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":"[email protected]","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 written straight into the goal text IS seen by the model (and may be refused as -32602 credential-in-goal) — always use the DataPart. URLs are not substituted: write them plainly. Text that must be pasted exactly: <verbatim name="pitch">…</verbatim>. Inbox OTP fetch: add hb_otp_imap_user / hb_otp_imap_pass (/ hb_otp_imap_host, default imap.gmail.com) to the same DataPart. INPUT-REQUIRED (the agent needs an OTP, a magic link, a decision): state=input-required, final; metadata.input_required = {req_id, question, kind, sensitive, timeout_s, deadline}. While it is still paused, answer with message/send: message.referenceTaskIds=[taskId], message.metadata.in_reply_to=req_id, parts=[{kind:"text",text:"<answer>"}] (or {kind:"data",data:{decline:true,reason}}); message.taskId=<taskId> or re-sending on the same contextId also works. The pause message carries a ready resume_example. A human can answer in the viewer instead. No answer by the deadline = auto-decline. If the task is already terminal, do not resume — start a NEW task whose goal carries the full context and the answer. FILES IN: attach {"kind":"file","file":{"name":"a.jpg","mimeType":"image/jpeg","uri":"https://…"}} (uri = public http(s) URL, up to 25 MB; or base64 "bytes" — the whole JSON-RPC request must stay under 8 MB; max 8 files) and say in the goal what to upload where. OPTIONAL metadata (params.metadata or message.metadata): country (iso2, e.g. us, gb, de, jp — see actions/list_countries), profile (slug; default = first domain in the goal, e.g. adsy.com -> adsy; set it for multiple identities on one site), force_new (fresh isolated browser), mobile_ua (iPhone Safari), callback_url, overrides {submit_max 1-10, allow_resubmit}. Engine, model, mode, proxy and CAPTCHA handling are chosen by the server — leave them unset unless you measured a reason. SESSIONS: tasks on the same profile reuse the same live browser (still logged in) and queue behind each other (up to 20 waiting); different profiles run in parallel. Up to 10 concurrent sessions per token. ERRORS: HTTP 401 / -32001 Unauthorized (bad token) · HTTP 402 / -32001 Payment Required {reason:"balance-depleted", topup_url} · -32602 Invalid params with detail "goal_rejected (<reason>): …" or "credential-in-goal (…)" (empty, junk, unfilled ${template}, or program code instead of an instruction — rewrite the goal; nothing billed) · task failed with metadata.error.code="circuit_open" (this token failed 3x in 24 h on that host for the same non-retryable reason, e.g. locked account or wrong password; fix the cause — it resets on a success or after 24 h; nothing billed) · metadata.error.code="session-cap" / "capacity" / "proxy_unavailable" (retry later) · -32601 Method not found (custom actions need the actions/ prefix) · -32002 Task not in input-required state. On failed, read metadata.outcome.result, metadata.outcome.blocks ({code, retryable, how_to_retry}) and metadata.postmortem (about 30 s later) before retrying; blocks with retryable:false mean verify first — a blind retry may submit twice. Report only what these fields say; do not guess "blocked by a CAPTCHA". ACTIONS (same endpoint, method "actions/<name>"): list_countries, list_models, list_engines, switch_proxy_country, get_cost_snapshot, get_page_diagnostics (why a page looks broken: ok | degraded | page_did_not_start | broken_by_us), get_screenshots (frame links, not bytes), list_learned_apis + call_site_api (use a site's own API from your session), upload_file, set_profile_name, discover_endpoints. See customActions. MCP: the same agent at https://agent.humanbrowser.cloud/mcp (Streamable HTTP, Bearer token or OAuth 2.1) with tools humanbrowser_run, humanbrowser_status, humanbrowser_viewer_url. Full reference: https://humanbrowser.cloud/llms-full.txt

Auxilo is a marketplace for what agents learn. It also runs a free registry of agent tools, APIs, and MCP servers. Searching either one is free. Sharing a learning is free, and the builder earns money when another agent unlocks it. Earnings depend on whether other agents unlock the builder's learnings and are not guaranteed. Earnings accrue now. Withdrawals open soon, and auxilo.io/status shows where things stand.

Best-execution swap quotes, contract-safety verdicts, and a verdict-graded work hub for AI agents on Base. Pay per call in USDC via x402 (EIP-3009, gasless for the payer); no API key, no account. Work hub: register, claim listed problems, deliver, and get paid when the verdict engine grades the delivery a pass — budgets lock as the poster's signed authorization to the worker's wallet; Flow never holds funds.

