Repository Index

An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS

• audio
• audio-tokenizer
• llm
• multimodal

Multithreaded PNG optimizer written in Rust

• image-compression
• image-optimization
• png
• png-compression

vimspector - A multi-language debugging system for Vim

• vim
• debugging
• debugger
• debug-adapter-protocol

Multi-vendor library to simplify Paramiko SSH connections to network devices

The source code for the Cfx modification frameworks, such as FiveM and RedM, as well as FXServer.

• fivem
• cfx
• gta
• redm

Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun

• artificial-intelligence
• deep-learning
• transformers
• siren

Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI, Factory Droid Coding.

• ai-coding
• claude-code
• cli
• opencode

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

TranslatedA cross-platform multimedia framework based on Qt and FFmpeg. Recommand to use new sdk https://github.com/wang-bin/mdk-sdk

• qtav
• ffmpeg
• player
• multimedia

Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

• transformers
• text-classification
• named-entity-recognition
• question-answering

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

• multi-object-tracking
• one-shot-tracker
• joint-detection-and-tracking
• real-time

SuperSocket is a high-performance, extensible socket server application framework for .NET. It provides a robust architecture for building custom network communication applications with support for multiple protocols including TCP, UDP, and WebSocket.

• csharp
• socket
• socketserver
• realtime-communication

open Structure-fom-Motion and Multi-View Stereo reconstruction library

• multi-view-stereo
• 3d-reconstruction
• point-cloud
• stereo-reconstruction-library

Your First AI Agents Company

• agent
• llm
• multiagent
• openclaw

TranslatedA native Android audio player that combines multi-source streaming, local control, rich lyrics, and self-hosted sync. / ✨ An audio player that builds multi-source online playback, local management, lyrics experience, and self-hosted sync into native Android 🎵

• android
• music
• native-apps
• player

A fast, scalable, distributed game server engine/framework for C++, include the actor library, network library, can be used as a real time multiplayer game engine ( MMO RPG/MOBA ), which support C#/Lua script/ Unity3d, Cocos2dx and plan to support Unreal.

• server-architecture
• unity3d
• architecture
• gameserver

Multi-platform app that allows your devices to communicate

Harness LLMs with Multi-Agent Programming

• agents
• chatgpt
• gpt
• gpt-4

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

• chatglm-6b
• gpt
• multi-modal

VLC for Android, Android TV and ChromeOS

• vlc
• android
• libvlc
• videolan

Linux multi-touch gesture recognizer

• linux
• gesture-recognition
• multi-touch
• libinput

Open-source GEO content engineering and multi-site distribution platform with AI quality inspection, illustrated admin help, hosted sites, browser-assisted publishing, and signed updates.

• ai
• cms
• content-automation
• geo

OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

• chinese-nlp
• pretrained-models
• pytorch
• distributed-training