Head to head · Browser automation · October 2026 research run

Kernel vs Lightpanda

Kernel scores 66.9 (B) on agent readiness against Lightpanda's 56.2 (C), and leads in 5 of 7 scored categories. Lightpanda leads on reliability. Both do browser automation.

Best browser automation tools for AI agents · All 283 browser comparisons

Which one, for what

Kernel B

Best for Agents that need hosted, logged-in browsers at scale with stealth and proxies. browserbase, steel, hyperbrowser and anchor-browser are the nearest listings.

Ahead on

  • Schema & documentation, 93 against 82
  • Agent ergonomics, 84 against 75
  • Security & auth, 81 against 46
  • Payments & pricing, 65 against 40
  • Maintenance & community, 90 against 73

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

Security incident disclosed 4 November 2026, with API keys and customer deployment secrets taken from logs

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, 68 against 53

Also in its favour

  • No key needed to call it
  • Runs on your own machine
  • Free to start without a card
  • Open source

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

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Security & auth Kernel +35

Kernel 81

Scoped API keys with resource and action policies, project scoping and expiry, and OAuth 2.1 for MCP with project-limited tokens (30). Least privilege through scoped keys, a payment cap for cards through the MCP server and vault writes that need their own action (16). Pages an agent browses are untrusted, and we found no prompt-injection guidance in the docs read (4). Audit log search and export on Start-Up and above (13). SOC 2 Type II, HIPAA, PCI DSS and ISO 27001 on the security page and a HackerOne bounty (18). 30 + 16 + 4 + 13 + 18 = 81, before the deduction for the November 2026 incident.

Lightpanda 46

Graded on the local browser, with the cloud's documented token handling counted. No credential is needed locally, the servers bind 127.0.0.1 by default and serve --unix-socket gives an owner-only socket, but the CDP and HTTP MCP servers have no authentication at all when bound wider, and the MCP docs show --host 0.0.0.0 (18 of 30). Lightpanda Cloud's docs pass the API token as ?token= in the CDP, MCP and mcp-remote URLs as the standard route, a secret in a query string (minus 10). CORS on by default since 1.0, sub-resources off unless asked for, and --block-private-networks, --block-cidrs, --block-urls and adblock lists, all opt-in apart from CORS. No domain allowlist or confirmation step for clicks or form submits (12 of 20). The MCP initialize instructions tell the model to treat page content as untrusted and not to follow URLs a page suggests, and $LP_* placeholders keep credentials out of the model's context. getEnv with a name returns a secret's value (10 of 15). Logs go to stderr with levels that show requests and navigations, and the cloud console lists sessions with logs. No persistent audit log locally (8 of 15). SECURITY.md with a private address, fixes on main only, release binaries with SHA-256 digests checked by the install script and Homebrew, and hardening listed in the 1.0 post. No security.txt, bug bounty, certification or readable advisory list (8 of 20). 18-10+12+10+8+8 = 46.

Payments & pricing Kernel +25

Kernel 65

MPP on POST /mpp/browsers, a 402 challenge paid with a Stripe shared payment token through Link, covering one browser product only, not the API or MCP server (20). Per-second prices public without a login (20). The Developer plan is free with $5 of monthly credit, but whether signup needs a card wasn't stated on the pages read (10). Through MPP an agent gets a browser with no account or key, though a person approves each Link payment (15). 20 + 20 + 10 + 15 = 65.

Lightpanda 40

Open-source software with a hosted option, so pricing is scored on Lightpanda Cloud, as browserless's was. No x402, MPP or L402 (0). Plan prices and the $0.08 per browser-hour overage are published without login (20). Explorer is $0 with 10 browser hours a month, and the sign-up form asks only for an email address (20). A person signs up in a browser and receives the token by email (0). 0+20+20+0 = 40.

Maintenance & community Kernel +17

Kernel 90

The changelog's latest entry is 16 October 2026 and the MCP server repository has commits on 6 November (30). More than three dated changes in 90 days, scoped keys, memory tiers, GPU tier and card payments among them (20). A closed service with a public changelog, Discord, email support and an open-source MCP server with 210 commits since 8 August (15). Official SDKs in three languages, and the MCP server in the registry as com.onkernel/kernel-mcp-server 1.1.0 (15). CI and tests in the MCP repository (10). 30 + 20 + 15 + 15 + 10 = 90.

