Browse agents

Headless PyMOL for molecular visualization, GROMACS/LAMMPS trajectories and clathrate-hydrate cage analysis, including H-bond networks and order parameters.

Search Bilibili content, with LangChain integration examples.

Native Safari browser automation without a Chrome dependency.

Stealth automation of unmodified Chrome over raw CDP, using accessibility-tree element refs; can attach to a running Chrome to reuse logged-in sessions.

Drive a local Playwright browser through residential proxies with a chosen exit country or city and a sticky identity per task.

Browser automation using Puppeteer, supporting local and remote browser connections.

Control your real, logged-in Chrome browser via an extension, with multiple concurrent color-coded sessions.

Tactile browser control and multimodal visual vision MCP bridge for Google Chrome.

Code-aware browser testing that reads routes, forms and existing tests, runs Playwright scenarios, and keeps regression history and screenshot reports.

Web scraper that returns clean Markdown, distributed as a single binary.

Visual, multimodal web scraping without CSS selectors, plus phishing and crypto drainer detection.

Web scraping, Llama 3 digests and Twitter intelligence, paid per call in USDC via x402 on Base.

Undetected Chrome automation via nodriver for anti-bot protected sites: accessibility snapshots, input automation, network inspection and persistent sessions.

Web scraping: clean content extraction, CSS-selector scraping, Playwright screenshots, link and metadata extraction, and Google search.

Browse the web with filesystem commands (ls, cd, grep, click) by mapping Chrome's accessibility tree to a virtual filesystem via an extension.

Access and organize open tabs, bookmarks and recent links across macOS browsers via the SupaSidebar app.

Browser automation using Playwright.

Lightweight browser automation with zero dependencies.

Token-budgeted web fetching that routes between Trafilatura, Jina Reader, Firecrawl and pypdf by URL, with token estimates, caching and truncation.

One-click browser-tab screenshots, captured by a companion extension and served locally to the model on demand.

Fetch web content as clean Markdown through a multi-tier fallback chain, handling tweets, YouTube, arXiv, PDFs and regular pages.

Self-hosted stealth browser built on a Firefox fork with fingerprint spoofing, shadow-DOM-aware page reading, login state detection and evidence recording.

Browser automation using Playwright, tailored for LLMs.

Headless browser automation and web scraping via the Browserless smart scraper API.

Control browsers with Selenium using natural language, for testing, automation and multi-user scenarios.

Browser automation with browser-use, including a Dockerfile to run Chromium in Docker with a VNC server.

Convert URLs into screenshots, PDFs or structured extracts.

Intent-aware visual verification: declare what a UI change should affect, then diff the page against a baseline and flag changes outside that scope.

Rent residential Chrome browsers run by real people, with real fingerprints and residential IPs.

Record your authenticated browser session (rrweb DOM, console, network) to local SQLite with PII masking, so coding agents can query it or drive the browser.

Generate screenshots, PDFs, OG images and narrated video recordings.

Control Chromium-based browsers such as Arc, Vivaldi and Brave via an extension: navigate, click, read pages, run JavaScript and record GIFs.

Deterministic attack-surface perception for AI security agents. Attaches over `chrome.debugger` to the Chrome you're already logged into (cookies, MFA and SSO already done) and turns the live page into a short numbered interaction graph an agent can act on (`[03] button 'Sign In'`), with CSS selectors kept server-side and out of the model's context. Cross-identity tools (`compare_identities`, `replay`) flag a byte-identical response across two logged-in users as a cross-tenant IDOR, and `scan` maps the attack surface from the CLI. No LLM in the parse; 71% fewer tokens than Playwright's ARIA snapshot mode.

Web search, reading and research through stealth-patched Chrome: strips hidden text, ranks passages across sources and returns SHA-256 provenance receipts.

Automate YouTube operations, also available as a CLI.

A browser shared by a human and an AI — same tabs, same live session; 24 MCP tools (snapshot, click, type, screenshot, tabs, annotations), built-in models or any MCP client, Esc takeover.

Browser automation and web scraping using Playwright.

Control the user's Firefox browser via a companion extension.

In-page debug bridge for web apps: read the DOM, console logs and network requests and interact with the page, in any browser or Cypress/Playwright run.

Interact with Apple Reminders on macOS.

Firefox automation via WebDriver BiDi: snapshot-based interactions, network monitoring, console capture and screenshots for testing and scraping.

Drive your logged-in Chrome via an extension: compact element refs, visual regression, accessibility, SEO and security audits, and network mocking.

Design debugging in Chrome: which CSS rule wins (with file and line), its blast radius, scoped fix selectors, live fix trials and WCAG contrast audits.

Self-hosted web scraping: scrape, extract, crawl, map, search, academic papers, research and monitoring, with a tiered fallback including Cloudflare bypass.

Website testing with Playwright: assertions, auto form-fill, persistent logins, network mocking, and accessibility, SEO, GEO and Lighthouse audits.

Zen Browser automation via WebDriver BiDi: navigation, form filling, screenshots and JavaScript evaluation.

MCP server + Chrome extension (MV3) that lets coding agents read pages through the user's real, logged-in Chrome; stdlib-only, local.

Connect to the Perplexity Comet browser for agentic browsing, deep research and real-time task monitoring.

Pay-per-call web scraping via x402 on Base, with structured extraction, screenshots, metadata, browser sessions and workflows.

