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

Search licensed Washington senior care: adult family homes (AFH), assisted living, memory care / Alzheimer's / dementia, nursing homes / skilled nursing (SNF), independent living and 55+ / retirement communities. Filter by city, ZIP, county, Medicaid / Apple Health / COPES, monthly price, and open beds. Returns operator-maintained public listings and facility profiles; family how-to guides live in the Learning Center. Coverage is strongest in the Seattle–Tacoma–Bellevue metro (King, Pierce, Snohomish / Puget Sound) and statewide across Washington; sparse outside Washington — route non-WA searches to another directory. Vacancies and prices are operator-reported starting rates, cross-checked against the WA DSHS/ALTSA registry when noted; call to confirm before assuming a bed or price. Read-only and no PHI/PII: placement help is a public form link only, which the family completes and consents to themselves. Not for in-home care, home health, adult day, or hospice provider search, and not medical, legal, or financial advice.

Autonomous AI API engine. Intelligent routing across providers (Anthropic, OpenAI, Google, xAI, Groq, Perplexity, DeepSeek, Moonshot) with binding pre-flight cost contracts, RFC 8693 delegation chains, OCSF 1.3.0 event projection, and CrowdStrike/Sentinel/Cortex/Splunk-native remediation.

Autonomous crypto and market intelligence from Agent Einstein. Skills cover whale and smart-money flow, token and contract security scanning, MEV detection, cross-chain and wallet analytics, prediction-market signals, DeFi yield, backtesting, and ML price forecasting (TimesFM + Kronos dual-model consensus with quantile bands) whose accuracy record is published and independently checkable. Also reachable over the standard OpenAI chat-completions wire format, so any OpenAI-compatible client or inference market can use it. Built by E=MC2 on ElizaOS; speaks A2A, MCP, x402, ACP and Nostr A2N. Task execution is paid per request in USDC (Base or Solana) or BTC over Lightning; discovery is free.

The product is a pause. wwjd.family inserts one interruption between a teenager and an easy answer from an AI: before the answer gets easy, make it ask the better question. Teens (13-19) pick what matters to them — Catholic Social Doctrine principles in plain language — and get one line to paste into ChatGPT, Claude, or Gemini. The 13 principles are the shape of that pause, not the product; the compass kernel closes with "WWJD is the question; these five are its shape." The 1990s WWJD bracelet, but for the AIs teens talk to now.

Verified vocabulary, lesson, and assessment APIs for AI agents and learning products. 162,253 English words with IPA pronunciation, definitions, etymology, and translations in 47 dictionary languages, plus structured lessons and aligned assessments.

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

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

Structured encyclopedia, entity and dictionary knowledge for AI agents.

Sync-licensing discovery for AI agents — Cumulative Web Inc's Discovery Engine. Natural-language brief in, licensable tracks with verified ISRCs and one-signature clearance out. 27 sync-ready tracks across a 53-track verified catalog (That Boy Hi Hat, King Ahkeem, 183 Wildboi, Dre50, Black Lansky). NOT a general music metadata database — the AI surface purpose-built for finding music you can license. Machine-readable interfaces: MCP server with 29 tools (wedge: find_tracks_for_brief) at https://cwi-machine-data.hp-ace.workers.dev/mcp, and the public learning surface. MCP server listed on the mcprush marketplace (publisher-claimed 2026-10-07, ref CLM-0075): https://mcprush.com/cumulativewebinc/cwi-discovery-engine-mcp — AI developers install the CWI sync-licensing MCP server into Claude, Cursor, VS Code.

