Get an audit

Head to head · Browser automation · October 2026 research run

agent-browser vs Skyvern

agent-browser scores 66.6 (B) on agent readiness against Skyvern's 63.1 (B), and leads in 3 of 7 scored categories. Skyvern leads on reliability, maintenance & community and transparency & trust. Both do browser automation.

agent-browserVercel Labs · MCP server B66.6/100#263 of 841 SkyvernIkonomos Inc. (Skyvern) · HTTP API B63.1/100#369 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

  • Security & auth, 67 against 59
  • Payments & pricing, 60 against 32

Also in its favour

  • No key needed to call it
  • No incidents deducted, where Skyvern loses 3 points for them

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

Skyvern B

Good for Agents that must finish a multi-step job on sites with logins, 2FA and forms, where stored credentials, saved workflows and cached scripts matter more than raw browser time.

Ahead on

  • Reliability, 57 against 48
  • Maintenance & community, 85 against 70
  • Transparency & trust, 72 against 61

Also in its favour

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

Watch for

Every API key and OAuth token has full organisation authority. The docs state there are no read-only, per-endpoint or per-resource keys

Score by category

CategoryWeight this runagent-browserSkyvernEdge
Reliability16%204857Skyvern +9
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28488Skyvern +4
Agent ergonomics13%16.27876agent-browser +2
Security & auth14%17.56759agent-browser +8
Payments & pricing10%12.56032agent-browser +28
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87085Skyvern +15
Transparency & trust7%8.86172Skyvern +11
Negative events≤150-3
Total66.6 · B63.1 · B

Facts side by side

Factagent-browserSkyvern
KindMCP serverHTTP API
VendorVercel LabsIkonomos Inc. (Skyvern)
Hosted endpointno (local only)https://api.skyvern.com/v1
TransportsstdioHTTP, Streamable HTTP, stdio
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceApache-2.0AGPL-3.0 for the open-source server, SDKs and MCP server. Skyvern Cloud is a proprietary service under Skyvern's terms, and its anti-bot measures aren't in the repository
Tools exposed158114
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedio.github.Skyvern-AI/skyvern
Last release2026-10-012026-10-01
Terms last updatedno document linked2026-02-27
Privacy policy last updatedno document linked2026-10-01
Customer content may train modelsyes, with an opt-out
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waiveryes
Popularity44k stars, 2.1M npm/wk23k stars, 3.2k npm/wk, 1.6k 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.

Skyvern

The hosted MCP server annotates every tool as read-only or destructive and can advertise a 29 or 32-tool subset in place of 114, and the API has a written six-month deprecation policy. Every key and OAuth token carries full organisation authority, with no read-only or scoped credential, and no request rate limits are documented.

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

Skyvern

  1. Connect to https://api.skyvern.com/mcp/x/lean or /x/operate, or send X-Skyvern-Scope, so the client loads 32 or 29 tools. The scope filters the list and does not limit permissions
  2. Use a separate Skyvern organisation for each blast radius. Any key or OAuth token can read and write stored credentials and delete workflows
  3. Never pass passwords to skyvern_act or skyvern_type. Store them as credentials and call skyvern_login
  4. Set max_steps on tasks, or x-max-steps-override on agent runs, to cap credits. A run that reaches the cap ends as timed_out
  5. On 503 from POST /v1/run/agents, wait Retry-After seconds. No run was created, so resubmitting is safe

Questions

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

agent-browser scores 66.6 (B) on agent readiness against Skyvern's 63.1 (B), and leads in 3 of 7 scored categories. Skyvern leads on reliability, maintenance & community and transparency & trust.

Do agent-browser and Skyvern need an API key?

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

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

agent-browser runs on your own machine, with no hosted endpoint listed. Skyvern has a hosted endpoint at https://api.skyvern.com/v1.

Are agent-browser and Skyvern open source?

Yes. agent-browser is open source (Apache-2.0). Skyvern is open source (AGPL-3.0 for the open-source server, SDKs and MCP server. Skyvern Cloud is a proprietary service under Skyvern's terms, and its anti-bot measures aren't in the repository).

Other comparisons with agent-browser or Skyvern

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