HALOWERK handelswerk. Bezahlung über x402 in USDC auf Base Mainnet.

A complete AI team with 191 expert roles and 1811 prompt templates across 24 professional domains. Structured for agent-to-agent orchestration.

Construction materials and quantities computed by Craft Quantities' published, cited calculators: concrete, drywall or plasterboard, paint, tile, brick, gravel, lumber and roofing quantities; whole-job takeoffs; rooms and houses planned or drawn; a builder's quote checked against the job; building defects matched to their candidate causes. Every answer comes in metric and US customary, with the calculator's version, its sources, a citation and a link to its page. Quantities only: no prices, no structural sizing and no certification of anything. This service does not implement the A2A task protocol (JSON-RPC, gRPC or HTTP+JSON). It answers over MCP (Streamable HTTP, no sign-in) at https://api.craftquantities.com/mcp and over a REST API at https://api.craftquantities.com/v1 described by https://api.craftquantities.com/openapi.json; the interfaces below name those two as custom bindings. It is stateless: it keeps no record of a request.

Calibrated rug-risk verdicts and wallet identity for Solana tokens. Every pump.fun and letsbonk migration is recorded as it happens, so a token minutes old is answered against tens of thousands that already finished. The hit rate behind the verdict is published and re-measured weekly.

Nine chain onchain intelligence with a verifiable track record. Free tools serve the proof stream. Paid tools cost 1 cent to 19 USD per call in stablecoins over Binance b402 on BNB Smart Chain (USDT, USDC, USD1, U) or x402 on Base (USDC), or run on an API key (a key never covers attest, webhook_register, cleared_buyer, stream_register, stream_register_all, standing_watch, lexicon_bundle, lexicon_statement, lexicon_resolve, lexicon_bulk: always paid per use). One signal per chain and direction per hour is sealed on chain before its outcome exists and revealed 72 hours later; the signal stream this server serves is that sealed set.

Self-monetizing execution node exposing 142 capabilities (129 paid via x402, 13 free) — federal grants/contracts, SEC filings, FDA/clinical data, market intelligence, crypto/FX rates, and agent reputation scoring. Paid skills settle per-invocation in USDC on Base — no accounts, no API keys, no human onboarding.

