Get an audit

Head to head · Browser automation · October 2026 research run

agent-browser vs TinyFish

TinyFish scores 67.7 (B) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on security & auth and payments & pricing. Both do browser automation.

agent-browserVercel Labs · MCP server B66.6/100#263 of 841 TinyFishTiny Fish, Inc. · HTTP API B67.7/100#227 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 57
  • Payments & pricing, 60 against 55

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

TinyFish B

Good for Agents that want one account for a goal-driven web agent, a raw CDP browser, and free search and fetch.

Ahead on

  • Reliability, 60 against 48
  • Maintenance & community, 80 against 70

Also in its favour

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

Watch for

The terms of 17 August 2026 allow Tiny Fish to train and improve its models on customer data. No opt-out was found in the reviewed pages

Score by category

CategoryWeight this runagent-browserTinyFishEdge
Reliability16%204860TinyFish +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28485TinyFish +1
Agent ergonomics13%16.27879TinyFish +1
Security & auth14%17.56757agent-browser +10
Payments & pricing10%12.56055agent-browser +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87080TinyFish +10
Transparency & trust7%8.86159agent-browser +2
Negative events≤1500
Total66.6 · B67.7 · B

Facts side by side

Factagent-browserTinyFish
KindMCP serverHTTP API
VendorVercel LabsTiny Fish, Inc.
Hosted endpointno (local only)https://agent.tinyfish.ai
TransportsstdioHTTP
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceApache-2.0Proprietary service under Tiny Fish's terms of service. The MCP proxy @tiny-fish/mcp and the cookbook are MIT. The SDK packages state no licence in npm or PyPI metadata
Tools exposed158none
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedai.tinyfish.agent/web-agent
Last release2026-10-012026-10-07
Terms last updatedno document linked2026-08-17
Privacy policy last updatedno document linked2025-12-14
Customer content may train modelsyes
Terms restrict automated accessyes
Terms restrict benchmarkingyes
Terms or service can change without noticenot found in the text
Arbitration or class-action waiveryes
Popularity44k stars, 2.1M npm/wk5.7k npm/wk, 6.5k 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.

TinyFish

OpenAPI documents are published for five APIs, errors carry typed codes and request IDs, and Search and Fetch are free within daily allowances. The terms let Tiny Fish train its models on customer data, run creation takes no idempotency keys, and the status page shows an hour or more of downtime on several days for the Browser and Search APIs.

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

TinyFish

  1. Check result as well as status. A run can be COMPLETED while the goal failed, with result.status set to failure
  2. Don't retry POST /v1/automation/run blindly after a timeout. There are no idempotency keys, so list runs first to avoid duplicates
  3. Use /v1/automation/run-async or /run-sse when a run may need cancelling. Runs started with the synchronous endpoint can't be cancelled
  4. Allow 60 seconds for Browser session creation, connect Playwright to cdp_url (not base_url), and DELETE the session when done because billing is per minute
  5. Never put passwords in goal, which is logged. Pass use_vault: true with credential_item_ids, or use_profile: true for saved login state

Questions

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

TinyFish scores 67.7 (B) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on security & auth and payments & pricing.

Do agent-browser and TinyFish need an API key?

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

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

agent-browser runs on your own machine, with no hosted endpoint listed. TinyFish has a hosted endpoint at https://agent.tinyfish.ai.

Are agent-browser and TinyFish open source?

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

Other comparisons with agent-browser or TinyFish

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