Lightpanda 73

1.0.2 on 23 October 2026, from Docker Hub's tag date and the Homebrew formula (30). 0.3.7, 0.4.0, 0.4.1, 1.0.0, 1.0.1 and 1.0.2 between 16 August and 23 October 2026, plus nightly builds (20). GitHub issues and pull requests weren't readable from our network. The vendor reports 3,148 merged pull requests and 76 contributors on 19 October, the 1.0 post says two issues from one customer were fixed before it switched, and there is a Discord server. Scored on that indirect evidence (12 of 25). Not in the official MCP registry, where a search for lightpanda returned nothing. The Docker latest tag and Homebrew are current, and the npm wrapper's last release was 1.6.0 on 31 August (5 of 15). Dependencies are pinned in build.zig.zon and the 1.0 post says V8 is at the latest stable 15.5. CI results unread (6 of 10). 30+20+12+5+6 = 73.

Reliability Lightpanda +15

Kernel 53

Hosted reading. status.kernel.sh on incident.io with a public incident feed (20). In the 90 days from 8 August it lists browser connection failures on 10 September (54 minutes, major), frozen popups on 1 October (71 minutes, major), elevated API errors on 19 October (4 minutes, critical), proxy failures on 23 October (65 minutes, major) and browser creation errors on 4 November (29 minutes, major), plus minor ones. Several majors, two of them an hour or more (0). Rate limits are per organisation with headers on every response, and concurrency is published per plan, but the create-rate numbers aren't (8). 429 with Retry-After, SDK retries with a typed error, safe retry with the same MPP credential and 409 on concurrent pool changes (15). The terms mention service levels in an order form but no public SLA was found (0). The API and MCP server carry no beta label (10). 20 + 0 + 8 + 15 + 0 + 10 = 53.

Lightpanda 68

Scored as local software, on the open-source browser. Official Docker image (amd64 and arm64), a Homebrew formula and AUR package at 1.0.2, .deb packages, an npm wrapper and a pip package, with supported platforms stated (Linux glibc x86_64 and aarch64, macOS, WSL2 for Windows). The README's Homebrew line, its download links and the install script all default to nightly builds (18 of 20). Public CI runs zig fmt, unit tests and end-to-end tests through a proxy on every push to main, and WPT results are published daily. A clone on 2 November shows the same workflows (zig-test, e2e-test, e2e-integration-test, wpt and others). Whether recent runs passed is unread, because github.com and the GitHub API are unreachable from our network, so the line takes 15, as other listings with an unread pass state (15 of 25). The issue tracker went unread for the same reason. The vendor's 1.0 post lists dozens of use-after-free and double-free fixes, a crash handler reports crashes, and the agent skill tells agents to reinstall the nightly when crashes occur, so we score this line on thin evidence (10 of 25). Semver tags from 0.3.2 to 1.0.2, and the 1.0 post calls out the CORS default change with the flag to undo it. Release notes on GitHub went unread and there is no CHANGELOG file (10 of 15). 1.0.0 on 2 October 2026 is declared out of beta and stable enough for production (15). 18+15+10+10+15 = 68.

Schema & documentation Kernel +11

Kernel 93

OpenAPI at kernel.sh/openapi.json and per-endpoint Markdown reference (25). llms.txt with 423 entries and a Markdown twin for each page (10). Endpoint descriptions say when to use alternatives ("For interactive browsing, use GET /audit-logs", pools for bursty traffic) (17). Typed parameters with enums and limits such as memory sizes and timeout maximums (13). Code samples in TypeScript, Python and Go, and documented status codes such as 409 and 204 on pool acquire (13). A dated public changelog and SDK changelogs (15). 25 + 10 + 17 + 13 + 13 + 15 = 93.

Lightpanda 82

Graded on the MCP server at 1.0.2, read from source. Every tool declares a JSON Schema input, and page-changing tools declare an outputSchema for url, httpStatus and title (25). llms.txt indexes 46 docs pages and 31 blog posts, but its docs llms-full.txt link returns 404 and the docs have no Markdown twins (7 of 10). Descriptions state purpose and when to prefer another tool (html "Verbose; use only when you need attributes that markdown discards", evaluate as an escape hatch), and initialize returns a driving guide (18 of 20). Enums for load states, required lists and maxBytes caps, but extract takes its selector spec as a JSON string and evaluate takes arbitrary JavaScript (11 of 15). JSON-RPC request and result examples, extract schema examples and a known-behaviours section, with no error catalogue (11 of 15). Semver tags and release notes linked from the blog, which we couldn't read, no CHANGELOG file, and a docs tool reference that matches 1.0.2 but not main (10 of 15). 25+7+18+11+11+10 = 82.