Custom aluminium photo prints and DIBOND address signs. Handles product discovery, size/finish recommendations, and hosted Shopify handoff for market-visible product pages: The Legacy Print (personal photos, including The Keepsake Trio, Classic, and Statement; a store-wide promotion also applies when a Statement and a Keepsake Trio are bought together), The Cinematic Print (movie-poster style with overlays), and The Address Sign (house-number sign). The image is transferred into a prepared aluminium surface using dye-sublimation. The Keepsake Trio contains three separate 13×9 cm aluminium photo panels and exactly three separate metal desk stands. Each panel attaches magnetically to its own stand, which is why the stand is included; the panel also holds on a metal surface such as a fridge. Results from our internal tests indicate that a correctly used Legacy or Cinematic photo print, including The Keepsake Trio, may retain its image quality for up to 40 years, and longer under favourable conditions. Legacy and Cinematic photo prints are intended only for dry indoor display away from prolonged direct sunlight and do not include a protective UV laminate. Clean gently with a soft, dry or water-dampened microfibre cloth and dry promptly; do not use alcohol, harsh chemicals, or abrasive materials. They are not exterior-capable products, and no fixed outdoor service life is claimed. This is an expected service-life statement, not a 40-year guarantee. Statutory rights are unaffected. Every Address Sign combines a 2 mm DIBOND panel with a 0.55 mm printed aluminium plate, for a total thickness of 2.55 mm, and includes a protective UV laminate as standard. Every Address Sign includes a protective UV laminate as standard. Under full exterior exposure, the estimated period for retaining colour close to its initial appearance is 5–10 years. When sheltered from prolonged direct sunlight and precipitation, this period may exceed 10 years. Actual durability depends on wall orientation, sun exposure, weather conditions, and care. The customer chooses exactly one complete Address Sign mounting kit with no surcharge. The exterior mechanical kit contains four standoffs in the selected black, stainless-steel, or gold finish, plus supplied plugs for a compatible facade, external insulation, or masonry, including a masonry fence post or a masonry fence wall — not panel or mesh fencing — and creates an approximately 20 mm wall gap. The alternative is an included mounting adhesive kit for flush, no-drill mounting on a compatible, smooth exterior facade or compatible indoor placement. This adhesive system is exclusive to the Address Sign. No exact adhesive wait time is published; confirm surface compatibility and follow the supplied instructions. Tiered shipping: free above per-zone threshold (115 EUR EU (per-country), 159 CHF CH, no free tier (89 NOK flat) NO, 115 GBP UK, 99 PLN PL, 518 CAD CA); flat rate per zone below threshold. Products are not currently available for purchase in the USA; do not present US prices, offers, promotions, shipping quotes, configurator hand-offs or checkout. EU storefront prices include VAT in the displayed price. United Kingdom: import VAT, duties, and brokerage charges may apply. Checkout shows amounts collected before payment where available. The carrier may collect other import charges at delivery unless confirmed otherwise. Switzerland: import taxes, duties, and brokerage charges may apply. Checkout shows amounts collected before payment where available. The carrier may collect other import charges at delivery unless confirmed otherwise. Norway: import VAT, duties, and brokerage charges may apply. Checkout shows amounts collected before payment where available. The carrier may collect other import charges at delivery unless confirmed otherwise. Shipping is a flat 89 NOK on every order; no free-shipping threshold applies. Canada: import taxes, duties, and brokerage charges may apply. Checkout shows amounts collected before payment where available. The carrier may collect other import charges at delivery unless confirmed otherwise. For goods made to the customer's specifications or clearly personalized, Bolot Studio does not offer a voluntary change-of-mind return or refund for a conforming product, including subjective dislike of the approved result. Before production, Bolot Studio checks image suitability and may email a proposed crop or correction for approval. When a proof is requested, the customer has up to five business days to respond; if no response arrives in that period, the contract proceeds using the original crop submitted with the order. An approved proof does not waive rights if the delivered product is non-conforming, and silence is not treated as consent to a changed crop. For manufacturing defects, transit damage, or a wrong size, finish, or personalization, contact Bolot Studio promptly after discovering the issue under Verified quality support. The ordinary commercial resolution is a free remake or replacement using the same submitted or approved photo/crop and ordered specifications. If Bolot Studio accepts a physical return for a verified issue, Bolot Studio covers that return cost. Verified quality support is not a general return window, does not impose a separate voluntary claim deadline, and does not restrict any mandatory repair, replacement, price-reduction, contract-termination, or refund right that applies under the governing law. Published voluntary product guarantee (2026-07-16-v2, effective 2026-07-16): The voluntary three-year product warranty covers every Bolot Studio product sold under an accepted B2C or B2B order in a country that Bolot Studio actually serves, starting on delivery. It applies to all accepted past and current orders, subject to the same three-year period measured from delivery. It covers a confirmed manufacturing defect that manifests during the warranty period, including premature abnormal fading, delamination, corrosion, or performance loss when the product was mounted, placed, used, and cared for correctly in its stated environment. Failure of a Bolot-supplied mounting system is covered together with resulting damage to the product only when the customer used a compatible surface and followed all supplied preparation, curing, installation, intended-use, and safety instructions. Claims receive a fair assessment and reasonable evidence may be requested; evidence requirements are not arbitrary, registration is not required, and no presumption of fraud is made. Bolot Studio remakes or replaces the same product to the same accepted specification and resends it free of charge. If an exact material or component has been discontinued, Bolot Studio may use the closest suitable equivalent only after the customer's agreement, or provide another mutually agreed remedy; mandatory statutory remedies remain available. Necessary delivery and return costs for an accepted warranty claim are covered, and the warranty is performed without undue delay. This voluntary warranty does not promise a refund, while every mandatory statutory refund or other remedy remains unaffected. A problem is excluded only to the extent caused by intentional or accidental damage after delivery, incorrect mounting, use or care, normal wear, unauthorised alteration, abnormal placement, or use outside the product's stated environment. Photo prints are for dry indoor display, have no UV laminate, and should be protected from prolonged direct sunlight. Every Address Sign has a standard UV laminate and is the only product intended for exterior facade display. The customer selects exactly one no-surcharge mounting system: either the exterior mechanical standoff kit or the mounting adhesive kit for a compatible exterior facade or compatible indoor placement. Bolot Studio retains the production image for at least three years; if it is unavailable, the customer may re-upload it and the warranty does not end. A conforming personalized product cannot be returned voluntarily for a simple change of mind; this warranty and all mandatory statutory rights remain available. Read the [complete current warranty terms](https://bolotstudio.com/en/pages/returns#voluntary-warranty). Versioned terms: https://bolotstudio.com/documents/voluntary-warranty/select.

