ego (lite) is just a browser, ego is your personal agent across devices.
Join waitlist
Download for Mac
Solutions
DocsEnterpriseChangelogBlog
ego lite vs Stagehand

The Best Stagehand Alternative

Stagehand is an SDK for assembling browser workflows. ego (lite) is the browser where your coding agent carries them out.

ego (lite) skips the SDK project and lets your coding agent run the workflow directly. Compact Snapshots and batched actions reduce model turns and token use.

Try ego (lite) freeGitHub
Trusted by developers from
GoogleAmazonShopifyTikTokHarvardStanfordUSCUCLA

Why ego lite is better than Stagehand

The choice is between building a browser workflow into a project and giving your agent a browser it can use immediately. ego (lite) handles the full range of agent-led web work, from finding and comparing information to completing forms and checking application flows, with your browser state and Spaces available when needed.

Fastest on real tasks

In Stagehand, three clicks in a row can mean three separate trips to the model before the page moves again. Stagehand's own speed guide shows this pattern and suggests calling observe first so later clicks can reuse what it found.

Run /ego-browser and your coding agent controls ego (lite) directly. Every page arrives as a Snapshot with stable @N refs it can act on instantly. Across our published benchmark, ego (lite) had the fastest average completion time.

Time to finish a task, shorter is better
81.8 sego lite
282.9 sagent browser
Data source - Task: scrape the main posts from the X account from the last 7 days

Parallel multitasking, execute faster

Running several Stagehand tasks at once means spinning up and tearing down browser instances in your own code, or moving to Browserbase and hitting session caps of 3, 25, or 100. To see what happened, you open a replay after the run finishes.

In ego lite there's no cap on how many Spaces you open inside the same browser: each one runs its own task at the same time, controlled by a coding agent via /ego-browser on its own imported Chrome profile. None of them ever steals the tab you're using, and you can watch or take over any Space anytime.

No more back and forth Cost fewer tokens

Stagehand's action cache helps when you repeat the same flow on the same page. On a new site, or after the DOM shifts, each call asks the model again, and stale caches have to be cleared by hand.

Run /ego-browser and your coding agent batches several actions in a few lines of JavaScript per turn to control ego lite. Stacked with Snapshot input, the same task completes on far fewer tokens overall.

Claude Code · ego lite
>/ego-browser Add the first product to the cart, then check checkout loads
●Bash(
ego-browser nodejs <<'EOF' await openOrReuseTab('localhost:3000') await click('.product-card') await click('.add-to-cart') await click('a[href="/checkout"]') cliLog('checkout loaded') EOF
)
⎿Output:
[t=4480ms] checkout loaded
Done. Both steps work.
─── 1 tool call · ↑ 1.1k tokens ───
Stagehand · env: "LOCAL"
>$ npx tsx run_task.ts const stagehand = new Stagehand({ env: "LOCAL" }) await stagehand.init()
await page.goto("http://localhost:3000")
// page = stagehand.context.pages()[0]
navigated: http://localhost:3000
↑ 1.6k tokens sent so far
await stagehand.act("click the first product card")
// LLM call #1 · model: gpt-5.6-sol
→ { success: true, message: "Action completed successfully",
actions: [{ selector: "/html/body/div[2]/main/div[1]/a",
method: "click", arguments: [] }] }
↑ 3.8k tokens sent so far
await stagehand.act("click add to cart")
// LLM call #2 · model: gpt-5.6-sol
→ { success: true, message: "Action completed successfully",
actions: [{ selector: "/html/body/div[2]/main/button[1]",
method: "click", arguments: [] }] }
↑ 5.9k tokens sent so far
await stagehand.observe("find the checkout link")
// LLM call #3 · model: gpt-5.6-sol
→ [{ selector: "/html/body/nav/a[href='/checkout']",
description: "Checkout link", method: "click", arguments: [] }]
↑ 8.0k tokens sent so far
await stagehand.act(action)
// no LLM: Action from observe()
→ { success: true, message: "Action completed successfully",
actions: [{ method: "click" }] }
navigated: /checkout
↑ 9.1k tokens sent so far
await stagehand.extract("is the payment form present?", z.object({ present: z.boolean() }))
// LLM call #4 · model: gpt-5.6-sol
→ { present: true }
↑ 11.4k tokens sent so far
await stagehand.extract("list the payment fields", z.object({ fields: z.array(z.string()) }))
// LLM call #5 · model: gpt-5.6-sol
→ { fields: ["card", "expiry", "cvc", "zip"] }
↑ 13.6k tokens sent so far
─── 7 model calls · ↑ 13.6k tokens ───
The same task, the same model. Left: one batched JavaScript call in ego lite, 1.1k tokens total. Right: a Stagehand script, a model call on nearly every step, tokens climb to 13.6k.

