AI SDK (Vercel) provider for Mixlayer — open-weight text and vision model inference over an OpenAI-compatible endpoint.

MCP stdio server for image recognition via an existing vision model

Give text-only pi models vision — describe images with a vision model you pick via an interactive picker, then hand off the text description to non-vision models

LLM-native image optimization MCP server. Reduces vision model token consumption by snapping to tile boundaries.

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

Pi extension — describe images via vision model when your active model cannot see images directly

SimMan (Simulated Manual) — selectorless vision-cursor testing for web. A vision model is the eyes, a real cursor is the hands.

MCP server exposing 7 vision tools (analysis, UI→code, OCR, error diagnosis, diagram, data-viz, diff) — works with any Anthropic-Messages-compatible vision model

MCP server for Alibaba Qwen3.7-plus vision model via DashScope Anthropic-compatible API

OpenCode plugin that lets text-only models handle image uploads by describing them via a vision model before they reach the LLM.

Accurate spatial reasoning over images — vision model extracts bounding boxes, LLM calculates exact distances

pi package adding a describe_image tool that lets non-multimodal models delegate image analysis to a vision model

MCP Server for Image/Video Understanding using Doubao Vision Model

MCP server that bridges text-only models with vision capabilities — image recognition and web page reading via any OpenAI-compatible vision model.

OpenAI-compatible MCP server for custom vision model endpoints

Browser-agnostic Playwright/Puppeteer captcha solver. Detects the captcha, reads the grid with a fine-tuned Qwen3.5-9B vision model on vLLM, and clicks through to a token.

MCP server providing image recognition for Claude Code via MiMo 2.5 vision model

OpenAI-compatible vision model provider for UseChat.

MediaPipe Vision Tasks. See the privacy notice at https://goo.gle/mediapipe-privacy.

A Node.js vision-model toolkit: detection/tracking with zone triggers, visual question answering, captioning, and image embeddings (joint and vision-only), importable directly with no HTTP required.