Best AI agents for browsing the web (2026)
Agents that open pages, click, type and fill in forms in a real browser so you don't have to. We list 104 tools for browsing the web below, each with a link-checked page, pricing as the maker states it and alternatives.
Updated
104 tools: 70 open source, 1 source-available, 19 free or freemium, 8 paid, usage-based or enterprise, 6 pricing on the maker's site.
Browser automation (64) See the full list →
LVLZ
LVLZ is a personal AI agent you run by messaging it like a person, on iMessage or WhatsApp, as a text, voice note or call. It runs errands on real websites in a cloud browser, such as bookings, forms and shopping, turns messages into tasks and projects, fills a CRM from your conversations, and runs routines like a morning brief or a price watch. Everything it does lands in a web workspace, its memory can be read, edited and exported, and it asks before paying, contacting someone new or deleting anything, with cards and passwords kept in an encrypted vault.
Added
Cumora
Cumora is a team chat app where AI agents are members of the workspace rather than a chat box you prompt. Each agent gets a persona, its own private memory and files, a status, and a schedule on which it wakes up, reads the room and decides whether to message someone, post an idea or pull a small group together. Agents can message each other, and you can read those side conversations. People join by email or link, agents can be grouped into teams and given projects, and the same live workspace runs on desktop, in the browser and on a phone. It is free during an invite-only preview.
Added
IDA MCP (Hex-Rays)
IDA MCP is Hex-Rays' official MCP server for the IDA disassembler and decompiler. It lets AI coding agents and people work on the same IDA databases at the same time, so an agent can inspect functions, types and decompiled code, rename and annotate, and coordinate analysis across several related binaries in one session. It works with the IDA GUI through a plugin or headless through idalib, installs with Hex-Rays' hcli tool, and needs IDA 9.4 or later.
Added
Kernel
Cloud browsers for AI agents: launch headless or live-view Chrome sessions in milliseconds with stealth mode, persistent profiles and replays, controlled through an API, CLI or MCP server. Free tier plus usage pricing.
Added
Libretto
An open-source CLI, debugging agents and browser tools for building and maintaining reliable web integrations, helping coding agents inspect real pages and write automations that keep working.
Added
Agent Sandbox (Kubernetes)
A Kubernetes project that adds a Sandbox resource for running isolated, stateful agent workloads such as code execution and browsers, with warm pools and fast startup on your own cluster.
Added
AgentBay
Alibaba Cloud's cloud sandbox service for agents, offering ready-made browser, Linux and Windows desktop, mobile and code environments that agents control through an SDK or MCP.
Added
Dodaios
Open-source desktop agent OS for Windows, macOS and Linux (formerly Personal Jarvis): talk to it and it runs your coding CLIs side by side, your browser and your apps, with offline Whisper speech, a local wiki memory and support for Ollama, Claude or ChatGPT subscriptions.
Added
BrowserStack MCP
BrowserStack's official MCP server, letting coding agents run manual and automated tests on real browsers and devices, debug failures and check accessibility from the IDE.
Added
Grok Bot Jev Router
Grok Bot Jev Router is an open-source Python reference router that puts TypeSafe Jev in front of Grok Bot as a cheap decision layer. Before expensive research, browser, retry or subagent work, Jev classifies the request and returns an explicit action such as reuse a cached result, stop a failing retry, cap research, run a deterministic step, or ask a human. It starts in shadow mode that only logs decisions, has an active mode for a Grok Bot skill that honors them, and includes a kill switch. It never sends, pays or deletes anything itself.
Added
SEAL
SEAL is an MCP server (npx sealnet-mcp) that lets AI agents send and request files and secrets with end-to-end encryption. After pairing, the default delivery route sends the file to the user's SEAL inbox and returns a handle to the model. Also has a browser app, CLI and SDK; free up to 1 GB per seal.
Added
CloudCLI
A web and mobile interface for Claude Code, Codex and Gemini CLI, so you can run and steer coding sessions from a browser or phone. Self-host free or use the hosted CloudCLI service.
Added
thClaws
An open-source AI agent workspace in native Rust that runs locally as a GUI, CLI, headless service or web app from a single binary, with multiple model providers.
Added
pooled
Peer-to-peer LLM inference in the browser: pool your laptops, phones and other devices into a room to run large open models for chat and coding agents, with no GPU server.
Added
Webcmd
Browser layer for AI agents that learns how each website works as agents use it and saves that as local memory to make later runs faster and cheaper.