Same Chrome, agent-native

Staying logged in is the hard part of local Stagehand. Chrome profile support still has an open bug in v3, cookie workarounds often miss the HttpOnly session cookies that matter, and the browse CLI only attaches if you started Chrome with remote debugging yourself.

Built on Chromium, ego lite imports your entire Chrome setup in one click. When your coding agent runs /ego-browser, it controls ego lite with your real sessions already in place, so it doesn't stall on SSO, 2FA, or captchas on accounts you already have.

ego lite Chrome profile import: one-click setup with all your logins

ego lite vs Stagehand

Feature comparison between ego lite and Stagehand.
Featureego liteStagehand
What you writeNothing. One sentence to the agent you already useA TypeScript or Python project: SDK, act/extract/observe, keep it working
How the agent acts on a pageCoding agent batches multiple actions in JavaScript per turn via /ego-browserOne model call per act, extract, or observe that isn't cached; precise locators when you want to skip the model
Token cost per taskLower: Snapshot plus batched JavaScript, measured per taskRepeated flows can reuse a cached selector; new pages pay for a fresh model call each time
Reuses your real Chrome loginsYes, one-click Chrome profile import; coding agent controls ego lite via /ego-browserNot reliably in local mode: Chrome profile support has an open bug, and browse needs remote debugging
SetupInstall ego lite, run /ego-browser in your agentnpm/pip install, model API key, and a project
Parallel task isolationUnlimited Spaces in one browser, bounded by your machineYour code manages instances; Browserbase caps concurrency by plan
Doubles as your daily browserYes. You browse in your Space, agents work in theirsNo. It launches a clean automation browser
Committed, repeatable automationNo. Tasks are interactiveYes: scripts with git history, review, and a committed cache
Reusable skills (coming soon)Distills successful runs into reusable skills for repeat tasks (limited beta)Action caching on repeated flows only
PriceFree, no subscription, no accountMIT and free to install; you pay model tokens (plus Browserbase if hosted)
Last updated Jul 30, 2026

Make it a seamless transition

Already running Stagehand scripts in CI or on a schedule? Keep those. Move browser work you want an agent to handle directly, including search, research, extraction, forms, testing, and logged-in workflows.

  1. Download ego (lite)

    Download ego lite and import your Chrome profile in one click. Logins, cookies, and extensions come with it.

  2. Run your first task with /ego-browser

    Paste into your agent

    /ego-browser Open ego.app and join the waitlist

    Paste one sentence into Claude Code, Codex, or Cursor and hit enter. No SDK, no model API key, no Zod schema.

  3. Watch it work
    ego lite Spaces overview with four browser tasks running side by side: Claude Code tracking Apple stock on Yahoo Finance, Codex filtering cars by year on cars.com, Hermes finishing a SaaS back-office task, a user scraping X, and a hand tapping + to open another Space

    The task runs in its own Space, so your tabs stay untouched. Watch live or take over anytime. Results land back in your agent's CLI.

Keep Stagehand for committed automation, typed extraction, and deterministic locators.

When to use each tool

Choose ego (lite) when

  • You'd rather describe browser work to your coding agent than maintain a TypeScript or Python project for it.
  • The work sits behind your own logins and should start signed in.
  • You want parallel Spaces you can watch, without managing browser instances in code.
  • You don't want to add an SDK, model key, and project for something your coding agent can already do.

Choose Stagehand when

  • Automation must live in a repo with review, caching, and the same run months later.
  • You want a deterministic escape hatch: precise locators when a flow must not vary.
  • You need typed extraction with a Zod schema into TypeScript.
  • It must run in CI or across many cloud browsers on Browserbase.

Give your agent a real browser

Free, runs on your Mac, imports your Chrome profile in one click. Works with Claude Code, Codex, Cursor, and any CLI agent that writes code.

Try ego (lite)

Keep reading

Still weighing your options? See how Stagehand compares with the other tools in the same space.

ego (lite) vs Puppeteerego (lite) vs Playwright MCPego (lite) vs Claude Chrome extensionego (lite) vs Browser Harnessego (lite) vs Browserbaseego (lite) vs agent-browserego (lite) vs Playwrightego (lite) vs Seleniumego (lite) vs Codex browserego (lite) vs Kimi Chrome extensionego (lite) vs Codex Chrome extensionAll comparisonsBrowser automation solutions

FAQ

Stagehand is Browserbase's MIT-licensed browser automation SDK for TypeScript and Python. It gives you act, extract, observe, and agent primitives, plus precise locators when you want to skip the model. It runs locally against Chromium, and pairs with Browserbase when you want hosted sessions, caching, and replay. For automation you commit to a repo and run on a schedule, it remains an excellent choice.