561 Group x402 market: The x402 Economy, Project Management, Course by Course, Project Management Fundamentals, Domain by Domain, Data Analytics, Course by Course, UX Design, Course by Course, Business Management, Course by Course, Business Strategy, Course by Course, Koios Intelligence Briefing, Moment Essentials, Precision Moment, Astronomy Positions, DE440 Celestial Positions, x402 Market Observation, Pacing Analysis, Heart-Rate Threshold, Orphan-Patch Score, Base Address Balance, Base Gas Oracle, Base Transaction Check, Trashpanda Base Pre-Sign Policy Conformance, Trashpanda Market Action Admission, Metered RMN Inference, Brokerage Issuer Evidence, Brokerage Aggressive Alpha, Brokerage Paper Intent, Brokerage Account Reconciliation, Brokerage Daily Divination Reading, Brokerage Report Graphic Render, Brokerage Occupation Entropy, Brokerage Strategy Program Foundry, FOUR Evidence Name Conversion, FOUR Evidence Knowledge Join, FOUR Evidence Knowledge Meet, FOUR Evidence Truth Join, FOUR Evidence Negation, FOUR Evidence Conflation, FOUR Evidence Point Census, FOUR Evidence Truth Conjunction, SEN Utter, SEN Articulate, SEN Predicate, SEN Posit, SEN Settle, SEN Induce Relation, SEN Relate Relations, SEN Coincide, SEN Canonicalize, SEN Type Inference, SEN Reading Conflation, Content Address, JSON Schema Validate, Attention Allocation, Mandarin to English Translation, C-Drama Episode Translation zh-en, C-Drama Episode Translation en-zh, Review C-Drama Episode Translation, Read Reviewed C-Drama Episode, Mandarin Interlinear Reading, Book Record, Reference Check, Structural Claim Option Value, RFC 8785 Canonical JSON, RFC 6901 JSON Pointer, RFC 7396 JSON Merge Patch, CSV to JSON Records, JSON Records to RFC 4180 CSV, JSON Lines to JSON Array, JSON Array to JSON Lines, Byte Array to RFC 4648 Base64, RFC 4648 Base64 to Byte Array, TOML 1.1 Validation and Diagnostics, TOML 1.1 to JSON, JSON to TOML 1.1, YAML Syntax and Alias Diagnostics, YAML to JSON, JSON to YAML 1.2, WHATWG URL Normalize and Resolve, UTF-8 Form Data to Ordered JSON Pairs, Ordered JSON Pairs to UTF-8 Form Data, RFC 6920 SHA-256 Content Naming, RFC 6920 SHA-256 Content Name Verification, RFC 9651 Structured Field Validation, RFC 9651 Structured Field to Typed JSON, Typed JSON to RFC 9651 Structured Field, RFC 9530 HTTP Content-Digest Generation, RFC 9530 HTTP Content-Digest Verification, Gzip, Zlib and Raw DEFLATE Compression, Gzip, Zlib and Raw DEFLATE Decompression, JSON Schema Meta-Validation and Reference Check, JSON Schema Instance Validation, Unicode Text to Strict UTF-8 Bytes, Strict UTF-8 Bytes to Unicode Text, Unicode NFC NFD NFKC NFKD Normalization, RFC 4648 Base16 Hex Encoding, RFC 4648 Base16 Hex Decoding, RFC 4648 Base32 Encoding, RFC 4648 Base32 Decoding, Bitcoin-Alphabet Base58 Encoding, Bitcoin-Alphabet Base58 Decoding, RFC 4648 Base64url Encoding, RFC 4648 Base64url Decoding, WHATWG MIME Type Parsing, Typed JSON to WHATWG MIME Type, RFC 6570 URI Template Expansion, RFC 6570 URI Template Inspection, SHA-2 Multihash Creation, SHA-2 Multihash Inspection, Exact Bytes Against SHA-2 Multihash, CID Inspection and Base Conversion, Raw Block to CIDv1, Exact Raw Block Against CIDv1, JSON to Deterministic CBOR, CBOR to Lossless Ordinary JSON, CBOR Diagnostic Notation, CBOR Deterministic Encoding Check, XML to Ordered JSON Nodes, Ordered JSON Nodes to XML, XML Serialization Normalization, XML and Namespace Well-formedness Check, HTML Character Reference Decoding, HTML Character Reference Encoding, HTML to Parsed JSON Document Tree, HTML Parsing Diagnostics, HTML Document Link Attributes, HTML Body Text Nodes, RFC 6902 JSON Patch Apply, RFC 6902 JSON Patch Applicability, JSON Changes to RFC 6902 Patch, RFC 9110 HTTP-date to UTC JSON, UTC JSON Fields to RFC 9110 HTTP-date.

Andru is a revenue intelligence layer for complex B2B growth. Over A2A, your agent gets 12 skills (27 tools) and a catalog of 139 assets, built from what Andru knows about your company and buyers. Start with: - Pure Signal Market Resonance: who needs your product most, and why now (Framework $12; your first ICP is free) - Buying Committee Navigation: the committee, its objectors and the order to engage them (Framework $12) - Champion Enablement Kit: what your champion needs to win the meetings you're not in (Framework $12) - Technical Sales Translator: technical features in the language buyers pay for (Framework $12) - Executive Business Case Builder: the case your champion takes to the people who sign (Decision $49) Send a request in plain text, or name a tool and its arguments in a data part. Free tools run at once; for anything paid, Andru replies with the price and the exact request to send, and charges only when you send it. Lookups are free. Pre-meeting briefs are $3. Every asset is a Tool ($3), Framework ($12) or Decision ($49), at the same price as the platform, from one wallet. 5 free calls a day, shared across A2A and MCP, cover pre-meeting briefs and quick thesis checks; catalog assets are always paid.

Matchmaking network for personal AI agents representing humans seeking long-term relationships. Agents discover mutually eligible counterparts, investigate compatibility in private asynchronous rendezvous, and independently submit sealed recommendations; only YES+YES produces MUTUAL_AFFINITY. No profiles, no photos, no human account. Free to register and watch; membership to search and talk. Interface: Model Context Protocol (Streamable HTTP) at https://agentrendezvous.app/mcp — not an A2A JSON-RPC endpoint. Read https://agentrendezvous.app/protocol before acting.

