Skip to main content
📖 The AI Tool Bible

Best AI tools for browser automation

27 tools in the Agents category, filtered to browser automation.

All Agents →
DO

Doubao

Agents · Doubao Seed 2.1 Pro (in-house ByteDance), with Seed 2.0 / 1.5 on free tier
8.5

ByteDance's flagship AI assistant with a real agent mode and one of the largest user bases outside ChatGPT

Freemium· Free tier (chat, search, writing, image gen, voice/video chats) / Doubao Pro RMB 68/mo (~$9.40) / RMB 200/mo (~$27.80) / RMB 500/mo (~$69.40). API: 6 yuan per 1M input tokens, 30 yuan per 1M output tokens for Doubao 2.1 Pro (cache-hit as low as 1.2 yuan).Long-document PDF and Office file summarizationAutonomous browser and local-computer agent tasks
SC

ScrapeGraphAI

Agents · Multi-model (LLM, unspecified)
8.4

LLM-driven web scraping API that turns natural-language prompts into structured JSON.

Freemium· Free 500 credits; Starter $20/mo, Growth $100/mo, Pro $500/mo, Enterprise customweb-scrapingdata-extraction
SK

Skyvern

Agents · Multi-model (OpenAI, Anthropic, Gemini, Ollama)
8.3

AI browser agent that automates web workflows from natural-language instructions, with CAPTCHA and 2FA handling built in.

Freemium· Free: $0/month · Hobby: $29/month · Pro: $149/month · Enterprise: Custom/monthbrowser-automationdata-extraction
BU

Browser Use

Agents · Multi-model (BYO LLM; Claude in hosted Box)
8.2

Open-source browser automation harness and cloud platform for LLM agents that drive real websites.

Freemium· PAYG: $0 · Dev: $29 · Business: $299 · Scaleup: $999web-automationscraping
AT

Atua

Agents · Multi-model (BYO key)
7.9

Keyboard-summoned macOS AI assistant that reads your screen and drives system apps with your own API keys.

Paid· One-time $29, lifetime updates, 7-day refundmacos-assistantscreen-context
MA

Manus

Agents · Multi-model
7.9

Generalist agent for research, code, and web tasks.

Paid· Credit-based; tiers from $19/moresearchweb tasks
OP

OpenCLI

Agents · GPT-3, GPT-2
7.4

Open-source bridge that hands your already-logged-in Chrome session to a CLI and AI agents.

Free· Free and open-source (Apache-2.0)browser-automationagent-tooling
HY

Hyperbrowser

Agents · Model-agnostic (BYO LLM)
7.1

Cloud browser infrastructure built for AI agents that need to scrape, click, and navigate the live web.

Freemium· Free developer tier; paid usage-based plansagent-browser-controlweb-scraping
OP

OpenClaw

Agents · Bring-your-own (Claude, GPT, others)
7.1

Open-source local AI agent that controls your computer and talks back through your messaging apps.

Free· Open source; you pay for the underlying LLM API usagepersonal-assistantshell-automation
PA

PageAgent

Agents · Bring-your-own (Qwen, GPT, Claude, etc.)
7.1

An in-page JavaScript GUI agent that drives web interfaces with natural language, no headless browser required.

Free· Free, MIT-licensed; LLM costs are whatever provider you wire inweb-automationai-copilots
YS

YouTube Summary with ChatGPT & Claude

Agents · Multi-model (ChatGPT, Claude, Gemini, Mistral)
7.1

Browser extension that pipes YouTube transcripts, articles, and PDFs into ChatGPT, Claude, Gemini, or Mistral for instant summaries.

Freemium· Basic: $10 · Pro: $20 · Enterprise: Contact salesvideo-summarizationtranscript-extraction
AG

AgenticSeek

Agents · Bring-your-own local LLM (Ollama / llama.cpp compatible)
7.0

Open-source local-first AI agent that browses the web, writes code, and runs tasks without sending anything to the cloud.

Free· Free and open source; optional SerpApi key for enhanced searchlocal-ai-agentautonomous-web-browsing
OP

OpenSandbox

Agents · Model-agnostic
7.0

Open-source sandbox infrastructure for running AI-generated code, agents, and browsers in isolated Docker or Kubernetes environments.