Added
Hyperbrowser
Cloud browsers and isolated sandboxes for AI agents that you start in one call and drive with Playwright, Puppeteer or any agent.
Added
Lightpanda
Headless browser written from scratch in Zig for AI agents and automation, built for speed and low memory rather than forked from Chromium.
Added
CloakBrowser
Chromium build with source-level fingerprint patches, used as a drop-in Playwright or Puppeteer replacement for agent browsing.
Added
Browser Use Web UI
Gradio web interface for the Browser Use agent that runs AI browser automation tasks with many LLM providers and your own browser.
Added
Playwriter
Chrome extension and CLI or MCP that lets agents control your own logged-in browser by running Playwright snippets.
Added
Qwen-UI-Agent
Tongyi foundation GUI agent model that operates mobile, computer and browser interfaces, trained and evaluated on real devices.
Added
Ui.Vision RPA
Browser and desktop automation extension with OCR and image recognition, plus an MCP server so AI agents can create and run macros.
Added
Notte
Browser infrastructure for AI agents: stealth cloud browsers with CAPTCHA solving and proxies, a Playwright-based framework and serverless automations.
Added
Terminator
Desktop automation library and MCP server that lets AI assistants control any Windows app through the accessibility tree, like Playwright for the desktop.
Added
Agent-E
Emergence AI's web agent that automates tasks in the browser through hierarchical planning.
Added
Browserable
Open-source JavaScript browser automation library for AI agents.
Added
Fellou
Agentic browser that carries out multi-step tasks across websites, runs deep searches and turns results into reports.
Added
HARPA AI
Chrome extension browser agent that combines models like GPT, Claude and Gemini to automate web tasks, searching, writing and summarizing.
Added
Sigma AI Browser
Free private web browser with a built-in AI agent, local AI and ad blocker.
Added
AIO Sandbox
All-in-one Docker sandbox for AI agents that combines a browser, shell, files, MCP, VS Code Server and Jupyter in one container.
Added
OpenAgent
Self-hostable personal AI assistant shipped as one binary, combining LLMs, a knowledge base and agent loops with computer, browser and coding use.
Added
Atomic Agent
Local-first AI agent that drives your browser, edits files and runs approved commands using local open-weight or cloud models.
Added
HolyClaude
Containerized AI coding workstation with Claude Code, a web UI, a headless browser, several AI CLIs and 50+ dev tools.
Added
Skales
Personal AI agent for desktop and mobile that codes, automates the desktop and browser and runs scheduled tasks with local or cloud models.
Added
BrowserGym
ServiceNow's Gym environment for building, testing and evaluating web agents across browser benchmarks.
Added
Orke
BOMTOBE's free desktop workspace for Claude Code, Codex and other coding agents: terminal sessions, an in-app browser the agent can use, a Git review window and scheduled AI employees.
Added
Instinct
Personal assistant you text or call that works across your Gmail, calendar, documents and a cloud browser to get tasks done.
Added
Frontman
Browser-based AI coding agent: click an element in your running app, describe the change, and it edits the source with hot reload.
Added
Browser Harness
Agent skill from the Browser Use team that lets Claude Code, Codex or Cursor drive your own logged-in Chrome to click, type, read pages and download files.
Added
ego lite
Free macOS browser where Claude Code or Codex run automation tasks in their own isolated Spaces next to your tabs, reusing your logged-in sessions through an agent skill.
Added
Browser Use
Library that lets AI agents control a web browser.
Added
Chrome DevTools MCP
Official MCP server that lets coding agents control and inspect a live Chrome browser through DevTools for debugging and performance work.
Added
UI-TARS-desktop
ByteDance's open-source multimodal agent stack, including a desktop app and Agent TARS for controlling computers and browsers.
Added
Playwright MCP
Microsoft's MCP server giving agents browser control via Playwright.
Added
OpenCLI
Turns websites into CLI commands and lets agents use your logged-in browser.
Added
Stagehand
Browser automation framework mixing code with natural-language actions.
Added
Nanobrowser
Open-source Chrome extension agent that automates web tasks in your own browser.
Added
BrowserOS
Open-source agentic browser that runs AI agents locally.
Added
Magentic-UI
Microsoft Research's experimental human-in-the-loop agent that works across the browser and local files.
Added
Steel
Open-source browser API and sandbox for AI agents to control web browsers at scale.
