Stars
🎙️ 「大模型」从0训练0.1B能听能说能看的全模态Omni模型！A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!
The open-source alternative to Claude Cowork (powered by opencode)
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without …
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
A Flutter LLM Chat Client. Support Mobile & Desktop.
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Andr…
Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, L…
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
LVGL is a free, full-featured embedded UI library for devices from small MCUs to 3D-capable MPUs, enhanced by LVGL Pro, a professional editor and tooling.
A fast and lightweight 2D game physics library.
Godot Engine – Multi-platform 2D and 3D game engine
Animated sprite editor & pixel art tool (Windows, macOS, Linux)
Visualizer for neural network, deep learning and machine learning models
VLC media player - plays everything, runs anywhere. Code here: https://code.videolan.org/videolan/vlc
An open-source JavaScript library for world-class 3D globes and maps 🌎
Next generation frontend tooling. It's fast!
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors