Package to connect and trace LLM calls.

Collection of layout emotion components

Codemods to ease upgrading a RedwoodJS Project

## Purpose and Vision

Wasm JPEG XL encoder and decoder supporting the browser. Repackaged from Squoosh App.

Forma 36 FCSS

Dynamsoft Capture Vision (DCV) is a comprehensive SDK that integrates various functional products. It encompasses image capture, content understanding, result parsing, and interactive workflow. Essentially, DCV processes images to extract specific informa

A TypeScript MCP server that gives text-only LLMs image understanding through StepFun vision models.

VisionCamera Frame Processor Plugin to read barcodes using MLKit Vision Barcode Scanning

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).

An antd compatible media query hooks

VisionCamera Frame Processor Plugin to provide OCR support

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

eslint plugin for Redwood rules.

Flywheel UI elements provided as Angular components and native web components

Cross-script confusable detection, slug safety, and LLM Denial of Spend defence. Zero dependencies.

TypeScript definitions for vision

This package encompasses machine learning models, such as the Convolutional Neural Networks (CNN) model used for text recognition, empowering various foundational products under DCV architecture.

Give text-only LLM coding agents (DeepSeek V4 Flash/Pro, Qwen, Kimi) vision via any multimodal model. One analyze_image tool — paste or drag in one or many images, analyzed in a single call, scoped to the current session. Works with Claude Code, opencode,

Use GLM-4.6V-Flash to convert images to text for non-vision AI models