OpenVLA: An open-source vision-language-action model for robotic manipulation.

An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.

Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment

real time face swap and one-click video deepfake with only a single image

[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from sim…

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

The ultimate LLM/AI application development framework in Golang.

Unity MCP acts as a bridge, allowing AI assistants (like Claude, Cursor) to interact directly with your Unity Editor via a local MCP (Model Context Protocol) Client. Give your LLM tools to manage a…

Agent Framework For Fintech and Banks

MCP Server for the Bilibili API, supporting various operations.

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

A collection of MCP servers.

AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Detect and recognize the faces from camera / 调用摄像头进行人脸识别，支持多张人脸同时识别

车牌识别

Support data enhancement when there are few data sets（支持数据集较少的情况进行数据增强，包含随机的多种变化）

Mish Activation Function for PyTorch

Scaled-YOLOv4: Scaling Cross Stage Partial Network

Robust Speech Recognition via Large-Scale Weak Supervision

[Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime

Image Captcha Solving Using TensorFlow and CNN Model，with self-labeling image Dataset crawled from a website，free to download my Dataset for self-learning. accuracy 95%+

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

Visit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/

🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

OpenMMLab Pose Estimation Toolbox and Benchmark.

Forecast time series and stock prices with SCINet