Official Node.js client for Moondream, a fast and efficient vision language model.

Model-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable —

Out-of-tree dsh provider plugin: a DeepSeek gateway route that claims image input and transparently describes pasted images through a configured vision-language model (e.g. Qwen-VL) before the text-only DeepSeek wire sees them.

Local Vision image descriptions for DeepSeek Harness: a vision-language model on your own machine tells a text-only model what each image shows, beyond the text OCR can read

Local vision-description provider for DeepSeek Harness: a persistent MLX vision-language model on Apple Silicon, so a text-only model can be told what an image shows

Give text-only LLM agents eyes: an MCP server + CLI that describes images through a vision-language model (VLM) API.

Model-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable —

Local Vision-Language Model module for browser-ai - image understanding

No description provided.

Model-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable —

Name scanned receipt PDFs by reading the rendered image with a vision-language model (local Ollama or Anthropic API)

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

VLA vision-language-action inference addon for QVAC (ggml backend)

Per-model capability declarations (image input and reasoning efforts) for custom pi-ai providers, edited in place on the Models settings cards; writes the official llm-pi-ai settings namespace, no DSH source changes.

Official Node.js client for Moondream, a fast and efficient vision language model.

Google Cloud Vision API client for Node.js

React Native Vision Camera plugin for on-device text recognition (OCR) and translation using ML Kit. Maintained fork of react-native-vision-camera-text-recognition

Sanity plugin for running/debugging GROQ-queries against Sanity datasets

VisionCamera is the fastest and most powerful Camera for react-native.

DeepSeek Harness 外置视觉模型插件：inspect_image 把本地图片或 http(s) 图片 URL 发给任意 OpenAI 兼容端点，视觉模型看图的文字回答直接带回对话；附 Web UI 设置栏。