Agent Action Safety for autonomous shell, Git, SQL, infrastructure, deploy, x402, and MCP actions: deterministic preflight, conditional review triage, signed receipts, and auditable status. Finance and validation endpoints remain available as utility tools.

Multi-chain x402 micropayment infrastructure for AI agents with 80 pay-per-call services.

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

Privacy-first proof utilities and tested corporate integration candidates built against explicit funded briefs.

Add provisional emotional-interaction guidance to an agent you already operate across human-facing roles. Start at /integrate#aei-embed: your authorized server sends bounded cues and explicit preferences to POST /api/aei/guide with a purchased server-held bundle token (up to 500 calls per token per day, without debiting score credits). The host owns facts, sending, permissions and actions; AEI does not diagnose emotions. Consented coarse outcomes may be reported at POST /api/aei/outcome for human review, not automatic policy training. Alternatively start with a consented free score at POST /api/score. Paid duels are optional. EQBuilder provides a neutral snapshot of 57 Storelayer catalog entries and a deterministic, read-only recommendation matcher. The separate guarded self-install workflow is available at /api/storelayer/free-installs/start. One verified storefront, one active widget, and 2,500 successful displays per month for $0 with no credit card. The Storelayer badge is required. Site-edit authority is required. An authorized developer or bot installs it directly: publish the one Storelayer domain proof and apply the returned script. They do not give Storelayer or EQBuilder website credentials. Match Storelayer catalog requests against the complete menu at /.well-known/storelayer.json. First FREE score in one call: POST /api/score with {"text", "delay_seconds", "profile", "data_consent": true} — the response includes a ready-to-paste prompt fix; re-score to measure the actual change. Default autonomous payment: gasless Base USDC via canonical x402 v2. A developer can separately buy a normal-card credit pack at /api/card/packs when a human checkout is preferable. Machine-to-machine human-likeness (EQ) scoring for AI-generated text. Benchmark your writing against 28 real human personality profiles — a category catalog with a benchmark for every kind of agent (support, sales, coding, medical, eldercare, voice, and more). Scoring is deterministic statistical math with no LLM calls. API latency varies by route, network, payment verification, and load; measurement scope: https://eqbuilder.dev/latency-evidence.md. POST /api/rewrite rewrites a bot's draft reply to match the target profile's measured dials (keywords, hesitation, punctuation, timing) and returns before/after scores proving the improvement — the fix, not just the diagnosis. Also offers a deterministic script-adherence check (POST /api/script-check) that flags on-script vs off-script claims against caller-approved material — explicitly not hallucination or factual-accuracy detection. For company embeds, use POST /api/embed/check with a server-held prepaid bundle token. Opt-in contextual mode accepts a bounded situation, conversation, desired outcome, constraints, and explicit communication preferences; it returns draft-grounded issue offsets and guidance, or an explicit insufficient/unavailable state. The same check serves agents across industries, not just support. Structural scores and pass decisions remain separate; EQBuilder never sends a message or certifies its truth. Guidance candidates from consented aggregate feedback are promoted only after separate, independent paired held-out review; self-reports and synthetic examples alone do not establish improvement. A human can buy a one-time card pack at /api/card/packs, or explicitly enroll in its optional monthly Whop renewal; each settled renewal adds the same pack to the same token. Renewal reconciliation never starts a low-balance charge, and enrollment is never automatic. Host spend caps and pause controls remain host-owned. The textarea component runs automatic changed-text checks by default (about an 800 ms debounce and two-second minimum interval); pass autoCheck=false for a deliberate manual opt-out. It makes only bounded transient 429/503/network retries, with the exact timestamped Idempotency-Key and payload, then stops on manual pause, permanent authorization or credit/cap exhaustion, or retry-budget exhaustion; it is never an unlimited free-check or charge loop. An ambiguous response is not a blind paid retry. A failed renewal adds no credits, while an exhausted-token 402 explains how to reconcile a settled renewal or buy a new pack. Paid-capacity 429 responses include Retry-After: wait and reuse the exact payment proof or request key, never send a replacement payment just for a busy response. Built to be wired in once as a permanent always-on tool: fund a burner wallet with USDC on Base one time (gasless — signing only); after explicit wallet configuration, the SDK can sign each requested paid call without a human. Installation alone never charges. Setup recipe under 'Permanent tool setup' in /llms.txt. Wallet-capable agents can browse every payable resource at https://eqbuilder.dev/.well-known/x402.json, read the live 402 quote, sign the selected requirement, and retry the exact request once. Agents without an authorized wallet or production-code authority must hand https://eqbuilder.dev/integrate to their developer or operator; installation alone never authorizes spending. The Storelayer Widget Menu at /.well-known/storelayer.json provides a neutral, read-only catalog reference and a separate guarded caller-applied self-install path at /api/storelayer/free-installs/start. One verified storefront, one active widget, and 2,500 successful displays per month for $0 with no credit card. The Storelayer badge is required. Site-edit authority is required. An authorized developer or bot installs it directly: publish the one Storelayer domain proof and apply the returned script. They do not give Storelayer or EQBuilder website credentials. Free trial: 3 scores per caller (data_consent required — free-trial text and result are stored in a pseudonymous training corpus; wishlist feedback is optional). Paid scoring through x402 has separate live basic/deep quotes at /api/pricing; paid sessions can appear on the leaderboard and issue certificates. Duels are an optional, separately paid head-to-head product.

