TwilitRealm/dusklight

4.4k304

Gained this month

Dusklight brings a classic adventure to PC and mobile platforms with a variety of fixes and improvements.

ggml-org/llama.cpp

6.9k1.3k

Gained this month

LLM inference in C/C++

FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making in a user-friendly environment.

High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent orchestration, all from your IDE. Includes VS Code extension, TypeScript/Python SDKs, and Docker deployment.

OpenToonz - An open-source full-featured 2D animation creation software

Easily download and manage single-player game cheats for your convenience

Turn your Pico 2 W into a DualSense 5 dongle.

Private, fast, and honest web browser

qBittorrent BitTorrent client

Qt-based digital signal analyzer, using Suscan core and Sigutils DSP library

Truly independent web browser

Godot Engine – Multi-platform 2D and 3D game engine

G-code generator for 3D printers (Bambu, Prusa, Voron, VzBot, RatRig, Creality, etc.)

Open Source Steam Unlocker

An experimental embedded SQL engine in C++20. Query Parquet, CSV, JSON, Arrow, Avro, SQLite, and Excel files directly with SQL, in-process. Early-stage.

《明日方舟》小助手，全日常一键长草！| A one-click tool for the daily tasks of Arknights, supporting all clients.

🏋️ Python / Modern C++ Solutions of All 4046 LeetCode Problems (Weekly Update)

Port of OpenAI's Whisper model in C/C++

Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.

Hyprland is an independent, highly customizable, dynamic tiling Wayland compositor that doesn't sacrifice on its looks.

A sleek, customizable desktop shell crafted for Wayland.

Self-hosted game stream host for Moonlight.

fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。

An MCP-based chatbot | 一个基于MCP的聊天机器人