Write a review

Head to head · Browser automation · October 2026 research run

agent-browser vs Puppeteer

Puppeteer scores 70.6 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 3 of 7 scored categories. agent-browser leads on agent ergonomics and security & auth. Both do browser automation.

Best browser automation tools for AI agents · All 120 browser comparisons

agent-browserVercel Labs · MCP server B66.6/100#301 of 1076 PuppeteerGoogle · SDK + MCP BB70.6/100#154 of 1076

Which one, for what

agent-browser B

Best for Coding agents with a shell that want short commands and compact snapshots.

Ahead on

  • Agent ergonomics, 78 against 67
  • Security & auth, 67 against 52

Also in its favour

  • Runs on your own machine

Watch for

The ten most recent CI runs on main, 1 to 8 October 2026, all concluded in failure. In the newest, Windows Rust tests and native end-to-end tests failed

Puppeteer BB

Best for Agents that write and run Node.js scripts against Chrome or Firefox.

Ahead on

  • Reliability, 80 against 48
  • Maintenance & community, 89 against 70
  • Transparency & trust, 70 against 61

Also in its favour

  • Agent-ready, a grade of BB or better

Watch for

No MCP server, CLI or llms.txt of its own. The docs point agents to the separate chrome-devtools-mcp project

Score by category

CategoryWeight this runagent-browserPuppeteerEdge
Reliability16%204880Puppeteer +32
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28481agent-browser +3
Agent ergonomics13%16.27867agent-browser +11
Security & auth14%17.56752agent-browser +15
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87089Puppeteer +19
Transparency & trust7%8.86170Puppeteer +9
Negative events≤1500
TotalB 66.6/100BB 70.6/100

Facts side by side

Factagent-browserPuppeteer
KindMCP serverSDK + MCP
VendorVercel LabsGoogle
Hosted endpointno (local only)no (local only)
Transportsstdio
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Tools exposed158none
Read-only variant documentednono
llms.txtyesno
Last release2026-10-012026-10-08
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Popularity44k stars, 2.1M npm/wk96k stars, 11.5M npm/wk

Verdicts

agent-browser

Snapshots with element refs, a 29-tool default MCP profile and opt-in domain allowlists, action policies and content boundary markers suit agent use. The project is at 0.38.2 with no stable release, the ten most recent CI runs on main failed between 1 and 8 October 2026, and every security control is off by default.

Puppeteer

Puppeteer is a stable, Apache-2.0 library on 25.13.0, with ten releases since 27 July 2026, typed APIs, locators that wait and retry, and accessibility snapshots an agent can read. It has no MCP server or llms.txt of its own, and 10 of the 20 most recent CI runs on main failed between 7 and 13 October 2026.

Before you call either

agent-browser

  1. Run agent-browser install once after npm install -g agent-browser. It downloads Chrome for Testing
  2. Take a fresh snapshot -i after any navigation. Refs survive same-document changes only
  3. Pass --json for machine-readable results and --max-output to cap page text
  4. Set --allowed-domains, --action-policy and --content-boundaries for untrusted sites. None is on by default, and the allowlist rejects --profile, --cdp and --restore
  5. Start MCP with agent-browser mcp, and add profiles such as --tools core,network only when needed

Puppeteer

  1. Install with npm i puppeteer, which downloads a matching Chrome for Testing. Use puppeteer-core to bring your own browser
  2. Prefer page.locator() over page.$(). Locators wait for the element to be visible and stable before acting
  3. Read pages with page.accessibility.snapshot({interestingOnly: true}) rather than full HTML to keep output short
  4. Catch TimeoutError separately from TargetCloseError. The first can be retried, the second needs a new page or browser
  5. Packages are ESM only since 25.0.0. Use import puppeteer from 'puppeteer' rather than require

Questions

Which is better for AI agents, agent-browser or Puppeteer?

Puppeteer scores 70.6 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 3 of 7 scored categories. agent-browser leads on agent ergonomics and security & auth.

Can an agent call agent-browser and Puppeteer without installing anything?

agent-browser runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Puppeteer.

Are agent-browser and Puppeteer open source?

Yes. agent-browser is open source (Apache-2.0). Puppeteer is open source (Apache-2.0).

Other comparisons with agent-browser or Puppeteer

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report