step debugger for decoder differential analysis.
DLSS MFG on Ada — unlocks 3x/4x/6x frame generation on RTX 40-series cards and corrects the temporal midpoint. In-memory only.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent…
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B c…
Expose local http, tcp or websocket connections to the public internet
Scoop bucket for open source/freeware games and game-related tools
Don-Chad / ninfer-3090
Forked from Neroued/ninferHyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux builds.
ComfyUI node for MiniMax H3 that chains multiple video clips with motion context, disk caching, dynamic image references, audio reference support, and seamless final video/audio decoding.
Create hidden services for your containers - everything in docker.
Use ChatGPT Web (including Pro) as a native model in Codex — with context, tools, streaming and images, without using Codex quota.
A native recompilation of Skate 3 for Windows, Linux, and macOS.
C++ Recast/Detour wrapper behind CopilotBuddy's pathfinding. Faithful port of Honorbuddy's Tripper.RecastManager (WoD │ / Legion): same C API, same struct layouts, so the C# P/Invoke layer calls in…
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
A ComfyUI custom node integration for local multi-engine multi-language Text-to-Speech and Voice Conversion. Supports: RVC, Echo-TTS, Qwen3-TTS, Cozy Voice 3, Step Audio EditX, IndexTTS-2, Chatterb…
Local AI text-to-speech with voice cloning and voice design, powered by GGML. C++17 port of Qwen3-TTS (QwenLM/Qwen3-TTS). 10 languages, 24 kHz mono output, runs on CPU, CUDA, ROCm, Metal, Vulkan.
Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale…
Model Context Protocol server for ImHex hex editor
Multi-Platform Package Manager for Stable Diffusion
C(ontinued)-MaNGOS (Classic fork) is about: -- Doing WoW-Emulation Right!
World of Warcraft Engine Experiment - a custom opensource client.
LLDB MCP/HTTP server - drive LLDB from an external AI agent via a dbg_exec tool
MCP server for interfacing with Godot game engine. Provides tools for launching the editor, running projects, and capturing debug output.
Modern concurrency for C++. Tasks, executors, timers and C++20 coroutines to rule them all