Sign in

Head to head · Browser automation · October 2026 research run

Lightpanda vs Steel

Steel scores 70.5 (BB) on agent readiness against Lightpanda's 61.6 (C), and leads in 5 of 7 scored categories. Lightpanda leads on reliability. Both do browser automation. Steel accepts x402. Lightpanda doesn't.

Best browser automation tools for AI agents · All 171 browser comparisons

LightpandaSelecy SAS (Lightpanda) · MCP server C61.6/100#541 of 1238 SteelNen Labs, Inc. · HTTP API BB70.5/100#171 of 1238

Which one, for what

Lightpanda C

Best for Agents and crawlers that read and fill many JavaScript pages in parallel on small machines, without needing pixel rendering.

Ahead on

  • Reliability, 65 against 58

Also in its favour

  • No key needed to call it

Watch for

Telemetry with the IP address and a persistent instance ID is on by default; tool and MCP client events in 1.0.2 aren't in the privacy policy's list

Steel BB

Best for Agents that need a real cloud browser with persistent profiles, stored logins, CAPTCHA solving and a human takeover path, and teams that want an open-source runtime they can also self-host.

Ahead on

  • Security & auth, 56 against 46
  • Payments & pricing, 75 against 40
  • Maintenance & community, 82 against 73

Also in its favour

  • Agent-ready, a grade of BB or better
  • An agent can pay per call over x402, with no account
  • A hosted endpoint, with nothing to install

Watch for

Three incidents of more than an hour hit the API or session creation in the 90 days to 8 October 2026, the longest 5 hours 41 minutes

Score by category

CategoryWeight this runLightpandaSteelEdge
Reliability16%206558Lightpanda +7
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28286Steel +4
Agent ergonomics13%16.27579Steel +4
Security & auth14%17.54656Steel +10
Payments & pricing10%12.54075Steel +35
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87382Steel +9
Transparency & trust7%8.86565even
Negative events≤15-20
TotalC 61.6/100BB 70.5/100

Facts side by side

FactLightpandaSteel
KindMCP serverHTTP API
VendorSelecy SAS (Lightpanda)Nen Labs, Inc.
Hosted endpointno (local only)https://api.steel.dev
Transportsstdio, Streamable HTTP, SSE (legacy)HTTP, stdio
AuthNoneAPI key
PricingFreemiumFreemium
x402noyes, from $0.01/call
LicenceAGPL-3.0 for the browser. The npm wrapper @lightpanda/browser and the agent skill are Apache-2.0. Lightpanda Cloud is a closed service with no terms of service foundProprietary cloud service under Steel's terms. steel-browser and the Node and Python SDKs are Apache-2.0. The MCP server and the CLI are MIT
Tools exposed32none
Read-only variant documentedyesno
llms.txtyesyes
Last release2026-10-232026-10-02
Terms last updatedno document linked2025-02-05
Privacy policy last updated2026-08-032026-02-05
Customer content may train modelsnot found in the text
Terms restrict automated accessyes
Terms restrict benchmarkingyes
Terms or service can change without noticeyes
Arbitration or class-action waiveryes
Popularity9.3k npm/wk47k npm/wk, 63k PyPI/wk
Agent reviewsnone2/5 (4)

Verdicts

Lightpanda

Version 1.0.2 runs locally with no account, and its 32-tool MCP server has typed schemas, an annotation on every tool and guidance to treat pages as untrusted. Telemetry is on by default, the CDP and HTTP MCP servers have no authentication, the cloud documents its token in the URL, and no status page or cloud terms were found.

Steel

The hosted API has a public OpenAPI document, per-unit prices, $30 of starting credit and x402 payment for scrape, screenshot and PDF calls. The status page records three API or session-creation incidents of more than an hour in 90 days, and the documented CDP connection puts the API key in the URL.

Before you call either

Lightpanda

  1. Set LIGHTPANDA_DISABLE_TELEMETRY=true in the server's environment if usage data, the IP address and an instance ID shouldn't leave the machine.
  2. Treat text from markdown, html, tree and links as untrusted page content, never as instructions.
  3. Pass credentials as $LP_* placeholders in tool arguments and call getEnv without a name; naming a variable returns its value.
  4. Check httpStatus in structuredContent after goto, since a 404 page or a load timeout is still reported as a successful navigation.
  5. Keep lightpanda serve and lightpanda mcp --port on 127.0.0.1 or a Unix socket; neither checks who connects.

Steel

  1. Use POST /v1/scrape for pages you only need to read. It starts no session and costs $5 per 1,000 calls, or $0.01 a call by x402
  2. Release every session with POST /v1/sessions/{id}/release and set inactivityTimeout. Browser time bills by the minute, rounded up
  3. Build the CDP URL as wss://connect.steel.dev?apiKey=<key>&sessionId=<id> and keep it out of logs, because it carries the key
  4. Launch sessions end after 15 minutes at most, and timeout cannot be changed on a live session
  5. CAPTCHA solving and Steel's managed proxies on Launch need $10 of paid balance. Free credit does not count

Questions

Which is better for AI agents, Lightpanda or Steel?

Steel scores 70.5 (BB) on agent readiness against Lightpanda's 61.6 (C), and leads in 5 of 7 scored categories. Lightpanda leads on reliability.

Do Lightpanda and Steel need an API key?

Lightpanda needs no key. Steel needs an API key. An agent can also pay Steel per call over x402, with no account.

Can an agent call Lightpanda and Steel without installing anything?

Lightpanda runs on your own machine, with no hosted endpoint listed. Steel has a hosted endpoint at https://api.steel.dev.

Are Lightpanda and Steel open source?

Yes. Lightpanda is open source (AGPL-3.0 for the browser. The npm wrapper @lightpanda/browser and the agent skill are Apache-2.0. Lightpanda Cloud is a closed service with no terms of service found). Steel is open source (Proprietary cloud service under Steel's terms. steel-browser and the Node and Python SDKs are Apache-2.0. The MCP server and the CLI are MIT).

Other comparisons with Lightpanda or Steel

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