What it is

Browser agent SDK from Browserbase built on Playwright, adding natural-language primitives: act to perform a step, observe to find actionable elements and extract to pull schema-validated data. Actions self-heal across markup changes, and you can drop back to plain Playwright code whenever determinism matters.

Why it earns a slot

Selector-based tests shatter every time an AI rewrites your markup. Describing the step in English instead of pinning a DOM node keeps flows passing across cosmetic refactors you never asked for.

Know before you commit

Every natural-language step is an LLM call, so runs are slower, cost tokens and are less deterministic than plain Playwright. Cache resolved actions once a flow stabilises.

Getting started

npm install @browserbasehq/stagehand

Field notes

0 from the community

Sign in to add a field note. Reading is always open.

Loading notes…

Field check

Unverified

Sign in to confirm this entry is still accurate.

Pricing snapshot

$0 forever, MIT open source; runs locally free, or against Browserbase from $20/mo

Snapshots move fast — verify at checkout, and post a field note if it changed.

Drop into your Lovable chat

Evaluate Stagehand (https://stagehand.dev) for this project, then use it only if it fits what we are already building.
Context: AI browser automation SDK. Browser agent SDK from Browserbase built on Playwright, adding natural-language primitives: act to perform a step, observe to find actionable elements and extract to pull schema-validated data. Actions self-heal across markup changes, and you can drop back to plain Playwright code whenever determinism matters.
Reviewer notes (general, not written for this codebase): Selector-based tests shatter every time an AI rewrites your markup. Describing the step in English instead of pinning a DOM node keeps flows passing across cosmetic refactors you never asked for.
Watch out for: Every natural-language step is an LLM call, so runs are slower, cost tokens and are less deterministic than plain Playwright. Cache resolved actions once a flow stabilises.
Pricing: $0 forever, MIT open source; runs locally free, or against Browserbase from $20/mo
Setup: npm install @browserbasehq/stagehand
Rules: treat the notes above as background only. Do not assume a theme, style, layout or feature that is not already in this project — inspect the existing code first and ask me before changing visual direction.

/api/public/tools/stagehand

Also in Code review, testing & security

Aikido Security

aikido.dev

All-in-one AppSec scanner

Free tier + paidCode review, testing & security

Developer free forever: 2 users, 10 repos, 2 container images, 1 domain, 250k protected requests/mo, 10 AI autofixes/mo; Basic $300/mo base for 10 users and 100 repos; Pro $600/mo for 200 repos; Advanced $600/mo for 500 repos; Enterprise custom

Open dossier

Arcjet

arcjet.com

In-app rate limiting and bot defence

PaidCode review, testing & security

No free plan as of 2026; Individual $25/app/mo; Startup $299/app/mo; Growth $799/app/mo; usage fees on top at $5 per 1M requests plus per-feature rates such as $0.50 per 1M for bot detection; 15-day trial

Open dossier

Bito

bito.ai

AI PR review agent

PaidCode review, testing & security

Team $12/seat/mo annually or $15 monthly; Professional $20/seat/mo annually or $25 monthly; both include 5,000 lines reviewed per seat per month, overage $5 per 1,000 lines; Enterprise custom; 14-day trial

Open dossier

Browserbase

browserbase.com

Hosted headless browser cloud

Free tier + paidCode review, testing & security

Free: 1 browser hour/mo; Developer $20/mo with 100 browser hours then $0.12/hr; Startup $99/mo with 500 hours then $0.10/hr; Scale custom with 250+ concurrent browsers

Open dossier