🏠
Highlights
- Pro
Lists (2)
Starred repositories
261
results
for source starred repositories
Clear filter
Anny, A Free and Interpretable Human Body Model for all ages, written in PyTorch.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
An API-compatible, drop-in replacement for Apple's Foundation Models framework with support for custom language model providers.
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
JUCE is an open-source cross-platform C++ application framework for desktop and mobile applications, including VST, VST3, AU, AUv3, LV2 and AAX audio plug-ins.
5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .
FreeCAD MCP(Model Context Protocol) server
The AI coding agent built for the terminal.
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.
The official source code repository for the calibre ebook manager
Amperfy is an iOS/iPadOS/macOS app to play songs from an Ampache or Subsonic server
image scaling attacks for multi-modal prompt injection
This is a list of awesome demos, tutorials, utilities and overall resources for the robotics community that use MATLAB and Simulink.
A Swift framework for microcontrollers abstraction layer.
Open Source Alternative to Vercel, Netlify and Heroku.
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
A self-hosted web UI that simplifies AI experimentation and testing for Java developers. It provides playgrounds for all major vector databases and MCP tools, supports intuitive interaction with LL…
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.