vision

Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active

Xray, Penetrates Everything. Also the best v2ray-core. Where the magic happens. An open platform for various uses.

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

Caffe: a fast open framework for deep learning.

Automate browser based workflows with AI

https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

📸 A powerful, high-performance React Native Camera library.

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。

SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

Open source hardware and software platform to build a small scale self driving car.

[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

The Open Source Framework for Machine Vision

⬆️ Media Capture in Swift

Java and Kotlin Code samples used on cloud.google.com

Visual intelligence for your home.

A vision library for genicam based cameras

Videos, notes and experiments to understand deep learning

🌝 MLKit是一个强大易用的工具包。通过ML Kit您可以很轻松的实现文字识别、条码识别、图像标记、人脸检测、对象检测等功能。

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

An All-MLP solution for Vision, from Google AI

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

A CUDA implementation of SIFT for NVidia GPUs (1.2 ms on a GTX 1060)

A curated collection of iOS, ML, AR resources sprinkled with some UI additions

3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.

High-performance Vision library in Python. Scale your research, not boilerplate.

🎰 A curated list of machine learning resources, preferably CoreML

This application can translate text captured from any application running on your computer.

Convert any web design screenshot to clean HTML/CSS code

Computer vision based ML training data generation tool :rocket: