The browserfor your agent.

Install BetterWright
bun install -g betterwright

The loop

Snapshots

One snippet in.One snapshot back.

A snippet runs Playwright code in a sandboxed worker and returns a result envelope. Request a snapshot when you need a compressed accessibility tree, sized for a context window.

agent.tsTypeScript
import { withBrowser } from "betterwright/sdk"

const proof = await withBrowser(async (bw) => {
  await bw.run("await page.goto('https://shop.example/cart')")

  // what the model reads: the tree on the right
  const tree = await bw.run("return snapshot({ interactive: true })")

  // act on a ref with a human-shaped click
  await bw.run("await human.click(page.locator('aria-ref=e7'))")

  // only what changed, not the page again
  await bw.run("return snapshot({ interactive: true, diff: true })")

  return bw.run("return screenshot({ kind: 'proof', name: 'checkout' })")
})

What the agent sees

Interactive snapshots drop unrelated prose while retaining controls, live status, and short item or table context. Actionable refs let the model target controls without re-deriving a selector.

Diff mode

Only what changed

With matching snapshot options, diff mode returns changed lines or reports no changes.

Verified input

Honest failures

Typing reads the field back and fails the step when the text is not there. An editor that swallowed keystrokes is a miss, not a success.

Proof

Evidence the agent cites

A proof screenshot is an artifact, not a wall of pixels in the context. The result points at it.

Architecture

Your agent decides.BetterWright drives.The browser stays open.

Three layers, one clean seam between each. The agent never touches the session; the session never touches the task. Swap the bottom layer with one configure command.

  1. 01

    Decides

    Your agent

    Owns the task. Reads a snapshot, picks the next step.

    skill · MCP · SDK · exec

  2. 02

    Drives

    BetterWright

    Owns the session. Network policy, credential vault, snapshots, live view.

    one persistent session · policy floor · vault · diffs

  3. 03

    Stays open

    The browser

    Managed BetterChromium by default: downloaded once, coherent identity, GPU when the host has one.

    or any of nine cloud browsers

Cloud browsers

Browser providers

Full lifecycle start · list · stop

  • Kernel
  • Browserbase
  • Steel
  • Anchor
  • Hyperbrowser
  • Browser Use

Connect bring your own endpoint

  • Browserless
  • Bright Data
  • Oxylabs

Mechanisms & evidence

Read what matters.Check what changed.

Read the development reports

Prune

Focused observations

Interactive snapshots retain controls, live status, and short item or table context.

Diff

Compare the same view

Diff mode returns changed lines against a previous snapshot with the same options.

Reuse

Persistent sessions

Return to the same browser session instead of repeating login and navigation each turn.

The head-to-head reports are development case studies, not valid comparative benchmarks: the reference implementations are unnamed and unversioned. They do not establish a general speed or token advantage. Method and raw runs are in the repo.

Entry points

Two ways to drive it.One session underneath.

The same persistent sessions, vault, network policy, and snapshots sit under every entry point, so you can start with one and mix in the others later.

Skill or MCP

Your agent, step by step

Claude Code, Codex, Cursor, Pi, or any MCP client mans the browser as one part of a bigger job. No server, no glue code.

TypeScript SDK
title.ts
import { withBrowser } from "betterwright/sdk"

const title = await withBrowser(async (bw) => {
  await bw.run("await page.goto('https://example.com')")
  const r = await bw.run<string>("return page.title()")
  return r.ok ? r.result : null
})

Your own code, one import

withBrowser builds the client, runs your function, and closes it on the way out and on a thrown error. Results are values; check ok and decide.

Built-in agent
terminal
$ betterwright exec "find the top HN story and give me its title" --model gpt-5.6-sol
{
  "ok": true, "steps": 4, "toolCalls": 5,
  "answer": "…",
  "usage": { "inputTokens": 6880, "outputTokens": 1330 },
  "proof": "…/proof-hn.png"
}
# the 30 snapshots in between never reach your main agent

Hand over the whole task

One shell command in, one JSON object out. The browsing transcript stays inside the sub-agent, so a 30-turn checkout costs your main agent one tool call.

Live view and handoff

Take the wheel when it matters

Watch the run in a browser tab, chat between turns, and take over for MFA or a consequential click. Hit Done and the agent resumes.

Install it. Point your agent at it. Read the answer.

Give your agent a browser it can fit.

Start with the docsView source