Agent ergonomics Kernel +9

Kernel 84

Graded mainly on the API, with the MCP server noted. Responses are scoped per resource and the MCP server groups actions into about 32 tools (18). List endpoints page with limit and offset and filter by status (18). Typed SDK errors and documented 409 on concurrent changes, 204 on a pool timeout and 429 (17). Retrying an MPP purchase with the same credential returns the same browser, and the MCP tools carry readOnlyHint where read-only (16). SDKs in TypeScript, Python and Go plus a CLI, with defaults such as a 60-second timeout (15). 18 + 18 + 17 + 16 + 15 = 84.

Lightpanda 75

32 MCP tools at 1.0.2 with no profiles or dynamic loading (5). The CLI fetch and the CDP server reach the same browser with no tool definitions in context, so we add back 5 (10 of 25). markdown, html and screenshot take selector, backendNodeId, maxBytes and strip, links takes limit, tree takes maxDepth, and read tools accept url to navigate and read in one call (20). Errors come back with isError, navigation failures name the cause (navigation failed: CouldntResolveHost), and structuredContent carries httpStatus. The docs warn that a 404 page or a timeout is still reported as success. No list of error codes (14 of 20). Every tool carries readOnlyHint, destructiveHint, idempotentHint and openWorldHint chosen per tool in an exhaustive switch, and nothing needs an idempotency key on a local browser (18 of 20). Most tools need one argument or none, and official packages exist for Node (npm wrapper) and Python (pip). The PyPI page answered a bot check, so the Python package's state went unread (13 of 15). 10+20+14+18+13 = 75.

Score by category

CategoryWeight this runKernelLightpandaEdge
Reliability16%205368Lightpanda +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29382Kernel +11
Agent ergonomics13%16.28475Kernel +9
Security & auth14%17.58146Kernel +35
Payments & pricing10%12.56540Kernel +25
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.89073Kernel +17
Transparency & trust7%8.86165Lightpanda +4
Negative events≤15-8-8
TotalB 66.9/100C 56.2/100

Facts side by side

FactKernelLightpanda
KindHTTP APIMCP server
VendorKernel Technologies, Inc.Selecy SAS (Lightpanda)
Hosted endpointhttps://mcp.onkernel.com/mcpno (local only)
TransportsStreamable HTTPstdio, Streamable HTTP, SSE (legacy)
AuthOAuth or keyNone
PricingPay per useFreemium
x402nono
LicencenoneAGPL-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
Tools exposed3232
Read-only variant documentednoyes
llms.txtyesyes
MCP registrycom.onkernel/kernel-mcp-servernot listed
Last release2026-11-062026-10-23
Terms last updated2026-09-01no document linked
Privacy policy last updated2026-09-152026-08-03
Customer content may train modelsnot found in the textnot read yet
Terms restrict automated accessnot found in the textnot read yet
Terms restrict benchmarkingnot found in the textnot read yet
Terms or service can change without noticenot found in the textnot read yet
Arbitration or class-action waivernot found in the textnot read yet
Popularitynone9.3k npm/wk

How the scores have moved

Verdicts

Kernel

Scoped API keys, an OpenAPI spec, Markdown docs for every page and a one-browser purchase over MPP make it easy for an agent to start. Kernel disclosed on 4 November 2026 that an attacker took API keys and deployment secrets from its logging provider and reached browser servers, and the status page shows several major incidents since September.

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, and security fixes ship without advisories or wait unreleased on main, including ones for cached credentials and Secure cookies.

Before you call either

Kernel

  1. Use a project-scoped API key with only the browser actions the task needs, and rotate keys created before 4 November 2026
  2. Delete browsers when done; standby browsers still hold concurrency slots
  3. Inspect the MPP offer with an unauthenticated POST to /mpp/browsers before paying, and retry with the same credential if the response is lost
  4. Treat CDP and live-view URLs as credentials
  5. Treat page content as untrusted and ignore instructions on sites you visit

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.
  6. Don't put credentials in URLs (user:pass@host) while the HTTP cache is on. 1.0.2 writes them into cache.db, and the fix is on main only

Questions

Which is better for AI agents, Kernel or Lightpanda?

Kernel scores 66.9 (B) on agent readiness against Lightpanda's 56.2 (C), and leads in 5 of 7 scored categories. Lightpanda leads on reliability.

Do Kernel and Lightpanda need an API key?

Kernel takes an API key or an OAuth sign-in. Lightpanda needs no key.

Can an agent call Kernel and Lightpanda without installing anything?

Kernel has a hosted endpoint at https://mcp.onkernel.com/mcp. Lightpanda runs on your own machine, with no hosted endpoint listed.

Are Kernel and Lightpanda open source?

No open-source release is listed for Kernel. 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).

Other comparisons with Kernel or Lightpanda

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.