Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

This page's audience our own tag's counts — open to see them
–Visits
–Page views
–Clicks to vendors
–Time on page
–Reading now
Clicks to vendors, by tool
  • –
Top countries
  • –
Devices
  • –

– · visits, page views and clicks counted by our own tag, which counts more than our checked analytics; every figure rounded down · how we count

AgentBrowser

Freemium#10 of 20 in Browser Agents

AgentBrowser: Controlled browser sessions with credential safeguards, approvals, and replayable activity. Ranked #10 of 20 in Browser Agents by our editors (7.3/10); pricing: Free plan; best for teams needing controlled, observable browser sessions.

7.3/10Editor score
AgentBrowser7.3 Visit AgentBrowser

At a glance

  • Editor score
    7.3 / 10
  • Pricing
    Free plan
  • Best for
    Teams needing controlled, observable browser sessions
  • Free plan
    Yes
  • Paid from
    $49/mo
  • Browser control
    Cloud
  • Facts checked
    24 Sep 2026
  • Where it wins

    • Origin-bound vault injects credentials and TOTP without exposing secrets to agents.
    • Human approval checkpoints cover sensitive credential-vault requests.
    • Records sessions and streams replayable DOM, console, and network events.
  • Where it doesn't

    • Supported-browser information is limited to Chrome.
    • Pro starts at $49 per month, with metered overage.
    • Billing documentation says Stripe is in test mode despite published paid plans.

Our verdict on AgentBrowser

AgentBrowser gives AI agents a hosted Chrome browser for navigating pages, interacting with controls, running JavaScript, and completing multi-step web flows. It is aimed at teams that need browser work to be controlled and reviewable, rather than simply issuing an agent a browser and leaving its activity opaque. Access is available through MCP, REST API, Python SDK, GPT and Claude integrations, or CDP clients including Playwright and Puppeteer. A web console supports session control and review, and deployment options include cloud and self-hosted use.

Its standout fit is governance and observability around browser activity. The origin-bound credential vault can inject login details and TOTP without returning those secrets to the agent, while human approval checkpoints apply to sensitive vault requests. Full-session MP4 recordings complement replayable DOM, console, and network events; live DOM, console, and action streams are available over WebSocket, SSE, or NDJSON. Scheduled jobs can capture screenshots, create PDFs, read, or extract content. This combination suits teams that need to inspect or gate multi-step browser work. The published browser support is Chrome, so teams requiring evidence of broader browser coverage should look elsewhere.

The published plans show a Free tier at $0 per month with 5 instance-hours, 1 concurrent session, 2 GB for recordings and artifacts, a credential vault, and human approvals. Pro is $49 per month for 100 instance-hours, 5 concurrent sessions, 50 GB, metered overage, and email support. Scale costs $299 per month and includes 750 instance-hours, 25 concurrent sessions, 500 GB, metered overage with volume rates, and priority support. Documentation says Stripe is configured in test mode, while paid plans are published; that distinction matters to buyers evaluating checkout. AgentBrowser fits teams prioritizing controls and audit trails, but is less compelling where browser breadth or confirmed live paid billing is essential.

Your product? Our editors can test AgentBrowser in depth and publish a review, labelled as paid · from $149/mo →

AgentBrowser pricing

Plans Free planFreemium A usable free plan; paid tiers unlock the limits above. Prices checked 24 Sep 2026.
See plans on getagentbrowser.com

All 3 AgentBrowser plans and prices →

AgentBrowser fact sheet

Free planYes
Paid from$49/mo
Browser controlCloud
Task executionMulti-step
Supported browsersChrome
Monthly task limitNot verified
Human approvalYes
DeploymentCloud, Self-hosted, Desktop, Mobile
PlatformsWeb, Windows, macOS, Linux, iOS, Android
SupportEmail, Docs
Built forSolo, Small business, Mid-market, Enterprise (editorial estimate)
Integrations9 integrations: MCP, Claude Code, Claude Desktop, GPT plugin / Actions, REST API, Python SDK …
PricingFree plan (source)
Websitegetagentbrowser.com
Facts checked24 Sep 2026

AgentBrowser integrations

AgentBrowser lists 9 integrations on its own site.

  • MCP
  • Claude Code
  • Claude Desktop
  • GPT plugin / Actions
  • REST API
  • Python SDK
  • Playwright
  • Puppeteer
  • Codex CLI

Alternatives to AgentBrowser

See all AgentBrowser alternatives →

Used AgentBrowser? Be the first to review it

The editor score above is our own research. What this page doesn't have yet is a reader's view — what you used AgentBrowser for, what worked and what didn't. No stars are seeded and no review is paid for; an editor reads every one before it appears.

Write a reviewTwo minutes · verified accounts only · read by an editor before it appears

Reviews come only from verified accounts. Sign in or create an account first — your e-mail is never shown.

Your rating

0 characters · at least 80, up to 3,000

Posted from your verified account. Reviews appear after an editor reads them, usually within two working days.

Featured on iTechGuides

Featured on iTechGuides — AgentBrowser 7.3/10

AgentBrowser is listed in our Browser Agents directory. Add the badge to your site — it links back to this page.

<a href="https://www.itechguides.com/products/agentbrowser/"><img src="https://www.itechguides.com/best/badge/agentbrowser.svg" alt="Featured on iTechGuides" width="230" height="46"></a>

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated · How we research and update