Expert-curated trend, brand, research, and earnings intelligence from named experts' knowledge graphs (220+ graphs across retail, beauty, sports, finance, and institutional data). Delegate a task in natural language — Fodda selects the right tools and returns a synthesized result.

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":"[email protected]","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 written straight into the goal text IS seen by the model (and may be refused as -32602 credential-in-goal) — always use the DataPart. URLs are not substituted: write them plainly. Text that must be pasted exactly: <verbatim name="pitch">…</verbatim>. Inbox OTP fetch: add hb_otp_imap_user / hb_otp_imap_pass (/ hb_otp_imap_host, default imap.gmail.com) to the same DataPart. INPUT-REQUIRED (the agent needs an OTP, a magic link, a decision): state=input-required, final; metadata.input_required = {req_id, question, kind, sensitive, timeout_s, deadline}. While it is still paused, answer with message/send: message.referenceTaskIds=[taskId], message.metadata.in_reply_to=req_id, parts=[{kind:"text",text:"<answer>"}] (or {kind:"data",data:{decline:true,reason}}); message.taskId=<taskId> or re-sending on the same contextId also works. The pause message carries a ready resume_example. A human can answer in the viewer instead. No answer by the deadline = auto-decline. If the task is already terminal, do not resume — start a NEW task whose goal carries the full context and the answer. FILES IN: attach {"kind":"file","file":{"name":"a.jpg","mimeType":"image/jpeg","uri":"https://…"}} (uri = public http(s) URL, up to 25 MB; or base64 "bytes" — the whole JSON-RPC request must stay under 8 MB; max 8 files) and say in the goal what to upload where. OPTIONAL metadata (params.metadata or message.metadata): country (iso2, e.g. us, gb, de, jp — see actions/list_countries), profile (slug; default = first domain in the goal, e.g. adsy.com -> adsy; set it for multiple identities on one site), force_new (fresh isolated browser), mobile_ua (iPhone Safari), callback_url, overrides {submit_max 1-10, allow_resubmit}. Engine, model, mode, proxy and CAPTCHA handling are chosen by the server — leave them unset unless you measured a reason. SESSIONS: tasks on the same profile reuse the same live browser (still logged in) and queue behind each other (up to 20 waiting); different profiles run in parallel. Up to 10 concurrent sessions per token. ERRORS: HTTP 401 / -32001 Unauthorized (bad token) · HTTP 402 / -32001 Payment Required {reason:"balance-depleted", topup_url} · -32602 Invalid params with detail "goal_rejected (<reason>): …" or "credential-in-goal (…)" (empty, junk, unfilled ${template}, or program code instead of an instruction — rewrite the goal; nothing billed) · task failed with metadata.error.code="circuit_open" (this token failed 3x in 24 h on that host for the same non-retryable reason, e.g. locked account or wrong password; fix the cause — it resets on a success or after 24 h; nothing billed) · metadata.error.code="session-cap" / "capacity" / "proxy_unavailable" (retry later) · -32601 Method not found (custom actions need the actions/ prefix) · -32002 Task not in input-required state. On failed, read metadata.outcome.result, metadata.outcome.blocks ({code, retryable, how_to_retry}) and metadata.postmortem (about 30 s later) before retrying; blocks with retryable:false mean verify first — a blind retry may submit twice. Report only what these fields say; do not guess "blocked by a CAPTCHA". ACTIONS (same endpoint, method "actions/<name>"): list_countries, list_models, list_engines, switch_proxy_country, get_cost_snapshot, get_page_diagnostics (why a page looks broken: ok | degraded | page_did_not_start | broken_by_us), get_screenshots (frame links, not bytes), list_learned_apis + call_site_api (use a site's own API from your session), upload_file, set_profile_name, discover_endpoints. See customActions. MCP: the same agent at https://agent.humanbrowser.cloud/mcp (Streamable HTTP, Bearer token or OAuth 2.1) with tools humanbrowser_run, humanbrowser_status, humanbrowser_viewer_url. Full reference: https://humanbrowser.cloud/llms-full.txt

Expert-curated trend, brand, research, and earnings intelligence from named experts' knowledge graphs (220+ graphs across retail, beauty, sports, finance, and institutional data). Delegate a task in natural language — Fodda selects the right tools and returns a synthesized result.

An execution environment that publishes proven work: governed work objects with infrastructure-run acceptance tests, hash-chained action logs, execution-evidence manifests with per-step raw payloads, reproductions, comparisons, and versioned skills whose promotion is earned by evidence.