For agent-driven browser work, yes: run /ego-browser and describe the task. For committed automation you ship to CI, with typed extraction and deterministic locators, keep Stagehand. Stagehand is for workflows you encode; ego (lite) is for workflows your agent handles directly.

No. Stagehand runs locally against Chromium on its own. Browserbase is optional when you want hosted sessions, server-side caching, and replay. The Browserbase vs Stagehand pairing matters for cloud fleets, not for a local script on your laptop. ego lite has no hosted path: local only, free, no account.

Often yes in production, but for different reasons. Stagehand is the SDK you write act, extract, and observe calls in. Browserbase is where those scripts run when you need cloud scale. For your own agent chores on logged-in sites, you may need neither: run /ego-browser and let Claude Code or Codex drive ego lite directly.

Stagehand is MIT-licensed and free to install. You pay model tokens for every act, extract, or observe call that is not cached, plus Browserbase browser minutes if you host it there. ego lite is free. You only pay the model tokens your coding agent already uses.

Not dependably in local mode today. Pointing Stagehand at your Chrome profile still has an open bug in v3, and cookie workarounds often miss the HttpOnly session cookies that matter. ego lite imports your Chrome profile once, and every task starts signed in.

They aim at different developers. Stagehand is TypeScript-first with act, extract, and observe primitives for hybrid code-plus-AI automation. Browser Use is Python-first and runs a more autonomous agent loop. Both are frameworks you write and fund. ego lite is the Chromium browser your coding agent controls via /ego-browser. See ego lite vs Browser Use for that side.

Stagehand is an SDK: you write act, extract, and observe calls in TypeScript or Python. agent-browser is a CLI your agent shells out to, one command at a time. ego lite is neither. Run /ego-browser and your coding agent controls ego lite with batched JavaScript. See ego lite vs agent-browser.

Not as a native skill. Claude Code would run a Stagehand script you wrote, with model API keys and a project to maintain. ego lite is the shorter path: run /ego-browser in Claude Code, Codex, or Cursor and describe the task. No SDK install, no schema, no separate model billing loop.

When an action is not cached, the model picks the target again each time, so a shifting page can resolve differently. Caches can also go stale after the DOM changes. Use Stagehand's precise locators when a flow must not vary. ego (lite) is built for agent-driven browser work across changing pages and workflows.

Neither. Run /ego-browser in Claude Code, Codex, Cursor, Gemini CLI, or OpenCode. Free on macOS 12+, no account required.

Yes, when the account, report, and destination are authorized and the workflow is explicit. Use Stagehand's browser actions for the download, verify the filename and contents, then upload to a review-approved Drive folder; keep the file path and source URL in the run log. Require human approval before sharing, overwriting, or publishing a report, and stop at MFA or other access-control prompts.

Separate test data per worker, wait for meaningful UI state, and use stable role, label, or test-id locators for assertions that must not vary. Stagehand's natural-language act is useful for exploration, but a release gate should use deterministic locators, explicit fixtures, traces on failure, and a bounded retry policy. ego lite is a visible investigation path, not a replacement for a committed CI suite.

Keep Stagehand scripts that already run in CI or on a schedule. Move browser workflows by installing ego (lite), importing an authorized Chrome context, and asking your coding agent to run the task in a Space. Preserve the old assertions and expected output, compare one run, and move the task back to Stagehand if it needs deterministic replay, typed extraction, or cloud scale.

ego (lite) is a local browser for supervised agent work, not a Python SDK runtime or unattended production service. It can complement a local Stagehand or Browser Use project across research, testing, and workflow development, while production jobs still need process supervision, secrets management, retries, observability, and deterministic test boundaries.

Selector reuse can reduce repeated model work when the page contract and locator remain valid, but a cache must be versioned and invalidated when markup, route, locale, or account state changes. Store the selector with its source URL, matched role or label, and last verification; rerun the original assertion before trusting it. Never let a stale cache silently target a different control.

Treat Patchright as a browser-runtime integration that must match the SDK's supported Playwright and Chromium versions; verify the documented launch or CDP connection path in a disposable local profile first. Do not use stealth patches to bypass a site's controls. If the integration is brittle, keep the supported Stagehand runtime for committed tests and use ego lite for an observable, human-supervised local check.

Stagehand adds model-driven act, observe, and extract calls for a quick plain-language check; Playwright gives deterministic code, fixtures, traces, and cross-browser CI. Use Stagehand or ego lite for exploratory sanity checks, then encode a high-value workflow in Playwright once the expected behavior is known. That division keeps natural-language flexibility from becoming an unstable release gate.