Get an audit

Head to head · Browser automation · October 2026 research run

agent-browser vs Anchor Browser

Anchor Browser and agent-browser score within a point of each other on agent readiness, 67.3 (B) and 66.6 (B). agent-browser leads on agent ergonomics, security & auth, maintenance & community and transparency & trust. Both do browser automation.

agent-browserVercel Labs · MCP server B66.6/100#263 of 841 Anchor BrowserAnchor Forge Inc. · HTTP API B67.3/100#237 of 841

Which one, for what

agent-browser B

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

Ahead on

  • Agent ergonomics, 78 against 73
  • Security & auth, 67 against 54
  • Maintenance & community, 70 against 57
  • Transparency & trust, 61 against 51

Also in its favour

  • No key needed to call it
  • Runs on your own machine
  • Open source

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

Anchor Browser B

Good for Agents that must work inside signed-in accounts, with managed identities, MFA handling and a human sign-in link, and agents that need to start with no human signup.

Ahead on

  • Reliability, 80 against 48

Also in its favour

  • A hosted endpoint, with nothing to install
  • Free to start without a card

Watch for

No service agreement or API terms found. anchorbrowser.io/terms is a website terms of use dated 16 March 2025

Score by category

CategoryWeight this runagent-browserAnchor BrowserEdge
Reliability16%204880Anchor Browser +32
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28480agent-browser +4
Agent ergonomics13%16.27873agent-browser +5
Security & auth14%17.56754agent-browser +13
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87057agent-browser +13
Transparency & trust7%8.86151agent-browser +10
Negative events≤1500
Total66.6 · B67.3 · B

Facts side by side

Factagent-browserAnchor Browser
KindMCP serverHTTP API
VendorVercel LabsAnchor Forge Inc.
Hosted endpointno (local only)https://api.anchorbrowser.io
TransportsstdioHTTP
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceApache-2.0Proprietary cloud service. No service agreement was found, only a website terms of use. The TypeScript and Python SDKs and the self-hosted MCP server are Apache-2.0
Tools exposed158none
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-012026-07-28
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linked2026-02-24
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/wk43k npm/wk, 10k PyPI/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.

Anchor Browser

The API has a public OpenAPI 3.1 document, per-unit prices and Agent Access, an unauthenticated flow that issues a trial API key without a dashboard account. No service agreement is published, only a website terms of use, and the documented CDP connection puts the API key in the URL.

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

Anchor Browser

  1. Send the key in the anchor-api-key header. For CDP, build wss://connect.anchorbrowser.io?apiKey=<key>&sessionId=<id> and keep that URL out of logs
  2. Set session.timeout.idle_timeout and max_duration and end sessions with DELETE. The default maximum is 180 minutes, and browser time bills by the minute
  3. Session creation is capped at 5 a minute on Free, 25 on Starter and 100 on Growth. On 429, wait for the Retry-After seconds
  4. Connect the Anchor MCP server or Anchor (all), not both, because the docs say the pair duplicates tool names
  5. Authenticated browsers, CAPTCHA solving and proxies by country need the Starter plan or higher. The Free plan and Agent Access keys run plain sessions and web tasks

Questions

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

Anchor Browser and agent-browser score within a point of each other on agent readiness, 67.3 (B) and 66.6 (B). agent-browser leads on agent ergonomics, security & auth, maintenance & community and transparency & trust.

Do agent-browser and Anchor Browser need an API key?

agent-browser needs no key. Anchor Browser takes an API key or an OAuth sign-in.

Can an agent call agent-browser and Anchor Browser without installing anything?

agent-browser runs on your own machine, with no hosted endpoint listed. Anchor Browser has a hosted endpoint at https://api.anchorbrowser.io.

Are agent-browser and Anchor Browser open source?

agent-browser is open source (Apache-2.0). No open-source release is listed for Anchor Browser.

Other comparisons with agent-browser or Anchor Browser

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