Hyperbrowser wrapper

If you run Hyperbrowser agent tasks today, point your client at POST /api/wrappers/hyperbrowser/task — the TypeScript shim mirrors client.agents.hyperAgent.startAndWait. Your tasks default to routing: "smart" — the best runner across all providers — so pin routing: "hyperbrowser" only if you want provider parity during migration.

Why wrap vs call Responses directly

Use the Hyperbrowser wrapper when you already have Hyperbrowser client code and want the smallest diff: same method names / request shapes, Banana Peel key + base URL, optional routing. Use POST /api/v1/responses for new work — one API for smart routing, benchmarks, MFA input, and run inspection. Wrappers are a migration bridge, not the long-term product surface.

Install

npm install ./packages/wrappers/hyperbrowser → @bananapeel/hyperbrowser
agents.browserUse is aliased to the same task surface — agent family names share one backend today

Before → after

import { Hyperbrowser } from "@hyperbrowser/sdk";

const client = new Hyperbrowser({
  apiKey: process.env.HYPERBROWSER_API_KEY,
});

const result = await client.agents.hyperAgent.startAndWait({
  task: "Go to Hacker News and tell me the title of the top post",
  maxSteps: 20,
});
console.log(result.data?.finalResult);

Auth & base URL

Agents: npx -y @banana-peel/cli init --agent --json (see /docs/agents). Humans who already have an account can copy a key from the keys console: bp_live_… (or bp_test_…).

Env: BANANA_PEEL_API_KEY, optional BANANA_PEEL_BASE (defaults to the production Cloud Run URL)
Headers: Authorization: Bearer …, x-api-key, or vendor-shaped x-hyperbrowser-api-key, hyperbrowser-api-key
HTTP base for this wrapper: ${BANANA_PEEL_BASE}/api/wrappers/hyperbrowser

API mapping

Hyperbrowser	Banana Peel
agents.*.start / startAndWait	POST /api/wrappers/hyperbrowser/task
agents.*.get / getStatus	GET /api/wrappers/hyperbrowser/task/:id
task / finalResult	`data` (string output) + `banana_peel`
sessions / scrape / crawl	Not on this wrapper — CDP via Browserbase sessions or native Responses

Limits / gaps

No scrape/crawl/extract APIs, sandbox, or full CDP session surface.
Per-agent LLM catalogs and data.finalResult nested objects are flattened to string data.
Agent family names share one backend shim today.