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

aws google ai clone azure mcp gemini vision openai artifacts webui claude o1 chatgpt chatgpt-clone gpt-5 anthropic librechat deepseek responses-api

• Updated Nov 12, 2026
• TypeScript

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

dns tls tunnel network proxy socks5 shadowsocks anticensorship vpn trojan vision reality vmess utls xray wireguard xhttp vless xtls xudp

• Updated Nov 12, 2026
• Go

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

agent mcp vision vlm tars multimodal cowork computer-use mcp-server gui-agent browser-use gui-operator ui-tars agent-tars

• Updated Oct 9, 2026
• TypeScript

Caffe: a fast open framework for deep learning.

machine-learning deep-learning vision

• Updated Jul 31, 2024
• C++

Automate browser based workflows with AI

python api workflow automation browser ai selenium computer vision gpt browser-automation rpa puppeteer powerautomate playwright llm

• Updated Nov 12, 2026
• Python

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

search agent ai memory vision vlm searchengine multimodal rag

• Updated Nov 11, 2026
• Python

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

react javascript android ios instagram library snapchat typescript react-native camera native scanner qrcode barcode ml vision qr react-native-camera jsi worklet

• Updated Nov 9, 2026
• TypeScript

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）。

ocr vision glm image-to-text harness dsh codex multimodal cordis vision-transformer deepseek agent-skills claude-code claude-skills pi-agent openclaw harness-engineering hermes-agent text-only-llm dsh-plugin

• Updated Nov 7, 2026
• TypeScript

[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

audio python agent compression video retrieval memory mcp knowledge-graph vision semantic-search multimodal rag llm simplemem lifelong-memory

• Updated Jul 24, 2026
• Python

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

python raspberry-pi tensorflow keras vision self-driving-car cv2 donkeycar jetson-nano

• Updated Nov 9, 2026
• Python

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

transformers vision pruning model-compression efficient-deep-learning llm

• Updated Sep 7, 2025
• Python

👨🏻‍💻 Examples of new iOS 11 APIs

swift vision xcode9 ios11 arkit coreml core-nfc

• Updated Dec 31, 2021
• Swift

The Open Source Framework for Machine Vision

python computer-vision cv image-processing vision visionprocessing

• Updated Dec 20, 2024
• Python

⬆️ Media Capture in Swift

swift ios instagram snapchat video camera custom photography augmented-reality ar media avfoundation capture vision nextlevel mixed-reality coreimage arkit tiktok

• Updated Jun 8, 2026
• Swift

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

kotlin java appengine video cdn auth samples vision translate automl

• Updated Nov 11, 2026
• Java

Visual intelligence for your home.

notifications ai smart-home vision home-assistant multimodal cctv-detection hacs-integration llm

• Updated Nov 11, 2026
• Python

Python code to fuse multiple RGB-D images into a TSDF voxel volume.

cuda artificial-intelligence vision rgbd 3d 3d-reconstruction depth-camera volumetric-data 3d-deep-learning tsdf kinect-fusion

• Updated Feb 18, 2023
• Python

A vision library for genicam based cameras

c video camera gstreamer gobject-introspection glib gtk3 vision gobject usb3 gige meson genicam

• Updated Oct 23, 2026
• C

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.

vision dsh multimodal deepseek-harness dsh-plugin

• Updated Nov 12, 2026
• JavaScript

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

agent opencode vision glm codex multimodal vision-language-model deepseek computer-use agent-skills claude-code harness-engineering text-only-llm dsh-plugin

• Updated Oct 13, 2026
• Python