Tag
68 posts tagged #browser-automation
Browse 68 posts tagged Browser Automation, including practical setup notes, reviews, comparisons, and workflow patterns for engineers working with AI tools.
TinyFish runs hundreds of browser sessions simultaneously with a serverless architecture, scoring 82% on Mind2Web hard tasks against OpenAI Operator 43%.
Agent-first web browser for AI agents. Simulates human typing and mouse movement. Built on Playwright with a CLI for profile and browser context management.
Libretto gives AI coding agents a live browser and CLI to inspect pages, capture network traffic, record actions, and replay them as Playwright scripts. MIT, 877 stars on GitHub.
Open-source browser automation tool by Selenium's creator — gives AI agents a verification layer through CLI, MCP server, or JS/Python/Java libraries.
Intuned is a code-first browser automation platform where an AI agent builds, deploys, and auto-maintains scrapers, RPA scripts, and API integrations for services with no official API.
Smooth is a browser agent API that lets AI tools like Claude Code and Cursor navigate the web through natural language commands instead of low-level browser actions.
Smooth CLI gives AI coding agents a goal-oriented browser that navigates the web via natural language instead of DOM clicks, cutting cost and latency dramatically.
Smooth is a browser agent that runs tasks in 4 lines of code, delivering 7x better speed and cost than traditional browser automation. Built by Circlemind.
Smooth CLI gives AI agents a natural-language browser instead of low-level click-and-type tools. Token-efficient, 20x faster, and handles real web complexity so your agent focuses on goals, not buttons.
Smooth CLI is a serverless browser agent API that lets AI agents like Claude Code navigate the web using natural language instructions, scoring 92% on WebVoyager at 7x lower cost than Browser Use.
Build and run reliable browser automations as code. Coasty is a computer-use API that operates any web or desktop app via screenshots, mouse, and keyboard, no API required.
Open-source browser automation that uses vision LLMs to navigate websites, fill forms, and complete workflows without brittle XPath selectors.
Browserable is an open-source library that gives AI agents reliable browser control — navigation, form fills, clicks, and data extraction — scoring 90.4% on the Web Voyager benchmark.
Orchestra is a desktop studio for browser automation and web scraping. Build flows visually, watch them run live, and export plain Playwright code you own outright.
Waffy is a free, open-source Chrome extension that automates web tasks using AI. Tell it what to do in plain English and it clicks, types, and scrolls through workflows for you. No backend, no subscription. Uses your own API keys.
VibeBrowser MCP connects Claude Code, Cursor, VS Code Copilot, and OpenCode to your actual Chrome profile — cookies, sessions, and all — via a hosted relay. No local browser install needed.
Coasty ranks #1 on OSWorld (85.60%) and ships a production computer-use API with 1,000+ OAuth integrations, MCP server, and a $99/mo flat Unlimited plan.
Skyvern is an open-source AI agent that automates browser workflows using vision LLMs and Playwright, replacing brittle XPath selectors with adaptive visual navigation.
MarinaBox provides secure, isolated browser and desktop environments for AI agents. Docker-based, Python SDK included, works with Playwright and Selenium.
Smooth CLI replaces low-level browser automation with natural language commands, letting AI agents handle web tasks without context-window bloat or token waste.
Browser MCP pairs a Chrome extension with an MCP server to let Cursor, Claude, VS Code, and Windsurf automate your real browser profile with stealth.
Six Playwright tools let AI agents open browsers, read pages, and act. 55% lower cost than alternatives.
Turn any browser action into a reusable MCP tool. Codify records Playwright workflows and exposes them as JSON-driven tools for AI agents like Claude and Cursor.
Runtime uses predefined DOM attributes as skill gateways to automate browsers, sidestepping expensive LLM reasoning at execution time.
Safari MCP drives your real Safari browser from any MCP-compatible AI coding agent. 97 tools, no Puppeteer or Playwright needed, ~60% less CPU than Chrome.
OpenBrowser is an open-source AI browser automation framework using a CodeAgent architecture to control any browser via CDP, with MCP and Python 3.12+.
Intuned uses an AI agent to generate production-ready Playwright scrapers in TypeScript or Python, with self-healing, captcha solving, and scheduling built in.
A desktop studio for browser automation and web scraping. Build flows visually, watch them run live, and export plain Playwright code you own forever.
Tabstack gives AI agents structured web data and browser automation via a single API. Built by Mozilla, it handles the messy crawling layer so you can focus on the agent logic.
Vessel is an open-source browser built from the ground up for AI agents. It provides durable sessions, MCP control, and BYOK for autonomous web browsing on Linux, Mac, and Windows.
Cloud-hosted AI agents that control a real browser to automate web workflows — prospecting, outreach, social media, and lead generation without code.
shot-scraper, Simon Willison's screenshot tool, just gained a video feature. Define WebM demos in YAML, automate setup steps, and record smooth browser walkthroughs automatically.
Mochi.js is a Bun-native browser automation library that generates deterministic Chrome fingerprints, routes all traffic through Chromium itself, and uses biomechanical models for human-like input.