Added
Playwright Skill
Playwright automation skill for coding agents.
Added
OpenSwarm
AI-first 'operating system' where swarms of agents run apps and browsers in parallel.
Added
Anchor Action Index
Shared memory of web workflows for Anchor's cloud browsers: computer-use agents replay proven paths as deterministic code and the model only steps in where a page has changed, exposed as tools on Anchor's MCP server and REST API.
Added
Browserbase
Hosted headless browsers built for agents.
Added
Comet
Perplexity's AI browser with a built-in assistant that can browse, summarize and complete tasks on web pages for you.
Added
Minion AI
Browser agent that completes web tasks for you.
Added
Scalebrowser
Gives each agent its own isolated browser with a persistent identity for staying signed in.
Added
Skyvern
Automates browser workflows with vision + LLMs.
Added
BrowserTools MCP
MCP server that lets Cursor and other agents read browser console logs and network activity.
Added
OpenBot
Open-source AI coworkers that each get their own computer with a browser, files and tools.
Added
Cicero
Self-hosted voice interface for coding agents (Claude Code, Codex, ACP); talk from a browser or Telegram call.
Added
Voiceloop
Zero-dependency JS library for an interruptible in-browser voice loop (VAD, STT, LLM, TTS).
Added
Bolt
Prompt-to-app builder that runs full-stack apps in the browser.
Added
Replit Agent
Builds and deploys full apps from a prompt in the browser.
Added
Computer and desktop control (15) See the full list →
Handsy
Lets an AI model use a real iPhone through a $7 ESP32 board that acts as a Bluetooth keyboard and mouse, tapping and typing through apps with no jailbreak and no computer attached.
Added
LCU
Brings the computer-use runtime from the ChatGPT desktop app to Claude Code, Codex CLI and Pi, so any agent harness can see and control your desktop without a Codex sign-in.
Added
OpenGCUA
Open stack from Tongyi Lab's MAI-UI team for generalist computer-use agents that combine GUI clicks, accessibility trees, terminal commands, APIs and code: an OSWorld harness, a macOS real-device harness, a cross-device SDK and published task runs of eight frontier models.
Added
OpenAdapt
Execution layer for computer-use agents that turns a demonstrated task into a local program that repeats the clicks without model calls and stops on mismatches.
Added
Midscene.js
Vision-driven UI automation and E2E testing framework where a GUI agent carries out natural-language steps on web, mobile and desktop apps.
Added
RobotGo
Go library for cross-platform desktop automation and AI computer use that controls mouse, keyboard, screen, windows and processes.
Added
UFO
Microsoft's desktop agent framework that operates Windows apps and orchestrates multi-device tasks as task graphs.
Added
Windows-MCP
Lightweight MCP server for computer use on Windows that lets agents navigate files, control apps and interact with the UI.
Added
Peekaboo
macOS CLI, menu-bar app and MCP server for screen capture, accessibility inspection and native UI automation by AI agents.
Added
AstronRPA
iFlytek's open-source enterprise RPA desktop app with a low-code visual designer whose workflows can be called by AI agents.
Added
AGI-0 by AGI, Inc.
AGI, Inc.'s small action model and Android agent that sees the screen and acts across any app without APIs.
Added
Cua
Open-source infrastructure for computer-use agents: sandboxes, drivers across operating systems and benchmarks.
Added
TuriX CUA
Computer-use agent that operates desktop apps.
Added
Arro
Arro, a desktop assistant that guides you through tasks on your computer and repeats them for you.
Added
Holo4 (H Company)
Open-weight computer-use models (27B and 35B-A3B) released Oct 1.
Added
Scraping and crawling (11)
ByteFlow
ByteFlow is a no-code builder for AI agents on top of the systems a company already runs (ERP, CRM, in-house and legacy apps) through APIs or a browser agent. Agents prepare the work, such as a CRM update or ERP entry, and a person approves it with one tap. Includes voice agents in 10+ Indian languages and document extraction.
Added
Scout (Outcrawl)
Open-source browser agent from Outcrawl that opens a real browser and clicks, types and reads pages to finish a task you describe.
Added
Scrapling
Python web-scraping framework with fast HTTP requests, stealth browsers, adaptive parsing and concurrent crawling, plus an MCP server for agents.
Added
ScrapeGraphAI
Python library that uses LLMs and graph logic to build scraping pipelines: describe the data you want and it extracts it from websites or documents.