Drive your open, logged-in Chrome with token-budgeted page reading, complex SPA form and survey handling, and headless Ubuntu support.

Virtual staging for real estate: stage empty rooms, turn floor plans into 3D renders, classify room images, write property descriptions and suggest styles.

Compile browser automation into deterministic plans that run in your logged-in Chrome without runtime LLM calls, detecting drift when sites change.

Token-efficient browser automation: semantic page snapshots and stable element IDs instead of raw DOM or screenshots, driving Chrome over CDP.

Create, run, debug and manage Selenix browser automation tests through natural language.

Local-first web reading escalating from HTTP to a real browser when blocked: clean Markdown, site crawls, search, row extraction and local CAPTCHA handling.

Autonomous browser automation.

Fetch YouTube subtitles and transcripts for AI analysis.

Get transcripts and metadata for summarization and content analysis.

Minimal MCP server and client implementation using Azure OpenAI and Playwright.

Web intelligence API: screenshots, PDF generation, page metadata and specialized extractors for news, social media, search results, prices and more.

Headless browser for AI and web automation with a built-in MCP server.

Browser agent with human takeover via noVNC, reusable auth profiles, approval and audit controls, and isolated Docker sessions.

Control Safari via a web extension: navigate, read pages, click elements, fill forms and manage tabs, without Playwright or WebDriver.

Read any URL as a clean AIDocument (Markdown plus structure) through Lyrenth's cached index.

Web scraping with escalating fetch tiers on detected blocks, returning clean Markdown or saving large scrapes to SQLite for read-only SQL queries.

Browser automation for your existing Chrome or Firefox via CDP and BiDi, with stealth mode, Lighthouse audits, YAML action batching and raw protocol access.

Playwright browser automation: interact with web pages through structured accessibility snapshots.

Autonomous, goal-driven LLM web crawler with stealth browsing, distributed as a single binary.

Interact with your local browsers.

iOS Safari debugging via ios-webkit-debug-proxy with WebKit Inspector Protocol support: DOM, CSS, network, storage, debugger and more.

Web scraping, crawling and search API: extract content as Markdown or JSON, batch-process URLs and get answers with citations.

Control the user's real Chrome browser via an extension, reusing existing sessions, logins and cookies.

Security-hardened Chrome automation and logins with post-quantum encryption, a credential vault, memory scrubbing and audit logging.

Web automation through Selenium WebDriver.

Accessibility-tree browser automation with deterministic snapshots, human approval gates, redacted audit logs and console, network and Web Vitals monitoring.

Web search using Google search results.

Lightweight native browser that runs JavaScript, follows links, fills forms, manages cookies and returns low-token BlockMaps, without Chrome.

Real-browser QA audits of a URL: broken signup, login and checkout flows, console errors, missing analytics, security headers, tap targets and accessibility.

Record actions on any website and replay them in headless Playwright, with encrypted credentials and AI-based selector healing.

Web scraping, structured data extraction and screenshots with JavaScript rendering, residential proxy rotation and automatic retries.

Diagnostics for MCP servers: discover client configs, test connections, audit security issues and benchmark latency.

Render terminal output, syntax-highlighted code, web pages, Markdown, HTML and git diffs as PNG, JPEG, PDF or GIF locally via Playwright.

Integration with Apple Shortcuts.

Compress web page HTML into compact structured maps that preserve actionable elements, so agents can read and interact with pages using fewer tokens.

MCP server plus Firefox add-on that lets your agent work in your real, logged-in Firefox: accessibility snapshots with stable element refs, logins filled by alias from a local vault, hardened mode by default. Free for personal use.

Fetch web page HTML, AI-parsed JSON or Google results through the ScrapeUnblocker anti-bot API.

Capture web pages as images or PDFs with element targeting, device and viewport controls, location selection, page interactions and blocking options.

Browser automation, testing and bot-detection bypass using SeleniumBase CDP Mode with Chromium, including click-based CAPTCHA solving.

Selenium WebDriver automation with assertions and self-healing locators, plus code generation for Java, Python and C# test frameworks and CI pipelines.

Chrome automation over raw CDP with multiple tabs, cached accessibility-tree refs, server-side multi-step flow execution and a Python scripting API.

Website screenshots via Chromium with full-page capture, country-specific proxies and automatic ad and cookie-banner removal.

Let coding agents drive VS Code's Integrated Browser alongside you: snapshots, mouse and keyboard, forms, tabs, screenshots, console and network logs, a visible agent cursor, and click-to-source for React (Vite, Next.js).

Capture any URL as PNG, JPEG, WebP, PDF or HTML, diff page versions to catch visual regressions, and get AI page summaries.

Detect and solve Cloudflare Turnstile challenges: inspect whether a page uses Turnstile or another CAPTCHA and get a solved token when needed.

Playwright MCP-compatible browser automation using CloakBrowser Chromium.

Visible local browser automation in your signed-in Chromium profile, with recovery and optional policy and audit controls.

Self-hosted stealth Chrome automation via Patchright: parallel persistent profiles, encrypted credential vault with 2FA, and prompt-injection scanning.

Capture websites as PNG, JPEG, WebP or PDF with device emulation, dark mode, ad blocking and cookie banner removal.

Render any URL or raw HTML as PNG, JPEG, WebP or PDF, with batch processing, geo-targeting and async webhooks.

Drive a browser or Expo/React Native app alongside your dev server on one correlated timeline, lining up frontend errors with backend stack traces.