A collection of useful tools for accessibility testing and debugging in the browser, online and desktop
Semantic UI automation and lightweight accessibility snapshots for LLM agents to interact with Web and Desktop applications.
An open-source VS Code Extension integrating accessibility awareness into the development process. Generate accessibility trees for projects, receive feedback on accessibility issues, and implement fixes all within the dev environment. Or, share the accessibility feedback with collaborators via the extension's companion dashboard on our website.
Webpage accompanying the A11yRoot VS Code Extension. The webpage allows for the sharing of accessibility trees/analysis (generated via the extension) through direct links or secure accounts. Utilize to bring the power of the extension to collaborators and stakeholders.
Agent-ready CLI for static page inspection, search triage, and browser handoff.
Stateful browser runtime for AI agents built on Playwright, with stealth interaction, structured page state, resilient automation, and debug observability.
A browser automation-to-CLI framework. Leveraging browser-use, LLMs, and the CDP protocol to automate the entire workflow: exploration, code synthesis, and execution.
Python SDK for the Computer Use Protocol
⭐ Awesome A11Y Book & Course with interactive CodeSandboxes. Learn A11Y online with pleasure.
Give any AI agent a real browser. REST API + Web Dashboard + Vision AI. Control browsers via Playwright from OpenClaw, Hermes, or any LLM. Built with Next.js and TypeScript.
TypeScript SDK for the Computer Use Protocol
Playwright, but built for AI agents: the browser API models already know, token-efficient a11y snapshots, and scroll-driven collection over the network. Zero-port CDP underneath.
Browser bridge for AI agents — control Chrome via accessibility tree, navigate, click, fill, screenshot, and more
Connect an AI agent to your live Chrome session to read and interact with open tabs without extra setup or browser relaunch.
Human-like browser control for AI agents — verify-first (proves every action worked), with an MCP server + JS & Python SDKs. Playwright + native + extension. MIT.
Give your AI coding CLI eyes into web portals. No cloud. No storage. Read-only.
Full-featured headless browser for OpenClaw AI agents. Accessibility tree snapshot, @ref clicks, tabs, JS execution. No vision model needed.
MCP server that drives a Playwright browser for LM Studio agents — standalone browser or CDP attach to a running Brave/Chrome, with accessibility-tree snapshots
Standalone MCP server for image recognition via LLM vision API — OCR, image analysis, structured extraction, screenshot-to-accessibility-tree
To associate your repository with the accessibility-tree topic, visit your repo's landing page and select "manage topics."