Added
Moli
Lightweight Rust headless browser for AI agents that fetches pages, searches and extracts content, usable via CLI, CDP or WebDriver.
Added
webclaw
Rust web extraction tool that turns sites into clean Markdown or JSON for agents, as a CLI, MCP server and REST API, with a hosted API.
Added
Apify
Marketplace of thousands of ready-to-run scrapers and automation tools ("Actors") for real-time web data, usable from apps and AI agents, including via MCP.
Added
BrowserAct
No-code builder for reusable AI web scrapers that collect structured data and connect it to apps, workflows and agents.
Added
Crawl4AI
Open-source crawler that turns websites into clean, LLM-ready Markdown for agents and RAG pipelines.
Added
Maxun
Turns websites into structured APIs with no-code robots for extraction and monitoring.
Added
Spider
Fast Rust web crawler for collecting data for agents and LLMs.
Added
Mobile and remote control (7) See the full list →
Sundae
Sundae is a personal AI assistant you text from iMessage or Android RCS, with no app or account needed. It works on a computer of its own: it books tables, finds flights at current prices, compares shops, reads letters and photos you send, sets reminders, watches prices and builds simple web pages, then texts back with a screenshot so you can check. It remembers what you tell it, asks before spending money, sending, deleting or opening accounts, and stops at checkout for you to pay. It is free to start with a daily limit, with a paid Plus plan, and is in limited beta.
Added
VisorBot
An Android automation app where you type or say a task and VisorBot taps, swipes and types through your apps to do it, with reusable recipes. Free plan; Plus from $4.99 a month.
Added
Mobile MCP
MCP server that lets agents automate iOS and Android apps on simulators, emulators and real devices through one platform-agnostic interface.
Added
mobile-use
Open-source AI agent that controls real Android and iOS apps from natural-language commands.
Added
Google ARTEMIS
Google's tool that turns natural-language instructions into Android automation.
Added
Mobilerun
LLM-agnostic agent framework for controlling Android and iOS devices with natural language.
Added
Agent Device
Mobile app automation and verification for coding agents on iOS and Android.
Added
More tools (7)
Firefox DevTools MCP
Mozilla's MCP server that lets AI agents browse with Firefox and inspect pages with its developer tools over WebDriver BiDi.
Added
Airtop
Turns plain-English workflow descriptions into deterministic agents that work across your apps, APIs and the web.
Added
Kadoa
AI agents that build, monitor and maintain web data pipelines producing verified datasets for investors.
Added
Page Agent
JavaScript in-page agent that controls web interfaces from natural language instructions.
Added
Agent-S
Open agentic framework that uses computers like a human through the GUI.
Added
Unbrowse
Turns websites into APIs agents can call.
Added
TinyFish
Enterprise web agents that run at scale across websites to gather data and take actions.
Added
GitHub repos (78)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| Browser Use ↗ | 117,912 | MIT | 2026-10-17 |
| Scrapling ↗ | 88,372 | BSD 3-Clause | 2026-10-21 |
| Crawl4AI ↗ | 85,667 | Apache License 2.0 | 2026-10-20 |
| Chrome DevTools MCP ↗ | 53,681 | Apache License 2.0 | 2026-10-21 |
| UI-TARS-desktop ↗ | 39,297 | Apache License 2.0 | 2026-10-09 |
| Playwright MCP ↗ | 38,115 | Apache License 2.0 | 2026-10-19 |
| Lightpanda ↗ | 36,657 | GNU Affero General Public License v3.0 | 2026-10-21 |
| CloakBrowser ↗ | 32,280 | MIT | 2026-10-20 |
| ScrapeGraphAI ↗ | 31,882 | MIT | 2026-10-06 |
| OpenCLI ↗ | 30,335 | Apache License 2.0 | 2026-10-20 |
| Cua ↗ | 29,966 | MIT | 2026-10-21 |
| Page Agent ↗ | 29,459 | MIT | 2026-09-06 |
| Stagehand ↗ | 25,660 | MIT | 2026-10-21 |
| Moli ↗ | 19,349 | — | 2026-10-21 |
| Browser Harness ↗ | 18,465 | MIT | 2026-10-17 |
Top 15 of 78 by stars. Stars and licence come from each repo, checked when the listing was last verified.
Related tasks
Popular with: Automation engineers · Related searches: Free & open-source browser agents
Tools are matched to tasks by category, use cases and what each tool says it does. Missing one? Submit it free.