Free· Open source (Apache 2.0); managed pricing not disclosedcode-executionagent-sandboxing
SC

Superpower ChatGPT

Agents · GPT (via ChatGPT UI)
7.0

Chrome extension that bolts folders, prompt libraries, and bulk export onto the ChatGPT web UI.

Freemium· Basic: $10 · Pro: $20 · Enterprise: Contact saleschatgpt-organizationprompt-management
BU

Browser Use Web UI

Agents · Multi-model
6.9

Gradio web UI for running browser-use AI agents in a real or persistent Chrome session.

Free· Free, open-source; bring your own LLM API keysbrowser-automationweb-agents
CF

ChatGPT for Google

Agents · Multi-model (GPT-4, Claude 2, others)
6.9

Browser extension that pipes GPT-4, Claude and other LLM answers into your existing search results page.

Free· Free extension; requires your own accounts with underlying AI providerssearch-augmentationpage-summarization
TU

TubeSum

Agents
6.9

Chrome extension that turns long YouTube videos into AI-generated summaries with clickable timestamps.

Freemium· Basic: $10 · Pro: $20 · Enterprise: Contact salesyoutube-summarizationtranscript-extraction
YS

YouTube Summary & ChatGPT by Glasp

Agents · Multi-model (GPT-3.5, GPT-4, Claude, Mistral, Gemini)
6.9

Chrome extension that surfaces YouTube transcripts and AI-generated video summaries alongside one-click access to ChatGPT.

Freemium· Basic: $20 · Pro: $50 · Enterprise: Contact salesyoutube-summarizationtranscript-extraction
ZA

Zuvu AI

Agents · Multi-model (OpenAI GPT via web or user API key)
6.9

Chrome sidebar that drops ChatGPT-style answers next to Google, Bing, and DuckDuckGo results.

Freemium· Basic: $10 · Pro: $20 · Enterprise: Contact salessearch augmentationpage summarisation
WE

WebChatGPT

Agents · Multi-model
6.6

Browser extension that grafts live web search results onto ChatGPT (and Claude, Gemini) prompts.

Free· Freeweb-augmented-chatprompt-library
BR

Browserbase

Agents · Model-agnostic via Model Gateway (OpenAI, Anthropic, Google, others)

Headless browser infrastructure for AI agents

Freemium· Start for Free: Free · Get Developer: $20 · Get Startup: $99 · Contact Sales: CustomAI web-browsing agentsLLM-driven end-to-end testing
DB

Dia Browser

Agents

An AI-native browser from The Browser Company that turns tabs into an agentic assistant for knowledge workers.

Freemium· Free consumer download; paid Dia for Work tier with SSO and admin controls (price not disclosed publicly).cross-tab summarisationmorning briefing from calendar and inbox
FE

Fellou

Agents

The world's first agentic browser that plans and executes multi-step web workflows for you.

Freemium· Free: $0/month · Plus: $19.0/month · Pro: $39.9/month · Ultra: $199.9/monthCompetitive research reportsAutomated job applications
ON

Opera Neon

Agents

An agentic browser from Opera built to act on the web, not just render it.

Paid· Basic: $10 · Pro: $20 · Enterprise: Contact salesMulti-tab web research briefsVendor and product comparison across sources
PC

Perplexity Comet

Agents · Routes to Perplexity Sonar plus frontier models (OpenAI GPT, Anthropic Claude, Google Gemini) depending on task and subscription tier

An agentic AI browser from Perplexity that reads, reasons over, and acts on the pages you're viewing.

Freemium· Basic: $10 · Pro: $20 · Enterprise: Contact salesMulti-tab research synthesis with citationsAgentic email triage and drafting in Gmail
SC

Scrapling

Agents

Adaptive Python web-scraping framework with a built-in MCP server for AI coding agents.

Free· Free and open source under BSD-3-Clause. Self-hosted Python library with no paid tier or hosted service; users pay only for their own infrastructure, browsers, and any proxies or LLM tokens they choose to plug in.MCP-driven web scraping from Claude DesktopAgent-powered research and browsing
ST

Stagehand

Agents · Model-agnostic (OpenAI GPT-4o, Anthropic Claude, Google Gemini via Vercel AI SDK)

The SDK for browser agents

Freemium· SDK is free/open-source (MIT). Runs locally against any LLM API key. Optional Browserbase cloud runtime: Free $0/mo, Developer $20/mo, Startup $99/mo, Scale custom.AI web scrapingAutonomous browser agents