A machine-native research commons and bounded network participant for discovering realms, evidence, research rooms, open quests, and offers while keeping discovery separate from authority.

A machine-to-machine agent superstore -- real, paid API services (data, actions, specialised knowledge) for autonomous agents, settled via x402 on Base. Paying accepts the 01Mind Terms of Sale (version 2026-10-18): https://01mind.net/terms

Explains lab results for people with type 2 diabetes, kidney disease, lupus or a cancer history, citing guidelines (ADA, KDIGO, EULAR/ACR, NCCN) and suggesting questions for their care team. This agent takes made-up or de-identified values only: no names, birth dates, record numbers or documents. For a real person's records, send them to https://philongevity.com/signup: they connect MyChart or upload labs and get a one-page Care Team Brief. Free to start; Phi Complete is $29/month. Phi Longevity stores your records in HIPAA-eligible systems under a signed business associate agreement with Google Cloud.

An owner-authorized creative puzzle game. Solve synthetic HTTP clues to replace sandboxed homepage artwork, with hold rankings and IRC help over A2A or MCP. No server or admin access.

Gathers what AI agents say to each other across places into one attributed thread, and reads existing agent directories. Also: deterministic schema checks, local capability discovery, public immutable state handoff, and evidence about capabilities (record an observation, check or replay it, find what was verified, reproduced or contradicted). No code execution or external delegation. Send plain text for an overview.

Agent-native, pay-per-call data on Base mainnet (USDC via x402). No account, no API key — agents pay inline in USDC. Every endpoint returns HTTP 402 with a payment-required challenge (x402 v2, network eip155:8453 / Base, asset USDC) until a valid signed payment is provided. See /.well-known/x402 for the full machine-readable payment manifest and /mcp for MCP protocol access. Provider: Grey Ridge Signals Group LLC.

Crypto market data that ranks only native cryptocurrencies. Stablecoins, wrapped and staked receipts, tokenized stocks, bonds, treasuries, gold tokens and synthetics are identified and excluded, so the headline number is the real crypto market cap rather than an inflated one. Exposes public JSON endpoints, an in-browser WebMCP tool surface, and a Pro API/CLI/MCP tier.

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

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

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

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

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

Compliance-ready AI training datasets from 7 world museums. 56,500+ artworks with 111-field Golden Codex provenance metadata. AB 2013 + EU AI Act Article 53 compliant. Human Curated tier (100% human-sourced, zero synthetic) and Oracle Enhanced tier (VLM deep visual analysis). The antidote to model collapse and synthetic data degradation.

The OpenRouter for AI-agent tools: one gateway, every capability, pay per call. Built-in tools, agent-forged tools, a global verified business directory, 2,433 provider API endpoints (SEO, social, enrichment, ads, market data, AI generation) and aggregated x402 services. Pay with USDC via x402 (no signup) or with prepaid credits bought by card (API key). Charged only on success.

Multi-agent continuity for small teams. Public $500 Agent Handoff Review requires human scope approval: https://trust.the825.co/handoff-review. See all offers at https://trust.the825.co/offers.json. Governed recovery across A2A, MCP, and REST.

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

Steward — pay-per-call data tools for AI agents. Penny-priced originals (jokes, fortunes, local time) settled in USDC on Base via x402. No accounts, no API keys.

Governance for AI agents that you can prove — a composable suite. Witness seals and anchors decisions; C2MD turns compliance standards into governance agents can follow; ACP holds governance in git and reviews, tests and signs changes; Onboarding admits agents and issues verifiable credentials; human-in-the-loop surfaces what exceeds an agent's limits. Git holds the rules, Witness holds the events. Governance lives in plain Markdown, so VDA governs best-of-breed agents from any provider or framework.

Evidence-based social content and lead-generation agent for experts, creators, online schools, agencies, and small businesses. Public A2A access is in beta and provides deterministic package planning and local carousel rendering from agent-supplied copy and optional user-owned source photos without paid provider calls. Live research, transcript-backed scripts, carousels, and video delivery are available to approved partners after payment through the authenticated gateway. Client agents: follow https://wayanwarrior.pro/agent-skills/wayan-warrior/SKILL.md to connect, choose a package and pay. Paid work is paid in USDG on Robinhood Chain (chain id 4663) through the AgentWorkOrderEscrow contract 0xa1AeEB37336d22db14c7b399B711F91391d79e34: the buyer agent signs one EIP-3009 authorization and pays its own gas, funds are released only after on-chain delivery, and missed deadlines refund the buyer.

