All projects on Base matching “browser”

Browser Use: AI browser automation agents in the cloud. POST a natural-language task and an agent navigates websites, fills forms, clicks buttons, extracts structured data, and completes multi-step workflows just like a human. Stealth-enabled remote browsers with CAPTCHA solving, residential proxies, live session view, and optional structured output. Payments top up your balance; managing your ses

Avoid unnecessary browser launches with a lightweight preflight for AI agents. ZeroWorker inspects public pages before browser automation and returns static forms, field constraints, CAPTCHA/SPA signals, DNS/public-network safety checks, and a 3-state routing verdict: http_candidate, browser_likely, or undetermined. Use it to choose direct HTTP or escalate to a browser. No API key required. $0.003

Headless browser rendering for JavaScript-heavy pages and SPAs: full stealth Chromium render, then clean markdown plus title, meta description, and canonical URL. Use when a plain fetch returns an empty shell or a bot wall.

Fetch any public web page and return its main readable content as clean Markdown or plain text plus metadata (title), stripping nav/ads/boilerplate (trafilatura). Optional JS rendering via headless browser for SPAs; markdown or text output. Robots-respecting, public content only — the reader/scraper building block for RAG and agent pipelines.

Read the main content of a page your own crawler cannot reach, as clean markdown. Send a URL and receive the main content of the page as clean markdown, stripped of navigation, advertising and boilerplate. The page is fetched through a French residential IP with a real Chromium browser, so JavaScript-rendered content is fully resol…

Web scraping API for AI agents: read any live web page as clean markdown, text or HTML. Renders JavaScript in our own headless browser, then strips navigation, ads and boilerplate. Use it when a plain HTTP GET returns empty or garbled HTML: single-page apps, dynamic feeds, or content that only appears after scripts run. Also returns the page's HTTP status. Page text is flagged untrusted so an agen

Scrapes any webpage and pulls title, description, canonical URL, OpenGraph + Twitter card metadata, headings, and outbound links from a single URL. Server-side rendering; body content rendered as text, raw HTML, or clean markdown, with optional link extraction. Cheerio-based with no headless browser, so it is fast and cheap, ideal for static pages and SSR sites. For JS-heavy SPAs that need a real

Signed attestation of an Aave V3 position's liquidation risk right now: health factor, debt, collateral, risk tier and the observation time, read live from public RPCs by the FractalAI MIDAS scanner across 6 chains and signed with ML-DSA-65 (NIST FIPS 204). Publicly verifiable by receipt id at /api/midas/alerts/receipt/<id> and in-browser at /midas/proof — proof of "what was seen, when", not a liq

Opens each URL in a cloud browser and returns one tab per URL, in input order, with the title, content type, extracted text, the accessibility tree and a link map. Results over the inline size limit return a preview per tab plus a download reference. Each call is one request.

Create a new browser session ($0.10). Optionally pass sessionId to resume an existing Browserbase session. Returns sessionId (Browserbase session ID) to use for all subsequent calls.

Public sources for agent research: one You.com search plus fetch of up to three public HTTPS pages. Returns structured JSON with page text, metadata, source URLs, fetch timestamps and content hashes for source checking and company research. 0.01 USDC on Base per call via x402 v2; no signup. No browser rendering or synthesized answer. Generate a private request_id locally and reuse it on pending re

Scrape any web page: URL to Markdown / HTML to Markdown for LLM context. Readability article extraction strips nav, ads, scripts, and footers while keeping tables and code blocks. Optional render:true executes JavaScript in a headless browser for SPAs (React/Next/Vue).

AI and search visibility check for any live URL. Loads the page as Googlebot, Bingbot, OAI-SearchBot, PerplexityBot, GPTBot, ClaudeBot, CCBot and a browser, and flags JSON, empty or blocked pages served to crawlers. Checks robots.txt per bot, sitemap, llms.txt, noindex, text visible without JavaScript, tags, and how many pages Google shows. Returns the top 3 fixes in plain words.

Use when a page will not read correctly with a plain fetch — a single-page app, content loaded by JavaScript, or markup so noisy the text is buried. Fetches it with a headless browser (rendering JavaScript) and returns the main readable content as clean Markdown — ideal to feed an LLM as context. JSON body { url } (public http/https), optional include_images (default false). Returns title, final_u

Product price lookup for AI agents: give any public product page URL, get the product's current price, currency, availability (in stock or not), name, brand, SKU and images as clean JSON. The page is rendered in a real browser, so JavaScript stores work, and the store's own schema.org product data is read first. For price checks, price monitoring and comparing stores before you buy.

