A set of ready to use scientific skills for Claude

Stop juggling AI accounts. Quotio is a beautiful native macOS menu bar app that unifies your Claude, Gemini, OpenAI, Qwen, and Antigravity subscriptions – with real-time quota tracking and smart au…

让 AI 编辑器之间自然流动，不仅仅可以其他工具使用，也可以转换成 api 为本地开发提供动力。

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

A place to optimize llama.cpp for GFX906

Ollama 0.12.3 + ROCm 7.1 for AMD MI50 (gfx906) Docker image

Midscenejs pc connetor server.Based on ubuntu20 gnome desktop,accessed via VNC.一个支持运行各类Ubuntu软件的Docker镜像，如chrome、微信、钉钉、QQ、WPS等。

⚡A CLI tool for code structural search, lint and rewriting. Written in Rust

🖥️ Run AI Agent in your browser.

这是一个兼容OpenAI接口的Qwen3语音识别(ASR)服务，支持多种部署方式。支持spokenly直接调用，提供完整的语音转文字功能，包括多语言支持、智能标点格式化，以及与OpenAI Whisper API完全兼容的接口。

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…

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

This is a generator to create a class-diagram of PlantUML from the C# source code.

XSD2Code 是一个功能强大的命令行工具，专门用于将 XML Schema Definition (XSD) 文件转换为多种编程语言的类型定义和数据结构。该工具采用智能解析技术，自动处理复杂的XSD特性，生成可直接使用的、类型安全的代码。

文颜 MCP Server 可以让 AI 自动将 Markdown 文章排版后发布至微信公众号。

基于AI和证据搜索的虚假新闻自动检测系统

⚡ Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary. FREE now, FREE forever.

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

[NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'

这是一个从头训练大语言模型的项目，包括预训练、微调和直接偏好优化，模型拥有1B参数，支持中英文。

Docker Compose for n8n with all traffic routed through a SOCKS5 proxy

百度开源的依存句法分析系统

CUDA on non-NVIDIA GPUs

ROCm Library Files for gfx1103 and update with others arches based on AMD GPUs for use in Windows.

FORK of VLLM for AMD MI25/50/60. A high-throughput and memory-efficient inference and serving engine for LLMs

vLLM for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60