#vision

Multi-Model Visual Understanding MCP Server, GLM-4.6V, DeepSeek-OCR (free), and Qwen3-VL-Flash. Provide visual processing capabilities for AI coding models that do not support image understanding.多模型视觉理解MCP服务器，GLM-4.6V、DeepSeek-OCR（免费）和Qwen3-VL-Flash等。为不支持图片理解的 AI 编码模型提供视觉处理能力。

Use your X Premium or SuperGrok subscription in pi—with automatic vision routing for text-only models.

📷 📐 Geometric models of cameras for photogrammetry

Geometric models of OpenCV/ROS cameras for photogrammetry

Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.

AI vision GUI automation for browsers, mobile apps, desktops, and games — no DOM, no selectors. Standalone or on top of Playwright / Selenium / Appium / pytest.

Library for working with Event-based camera data

AI vision GUI automation for browsers, mobile apps, desktops, and games — no DOM, no selectors. Standalone or on top of Playwright / Selenium / Appium / pytest.

DLT (direct linear transform) algorithm for camera calibration

Codex vision bridge for DeepSeek V4 Flash: give text-only DeepSeek image capability in Codex. Local proxy turns pasted images and view_image into text via free GLM-4V-Flash or any OpenAI-compatible vision API. No GPU, no Ollama.

Capability-aware vision + paste extension for the pi coding agent. Delegates image analysis only when the active model is text-only; passes through natively for multimodal models (zero delegation).

AI SDK provider for Mixlayer — the fully oxidized inference API