Simplex provides API-first browser automation infrastructure — headless browsers, proxies, and captcha solving without managing your own browser fleet. YC S24.
Record browser workflows or describe them in plain English. Tasker is a free, MIT-licensed desktop agent that uses AI to execute multi-step web tasks. Supports Claude, GPT-4o, and Gemini.
Kampala from Zatanna captures the real network traffic behind any web portal and exposes it as a stable, callable API endpoint for AI agents.
A Chrome Extension that exposes your browser as a remote MCP server, letting any AI agent drive web tasks without context switching. BYO-subscription model.
Agentyc is a lightweight MCP-first browser automation runtime built in Rust. No API keys, no LLM dependency — just CDP, stdio MCP, and 61 deterministic tools.
Browser Harness connects an LLM directly to your Chrome browser via CDP, letting the agent write its own helper code when tasks require custom logic.
An AI browser agent that browses the web in plain English. Telegram bot, REST API, free tier. Automates scraping, bookings, forms, and price monitoring without code.
Gepetto is an open-source CLI tool that uses natural language tasks and a headless browser to automate QA testing, liveness checks, and data scraping. MIT licensed.
OpenBrowser lets any LLM control Chrome via natural language, using a CodeAgent that writes and executes Python code against live CDP sessions. 2-6x fewer tokens than Playwright MCP.
Axiom.ai lets you build browser bots via no-code drag-and-drop, Puppeteer/Playwright code, or plain English descriptions to Claude. YC W21 startup, cloud or self-hosted.
Gabriel Operator is a teach-by-demo browser automation tool. Click through a task once and it becomes a reusable AI-powered workflow you can run with parameters, loops, and branches.
Actionbook turns any website into an AI-agent-operable page via MCP connector and Chrome extension. No CLI install, handles logins and paywalls, 10x faster than traditional browser agents.
Browser Use is an open-source AI agent framework with 99K GitHub stars that controls real browsers via Python. This guide covers setup with Cursor and Claude Code, CLI usage, and when to pick open-source vs cloud.
BrowserOS is an open-source Chromium fork with built-in AI agents, MCP server, scheduled tasks, and 40+ app integrations. Privacy-first, BYOK, runs local models via Ollama.
Skyvern is an open-source AI agent that automates complex browser-based workflows using LLMs, supporting multi-step tasks, form filling, and API integrations.
Record browser workflows in a cloud browser and compile them into deterministic automation code—no AI needed at runtime. Built for reliability over LLM unpredictability.
Flowtest.ai is an AI agent that browses your website like a real user, detects issues, and self-heals when layouts change.
Scalable browser infrastructure for AI agents. Launch headless Chrome sessions via API, run web automation at scale without managinginfra.
A code-first browser automation platform with an AI agent that builds and maintains your automations as deterministic, production-ready code.
Superhighway serves live web search to AI agents through the x402 payment protocol, charging per-call in USDC with no API key required.
Owl Browser is a self-hosted Chromium engine with source-level fingerprint spoofing, 256 parallel sessions, built-in CAPTCHA solving, and drop-in Playwright migration.
Zatanna reverse-engineers any web portal's network traffic and generates headless APIs that AI agents can execute in seconds. No UI required.
YC S22 startup Intuned lets you build, deploy, and maintain browser automations as code. An AI agent writes Playwright scripts and auto-heals them when sites change.
Rtrvr.ai exposes your Chrome as a remote MCP server so any AI agent can drive it. Learn how the architecture works and how to set it up in minutes.
Airtop lets AI agents drive cloud browsers via Puppeteer, Playwright, or natural language. Handles bot detection, proxies, and captchas. Full setup guide, pricing breakdown, and alternatives.
Propolis runs swarms of browser agents that collaboratively explore your web app, report bugs, and write end-to-end tests for your CI pipeline.
BrowserBook is a Mac IDE that writes deterministic Playwright scripts instead of AI agents that drift. Built by a YC F24 startup that automated healthcare and.
Mozilla-backed API that abstracts complex web browsing for AI agents—handles proxies, hydration, DOM parsing, and returns clean structured data instead of raw.
Notte records your browser interactions once and compiles them into deterministic automation code — no LLM at runtime, no fragile selectors.
Propolis runs swarms of AI browser agents that explore your web app, find bugs, and generate Playwright e2e tests for your CI pipeline. Here's how it works.
Hyperbrowser spins up hundreds of headless browser sessions in secure isolated environments with sub-second launch times, captcha solving, and residential.
BrowserBook is a Mac desktop IDE for writing, debugging, and replaying Playwright-based browser automations with deterministic test execution.
Simplex is a YC S24-backed browser automation platform that lets developers control headless browsers programmatically for testing, scraping, and AI agent.
Smooth CLI replaces low-level click/type/scroll with natural language commands. 20x faster, 5x cheaper, and works with Claude Code, OpenClaw, and any AI agent.
Cloud browsers built for AI agents that need to navigate, scrape, and interact with the web at scale. Handles proxies, stealth detection, and concurrent.