Document viewer API for Node.js (powered by Java). Powerful, high-performance, cross-platform library for building desktop and web file viewer applications.
Simple node.js API for document processing, powered by PrizmDoc Server.
Small, fast and advanced PNG / APNG encoder and decoder (vendored for @cantoo/pdf-lib)
ROM patcher and toolkit CLI (alias of @rom-weaver/cli, so `npx rom-weaver` works): IPS/BPS/UPS/xdelta/PPF patches, CHD/RVZ/Z3DS/ISO conversion, ROM identification.
Local MCP server that converts HEIC images to non-overwriting JPEG files.
Compress images entering a Pi session to WebP before they are stored in conversation history.
A collection of robust, type-safe utilities and helpers for Node.js, browser, React, and server environments. Includes utilities for color conversion, image generation, cookie management, array manipulation, string processing, environment variables, React
MCP Universal File Converter - 支持压缩包、图片、PDF、Office文档等转换成可上传的 JPG (≤2MB),支持Excel工作表拆分
Files for NestJS: upload tickets, S3/MinIO storage, malware scanning that fails closed, HEIC conversion, abandoned-upload sweeping, signed media links and an image pipeline
Preview local images inside a DeepSeek Harness conversation: bare image paths in prose become thumbnails, a path alone on its line becomes an inline preview, a preview_image tool card shows a gallery, and a full-screen viewer handles zoom, pan, paging and
Official first-party GitHub Action for Zapwebp — automated image conversion, transparency verification, and PR commenting in CI. Powered by @zapwebp/core.
Vision recognition plugin for DeepSeek Harness: paste images into the composer, recognize them via GLM-4V on the host side, and inject the result into the conversation.
Pi extension for AI multimodal generation and media processing via the multix CLI: images, video, speech, music, 3D, document conversion, and ffmpeg/ImageMagick optimization.
JavaScript / TypeScript SDK for EnConvert: read any page or file into agent-ready Markdown, JSON, or screenshots (scored 0.0-1.0), compress images, and convert documents. V2 perception + MCP.
QLLM CLI: A versatile CLI tool for interacting with multiple AI/LLM providers. Features include chat sessions, one-time queries, image handling, and conversation management. Streamlines AI development with easy provider/model switching and configuration.
A quick proof-of-concept React component for image format conversion. Currently converts to WebP. Browser capability dependent.
Convert PDF to images in Node.js (PNG, JPEG, BMP, PPM, ICO, TIFF). Fast, zero-dependency, TypeScript-first with NestJS support.
OpenAI-compatible image generation for DeepSeek Harness: text-to-image, image editing and batch generation, with the pictures rendered straight in the conversation — 通过 OpenAI 兼容接口生图与修图。
Invoice MCP server — extract structured data from PDF & image invoices, create e-invoices (UBL, CII, ZUGFeRD/Factur-X), convert between formats including Excel, and validate against EN 16931.
Convert (almost) anything to PDF — Node bindings with napi
PDF, office document and image conversion (structured text, local OCR) through here-docs, for @searxng-js/sex-scrape
Browser-side image compression with format conversion, resizing, quality control, and size targeting.
Node.js binding for the madeitpx pixel-art image conversion library
MCP server for 500Toolbox - Google Search Console, Bing Webmaster Tools, Yandex Webmaster, PDF/Office conversion, background removal, AI upscaling, screenshots, DNS/SSL/IP lookups, hashing, QR codes and more, for Claude, Cursor and any MCP client.
Model Context Protocol server for the Zactonz APIs: screenshots, web page to Markdown, link previews, DNS, SSL, WHOIS, email checks, QR codes, barcodes, social card images, image conversion and translation as tools for AI assistants.
Convert (almost) anything to PDF — Node bindings with napi
Shared TypeScript type definitions and response helpers for the SVGR image-to-SVG conversion platform.
Dynamic attachment presentation plugin for conversation input, message-image, and trajectory image slots
MCP server exposing imgcli — convert, resize, crop, filter & composite images as native agent tools
Text and image-pin annotations for Gestaltrun Desktop conversations
Lets a picture into the conversation both ways: the agent can send one, and you can drag-select a screen region with ⌥⌘S and attach it to the current conversation.
Browser-native image loading, resizing, transforms, EXIF parsing and encoding with Canvas and OffscreenCanvas.
DeepSeek Harness host plugin: serves a configured workspace/media folder over the web server under /media, so any conversation can display local images by referencing http://<host>:/media/<relative-path>.
A lightweight TypeScript utility class for easy image handling, format conversion, and transformation in browser applications.
Core engine to convert extended MDAST to DOCX. Supports plugins for footnotes, images, lists, tables, and more. Designed for seamless Markdown-to-DOCX conversion.
Fast and powerful CLI for file conversion, image compression, and resizing by isconvert.com
Side-channel image understanding for dsh: the describe_image tool routes one image (file path or conversation attachment) through the harness llm service to a separately configured image-capable model and returns the description as text, so a text-only co
Select a range of a DeepSeek Harness conversation and share it as a branded PNG long image, with draggable magnetically snapping range markers.
Drive native Infinite Canvas Agent conversations and organize reference images and results in a Frame.
Sharp-based image processing for Node.js with EXIF inspection, transforms, encoding and an optional Fastify adapter.
PDF & Image conversion API for developers
Convert any document to Markdown with Microsoft's markitdown CLI — PDF, DOCX, PPTX, XLSX, images (OCR), audio (transcription), YouTube, HTML, CSV, JSON, XML, EPUB, ZIP
Node.js Native Addon for LibRaw - Process RAW image files with JavaScript
Give opencode native image, PDF and document analysis via any OpenAI-compatible multimodal API. Files are sent as-is; the API decides what it can read. No OCR, no conversion.