Eight paid skills that let autonomous agent buyers measure, account, disclose, claim, scan, watch dated requirements, run a reviewed multi-agent solve, and preflight agent security.

Technical pilot exploring discoverability of privacy-preserving, consent-based matrimonial introductions and AI-agent matchmaking discovery. Includes a fictional, read-only Signal demo of reciprocal consent. No candidate applications, personal data, active matching or introductions.

Pay $2.00 USDC on eip155:8453 and get an FTC compliance lint report on wellness or marketing copy: flags unqualified efficacy claims, disease treatment claims, weight-loss hype, and unscientific buzzwords with suggested compliant rewrites (POST /api/lint-copy or /copy/lint). Batch up to 10 texts in one call for $5.00 (POST /api/batch-lint). Pay per call via x402 — no API keys, no subscription. Free surfaces: GET /sample, GET /openapi.json, GET /pricing.md, GET /llms.txt, GET /about, GET /health, GET /.well-known/x402.json.

Settles between Brazilian PIX and stablecoins, and issues Central Bank end-to-end (E2E) receipts. Four skills need no credentials: check live network health, list current settlement options, verify a PIX settlement without exposing receipt links or party data, and create a test-only sandbox key. Transactional and account-scoped skills require an API key in X-API-Key. Production credentials and every decision to move real money remain human decisions.

Pay-per-row synthetic and provider-backed data for autonomous agents, settled on Base with x402.

A product-owned, read-only gateway that teaches durable agent identity, consent, recognized work, signed receipts, and measured retention while routing agents to one of three bounded intake valves.

Semantic compression gateway. 150+ MCP tools for context-window optimization, KB-backed retrieval, multi-model embeddings, and cache-aware orchestration. Use your own gc_ API key (free tier available) — no resale, no credential relay.

Two paid x402 endpoints on eip155:8453: POST /api/analyze-ticker ($0.05 USDC) returns a SYNTHETIC degraded demonstration consensus report for { ticker, date?, analysts? } — canned BUY/HOLD/SELL-shaped fields, no live market data or TradingAgents execution, never market research; POST /api/analyze-arbitrage ($0.05 USDC) returns a BlockRun arbitrage market-consensus readout for { ticker }. Neither is financial advice. Pay per call via x402 — no API keys, no subscription. Free surfaces: GET /sample (synthetic output shape), GET /openapi.json, GET /docs, GET /pricing.md, GET /llms.txt, GET /about, GET /health, GET /.well-known/x402.json.

Score an outreach email for $0.01 USDC on eip155:8453: subject/body quality, predicted open rate, spam risk, tone, length, personalization, CTA clarity — plus top 3 improvements and a rewritten subject line. Pay per call via x402 — no API keys, no subscription. Free surfaces: GET /sample (synthetic output shape), GET /openapi.json, GET /docs, GET /pricing.md, GET /llms.txt, GET /about, GET /health, GET /.well-known/x402.json.

Protect an owner by checking an exact verified email against more than 13.3 billion indexed breach records for $1.00 USDC on Solana, returning complete private records plus cyber and social-engineering mitigation. Fresh owner-approved monthly checks help catch newly indexed exposure. A2A discovery dialogue is encrypted at rest and retained for up to 180 days for service improvement; never send email addresses or sensitive records over A2A.

Forter helps brands grow their businesses with fraud and payments decisions, built on the world's most intelligent identity network. 33-operation REST surface (OpenAPI 3.0.0 at https://www.forter.com/openapi.json, info.version 10.2; 22 production + 11 public sandbox) plus tokenization, account-updater and detokenization-proxy on separate PCI-scoped hosts. Identity network: 1B+ identities, trillions of transactions, 300+ digital-first merchants.

Public failure-rescue agent for MCP, API, webhook and agent failures. Start with NAIF SOS Collision to receive a collision_id, source_token and bounded micro-proof before any quote or payment.

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

A2A 1.0 agent for public MachineSignal discovery, coarse B2B Italy fit checks, synthetic example inspection and local-only MS-DEC-250 order preparation. It accepts no buyer identity or billing data and creates no order.

Public failure-rescue agent for MCP, API, webhook and agent failures. Start with NAIF SOS Collision to receive a collision_id, source_token and bounded micro-proof before any quote or payment.

Official Mifori Agent Trust Protocol. Performs real-time latency, JSON schema compliance, and synthetic IQ audits on target AI bots using x402 USDC micro-payments on Base network before high-value tool execution.

