공식 API나 MCP가 없는 모든 웹사이트도 백엔드와 통신하기 위해 1차 API에 의존합니다. Unbrowse는 이 웹사이트의 퍼스트파티 API를 사용해 에이전트틱 브라우징을 브라우저보다 50-100배 빠르고 95% 저렴하게 만듭니다.

이것은 호스팅된 Unbrowse 서비스의 오픈소스 클라이언트입니다 (https://unbrowse.ai): REST API용 @unbrowse/sdk TypeScript 클라이언트, 그리고 unbrowse CLI는 그 위에 구축되었습니다.

에이전트 스킬 설치하기:

에이전트와 연결하세요:

클라이언트에서 OAuth 로그인을 완료하세요. 터미널에서: npx unbrowse login (브라우저 내 OAuth, 붙여넣을 필요 없음), 그리고 npx unbrowse run 'top stories on hacker news'.

설치 · CLI · MCP · SDK · 문제 해결

작동 방식

1. 발견하기. 탐색 해제 기능은 개인 기능을 검색한 후 공개 사이트 등록부를 생성합니다 이미 도구에 컴파일되어 있습니다.
2. 런. 매칭 기능은 사이트의 자체 1자 HTTP 요청을 재생합니다. 브라우저 없음. 런은 결과가 검증될 때만 성공합니다.
3. 한 번 배우기. 일치하지 않음: 에이전트가 Unbrowse의 녹화된 클라우드 브라우저(MCP)에서 작업을 수행하거나, 두 개의 HAR 녹화 파일을 업로드합니다 (unbrowse learn). Unbrowse는 요청을 컴파일하여 원콜 기능.

Unbrowse

Every website, even those without an official API or MCP, still rely on a first party API to talk to their backend. Unbrowse calls these website’s first party APIs to make agentic browsing 50-100x faster and 95% cheaper than using a browser.

This is the open-source client for the hosted Unbrowse service (https://unbrowse.ai): the @unbrowse/sdk TypeScript client for its REST API, and the unbrowse CLI built on it.

Set up every agent on this machine (skills, an always-use rule, MCP):

npx -y unbrowse setup && npx -y unbrowse login

Or tell your agent: set up unbrowse - https://raw.githubusercontent.com/unbrowse-ai/unbrowse/main/llms.txt. Skill only: npx skills add unbrowse-ai/unbrowse --skill unbrowse.

Connect your agent:

claude mcp add --transport http unbrowse https://unbrowse.ai/mcp

Complete OAuth sign-in in your client. From a terminal: npx unbrowse login (OAuth in your browser, nothing to paste), then npx unbrowse run 'top stories on hacker news'.

Install · CLI · MCP · SDK · Troubleshooting

How it works

1. Discover. Unbrowse searches your private capabilities, then a public registry of sites already compiled into tools.
2. Run. A matching capability replays the site’s own first-party HTTP requests. No browser. A run succeeds only when its result is verified.
3. Learn once. No match: an agent does the task in Unbrowse’s recorded cloud browser (MCP), or you upload two HAR recordings (unbrowse learn). Unbrowse compiles the requests into a one-call capability. Next time is step 2.

Passwords stay in the Unbrowse password manager; the CLI never takes one.

More: docs/how-it-works.md · Paper: Internal APIs Are All You Need (arXiv:2604.00694)

Commands

unbrowse login [--key ub_live_…]    sign in (browser OAuth) or store an API key
unbrowse discover            your capabilities, then the public registry
unbrowse run  [--set k=v]    run a task from your IP (--from-unbrowse: from Unbrowse); waits for a verified result
unbrowse resume  k=v…        answer what the run asked for, on the same run
unbrowse scrape                read one page as markdown
unbrowse index                 teach Unbrowse a site: each flow becomes a tool
unbrowse learn a.har b.har          compile two recordings into a capability
unbrowse logins                     saved logins, masked
unbrowse registry [query]           public compiled sites (no account)

All commands: docs/cli.md. Exit codes: 0 ok, 1 error, 2 input required, 3 sign-in or login needed, 4 not verified.

SDK

import { Unbrowse } from "@unbrowse/sdk";
const ub = new Unbrowse(); // UNBROWSE_API_KEY
const run = await ub.wait((await ub.run({ task: "top stories on Hacker News", idempotencyKey: crypto.randomUUID() })).runId);