Twitter (X) video & image downloader — pass a public tweet / X post URL, get direct CDN media links: .mp4 video URLs with thumbnails plus every image in the post, ready to stream, embed, re-host, or download. No scraping or browser automation.

VpsAgent — rent disposable VPS compute via x402, no signup required. Two product lines: ephemeral sandboxes (1h / 6h / 24h, 1 vCPU / 1 GB RAM / 25 GB SSD, $0.50–$5.00) for code execution, CI runs, browser automation; persistent servers (small / medium / large, 30-day or 365-day, $14.99–$449.99) with 4–8 vCPU / 8–24 GB RAM / 100–300 GB SSD, 200–600 Mbit/s unmetered for hosting agents, services, dev

Fetch any public URL and return a clean, readable markdown or JSON extract for AI agents. Pass the target as ?url=<encoded>. Ideal when you need to read webpages, docs, or articles without a browser. Blocks script/style tags, normalizes links and images, strips HTML.

Screenshot any public URL — returns base64 JPEG/PNG with metadata (page title, file size, render time). Full-page scroll capture, CSS selector targeting, device emulation (iPhone 15 Pro, Pixel 7, iPad Pro 12.9), dark mode, ad/cookie banner auto-removal. No browser infrastructure needed, no server costs. Pay per capture. Accepts USDC payments on Base and Solana

NIGHTWATCH Checker: A checker for Aspiring indie builders and side-hustlers who want a step-by-step playbook to go from idea to first sale using NIGHTSHIFT, and are willing to pay $9 for a practical, no-fluff guide.: paste in your work and see exactly what to fix. A browser tool (you get its address in a Markdown file) by NIGHTWATCH, an AI company on NIGHTSHIFT. Free preview: https://getnightshift

Sends a real request to any URL you provide, attaches an Origin header, and reads back all six standard cross-origin permission headers the server returns. Tells you whether cross-origin requests are enabled at all, whether your specific origin is permitted, and shows every permission value exactly as the server sent it. Useful for finding why a browser is blocking a request, confirming a new depl

Check a public website before deploy: test mobile website layout, accessibility, browser errors and screenshots across three viewports

Search products across China B2B wholesale marketplaces (Yiwugo, Made-in-China, DHgate) via a stealth browser farm. Returns structured products: title, price, MOQ, supplier, images (optional CDN URLs). POST with {keyword, siteIds, limitPerSite, saveMedia}. Best for B2B sourcing, price comparison, and dropshipping research.

Render any public URL in a real browser (Chromium): markdown text plus screenshot and evidence URLs. $0.005 USDC on Base per call.

Submit an async browser job (screenshot, markdown, scrape, etc.). Returns job_id + poll_url; poll is free with token — no long x402 request hold. Integrators: POST /v1/firecrawl/crawl or /v1/firecrawl/batch/scrape on browser.gedx402.com.

Independent website QA and pre-handover verification for AI agents. Submit one public website URL. Atinamos loads the real site in desktop and mobile Chromium, checks HTTP and browser failures, failed requests, console errors and warnings, captures screenshots, and returns machine-readable evidence. Poll the returned status_url for results.

Web page scrape: one URL fetched and rendered by Firecrawl (headless browser), returned as markdown, html, rawHtml and/or links. Not charged when the page cannot be fetched.

One-call web research for AI agents: it searches the live web, renders the top pages in a real browser and returns a grounded answer with numbered citations ({answer, sources: [{n, title, url}]}). max_pages sets how many pages it reads (1 to 3, default 3). Pay per call in USDC on Base with x402: no account and no API key.

LLM cost scout: send your monthly OpenAI API spend in USD and get back the flat ChatGPT/Codex subscription tier that absorbs it through the ProxyLLM gateway, the exact new monthly total and savings, the live model catalog, and machine-readable signup steps an agent can complete autonomously (email OTP, no browser).

Website audit bundle for local business websites and lead qualification: performance (browser-measured), security headers and TLS, SEO basics, accessibility and AI-crawler visibility of one public page, with section scores, grades and prioritized findings, in one call.