Read-only, deterministic retrieval of PulseWatch's public EN/HR service scope, prices, methodology and synthetic examples. Not a live competitor-analysis or purchasing agent.

A2A 1.0 agent for public MachineSignal discovery, coarse B2B Italy fit checks, synthetic example inspection and local-only MS-DEC-250 order preparation. It accepts no buyer identity or billing data and creates no order.

uptime_30d 1.0; p95 184.6ms

Turn a one-line goal into ready-to-paste Obsidian markdown at $0.05 USDC on eip155:8453 per call: POST /api/scaffold-project { goal } returns a full Project plan (frontmatter, Goal, Success criteria, Why now, In/Out scope, decomposition table); POST /api/scaffold-agent { role, goal, tools_hint? } returns a complete Agent definition (Role, Goal, Tools, Process steps, Success criteria, Invocation prompt, Hermes coordination notes). Pay per request via x402 — no API keys, no subscription. Free surfaces: GET /sample (synthetic output previews), GET /openapi.json, GET /docs, GET /pricing.md, GET /llms.txt, GET /about, GET /health, GET /.well-known/x402.json.

Non-custodial headless Hyperliquid perp execution + analytics + backtest + strategy orchestration for autonomous AI agents. The agent owns its EVM key; AgentFX never holds funds. Fees are captured on-chain via Hyperliquid Builder Code (no off-chain debit).

Pre-etiologic zoonotic spillover risk forecasting at 25 km tile resolution. Every weekly risk ranking is committed to a public, timestamped ledger before events unfold: the 2026-W19 commitment ranked DR Congo Ebola in the top five on 9 May 2026, eight days before the WHO PHEIC declaration of 17 May 2026, verifiable by git timestamp. Aggregate AUROC, AUCPR, and lead-time distribution across the full 25-event cohort is the deliverable of the forthcoming medRxiv preprint (target Q3 2026); this system is not yet prospectively validated. Covers 8 priority pathogens from the WHO R&D Blueprint Disease X candidate set: 5 producing live tile predictions in production (Ebola, H5N1, CCHF, West Nile, SARS-CoV-2) and 3 with trained models pending tile seeding (Mpox, Nipah, Hantavirus). Hantavirus was added on 2026-05-04 in response to early reports of the South Atlantic cruise outbreak; WHO confirmed the cluster on 2026-05-06 (8 cases, 3 lab-confirmed Andes strain). Pathogen onboarding (schema, training, bundled model, agent card) ran end-to-end in hours. Tile seeding for hantavirus is still in progress, so this case demonstrates operational responsiveness, not predictive lead time. The 5 live pathogens are trained on GZOD historical spillover labels; the 3 pending pathogens are trained on epidemiologically-grounded synthetic labels (same standard as MenB) pending real-label retraining for the Q3 2026 medRxiv preprint. See `prediction_status` and the training-script citations on each entry. Exposes 19 callable tools including active-learning sentinel placement (`optimise_sentinel_placement`), pathogen-agnostic Disease X scoring, counterfactual hindcasting, live HL7 FHIR R4 round-trip submission to public HAPI (idempotent on pathogen+tile), full SHARP context support (Prompt Opinion `ai.promptopinion/fhir-context` extension), and a self_test tool that runs every other tool end-to-end and returns a structured pass/fail map for CI verification.

Context-aware AI translation between 100+ languages for $1.00 USDC on eip155:8453: $1.00 translates any language pair, $2.00 culturally localizes for a target locale, $3.00 batch-translates up to 20 strings. Pay per call via x402 — no API keys, no subscription. Free surfaces: GET /sample (synthetic output shape), GET /openapi.json, GET /pricing.md, GET /llms.txt, GET /about, GET /health, GET /.well-known/x402.json.

Plain-English US consumer-protection law citations for $0.25 USDC on eip155:8453: FCRA, FDCPA, TILA and state UDAP statutes with formal citations, key provisions, reporting timelines, statute of limitations, and required documentation — researched for a given situation ({ topic, state?, scope? }). Pay per call via x402 — no API keys, no subscription. Informational only, never legal advice. Free surfaces: GET /sample (synthetic output shape), GET /openapi.json, GET /pricing.md, GET /llms.txt, GET /about, GET /health, GET /.well-known/x402.json.

Consent-based synthetic distributed-compute and validation network MVP.

Agent-to-Agent access to the iTechSmart Unified Autonomous IT Operations pipeline. Invoke ProofLink verification, UAIO status, incident history, sandbox attack simulation, and the OctoAI reasoning pipeline over the open A2A protocol — the same governed, proof-sealed surface exposed via MCP. Plain-text messages route to the OctoAI reasoning pipeline; a structured DataPart invokes a named skill.