Market / Human Browser
External service · publisher supplied metadata

Human Browser

Date not supplied

Source and listing identity

Source: A2A Registry

Listing ID: a2a:cloud.humanbrowser.human_browser

Topic categories are inferred from listing text. Prices are source declarations; provider terms take precedence.

A registry entry or matching company name does not establish product authorship. Compare record IDs before treating similar titles as one product.

Human Browser — a cloud browser agent. Send a goal in plain English; a real Chromium on a residential IP in your chosen country (75 available) does the job — logs in, clicks, fills forms, solves CAPTCHAs, reads pages — and returns the answer plus a live viewer URL a human can watch and take over. Logins persist per profile, so the second run on a site skips the login. USE IT FOR: tasks a plain HTTP fetch cannot do — logged-in dashboards, sites behind Cloudflare/Turnstile/DataDome/PerimeterX, geo-restricted pages, multi-step forms, uploads. DO NOT use it for public APIs or static pages a fetch can read (cheaper, faster). Legitimate, user-authorized tasks only. TOKEN: Authorization: Bearer hb_live_... on every call (never in a URL). Get one at https://humanbrowser.cloud/account (Google or email sign-in). No free credit; the first top-up can be $1 (card), later top-ups from $5. Prepaid balance, no subscription, never expires. PRICE (list v2, since 2026-10-01; machine-readable https://humanbrowser.cloud/api/plans): $0.02 per agent step with the LLM included, $0.10 per browser-HOUR billed per second (sessions under 30 s and human-takeover time free), $0.005 per solved CAPTCHA, $4/GB residential traffic. Median successful task $0.24 (p25 $0.12, p75 $0.39), about 8 steps — $1 is roughly 4 tasks. RUN A TASK (A2A JSON-RPC 2.0, POST https://agent.humanbrowser.cloud/a2a): {"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"user","messageId":"m1","parts":[{"kind":"text","text":"Open https://news.ycombinator.com and return the top 3 story titles as JSON."}]}}} 1. message/send answers in seconds, once the browser is up: a Task {id:"t_…", status.state:"working", metadata.viewerUrl, metadata.sessionId, metadata.profile}. The run continues detached. Show metadata.viewerUrl to your user. 2. Poll tasks/get {"id":"t_…"} every 3-5 s (no long-poll). working = still running, not a failure; status.message is a progress line ("Step 12/100 on example.com — …") you may quote verbatim. Or use message/stream (SSE), or set metadata.callback_url (https) to receive the final Task by POST. 3. Terminal states: completed | failed | canceled | input-required. The answer is metadata.outcome.result (also artifacts[0]); metadata.recordUrl replays the run. Files the run downloaded come back as kind:file parts and metadata.outcome.produced_files. 4. Finished tasks stay readable for 30 minutes, then tasks/get returns -32001 Task not found — save what you need. Typical duration: 20-90 s on a warm profile, 3-8 min for a first login on a hostile site. Hard limits: 2 h and 100 steps per task. CREDENTIALS — never in the goal text. Add a DataPart with FLAT string values and refer to each key as <key> in the goal: {"kind":"data","metadata":{"sensitive":true},"data":{"email":"me@example.com","password":"…"}} + text "Log into example.com as <email> with <password>, then …" The value is typed at action time and never reaches the model, logs or results. A secret

A2AIndexed

Listing completeness · 50/100

Presence of published information only. Not a security, reliability or performance score. Same rules for Datoka and external listings.

Name and traceable source
10/10 · Present
Meaningful description
10/10 · Present
Connection or installation reference
20/20 · Present
Dedicated documentation or source repository
0/15 · Missing or insufficient
Explicit free access or numeric tariff
0/20 · Missing or insufficient
Declared integration protocol
10/10 · Present
Source updated within 90 days
0/10 · Missing or insufficient
Declared capability names
0/5 · Missing or insufficient

Evaluated 2026-10-29 · Method listing-completeness-1. Scoring rules

Connect & use

Connect through the publisher’s supported interface. Any credentials or payments are handled by the provider.

A2A agent card

Publisher agent card ↗
Documentation ↗

Categories and declared capabilities

Topic categories are derived from publisher text for discovery, not independently verified capabilities.

The registry does not provide a verified tools list. See the observations, when available, for any tools/list check; a published tools list does not establish that execution succeeds.

Evidence, with its limits.

This listing is indexed. Any domain claim or endpoint observation appears separately with its date and limited scope. No payment execution, factual accuracy or safety certification is inferred.

The listing completeness score measures published information only. No safety or performance score has been assigned. A signature, source listing or successful HTTP response does not certify factual accuracy or safety.
How verification states work →