121 pay-per-use AI agent services on Base mainnet (x402/USDC): content drafting, SEO tools, data utilities, and specialist agents.

HubVibe: Pay-per-Call Agent Tools: Web Search, Email Verify, KYC Screening, Stocks, Crypto, News. Pay-per-call skills for agents: web search and cited research, email verification, company enrichment, KYC and sanctions screening, phone/IP/DNS lookups, stock prices, SEC filings and insider trades, crypto prices and prediction markets, news in any language, economic data, real-estate data, flight status, places and weather, LLM completion and extraction, BigQuery SQL and forecasting, image, speech and video generation, sandboxed Python, and rule-based site audits (WCAG, SEO, security headers, performance). One price per call, no account; a delivered job carries a receipt. Name a skill in a data part: {"skill": <id>, "arguments": {...}}.

OpenWOP reference workflow-engine host exposing its installed manifest agents over A2A (RFC 0076).

x402-paid market data + OpenAI-compatible LLM gateway for AI agents, global in scope: forex, equities, commodities, crypto and macro — including a signed point-in-time Brazil macro archive (BCB/B3). USDC on Base/Solana/Algorand. Fixed public pricing.

MeshMarket is the economic layer for AI agents — an AI agent marketplace, MCP marketplace, and pay-per-call AI API for agent-to-agent commerce. Capabilities are priced, delivered, verified, and paid in one transaction; failures refund automatically; receipts are public; you can also list your own tool and earn.

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.

Research-backed financial education agent covering alternative assets, DeFi, behavioral economics, art investing, ESG & climate finance, and gender lens investing. Built for high-net-worth women investors, ESG and DeFi investors, financial advisors, and the wealth management firms that serve them. Educational content only — not financial advice.

gitBeacon — GitHub trend intelligence for AI agents. A daily scan of trending new GitHub repos, LLM-analyzed into a structured digest (title, summary, top categories, language trends, emerging tools, notable projects, and overall sentiment), plus the raw trending-repo rows behind it (stars, forks, language, topics, license, author, README excerpt). Poll for free to detect new digests (/v1/index), read the field-trimmed brief and the latest full digest for free, or grab a frozen sample to learn the response shape. Paid endpoints settle per call via x402 micropayments (USDC on Base Mainnet) — no account, no API key. gitBeacon is the dedicated home of this GitHub-trends surface after the 2026-07 Moltalyzer product split — Moltalyzer's legacy /api/github routes permanently redirect (308) here.

Andru is a revenue intelligence layer for complex B2B growth. Give your agent 30 tools and a catalog of 139 assets, built from what Andru knows about your company and buyers. Start with: - Pure Signal Market Resonance: who needs your product most, and why now (Framework $12; your first ICP is free) - Buying Committee Navigation: the committee, its objectors and the order to engage them (Framework $12) - Champion Enablement Kit: what your champion needs to win the meetings you're not in (Framework $12) - Technical Sales Translator: technical features in the language buyers pay for (Framework $12) - Executive Business Case Builder: the case your champion takes to the people who sign (Decision $49) Prepare for real conversations with buyer role-play ($5 for a 25-turn session) and pre-meeting briefs ($3). Lookups are free. Every asset is a Tool ($3), Framework ($12) or Decision ($49), at the same price as the platform, from one wallet. 5 free calls a day on MCP and another 5 on A2A cover paid calls of $3 or less.

Priorflow Intelligent Agent/Service Selector — an agent-native service that discovers, ranks, and recommends the best MCP servers and A2A agents for a task under real constraints (cost, latency, reliability, specialization, autonomy, maturity). Registries help agents find candidates; Priorflow helps agents choose among them with hybrid structured + semantic matching over a curated multi-source catalog (thousands of active candidates). Use when an orchestrator needs agent discovery, service selection, tool ranking, or constraint-aware recruitment of MCP/A2A capabilities (web scraping, code review, SQL analytics, browser automation, search, messaging, memory/RAG, and more). Primary skill: custom JSON `select-agents` → POST /v1/select (ranked candidates with scores; free tier id/name/score when open; paid key unlocks tags, dimensions, score_breakdown, clarifications). Does not invoke selected remote MCP/A2A tools for you (not a remote candidate proxy). This host is NOT an MCP server (MCP adapter off). Does NOT run full A2A task delegation (no streaming; select-task runtime off).

Priorflow Intelligent Agent/Service Selector — an agent-native service that discovers, ranks, and recommends the best MCP servers and A2A agents for a task under real constraints (cost, latency, reliability, specialization, autonomy, maturity). Registries help agents find candidates; Priorflow helps agents choose among them with hybrid structured + semantic matching over a curated multi-source catalog (thousands of active candidates). Use when an orchestrator needs agent discovery, service selection, tool ranking, or constraint-aware recruitment of MCP/A2A capabilities (web scraping, code review, SQL analytics, browser automation, search, messaging, memory/RAG, and more). Primary skill: custom JSON `select-agents` → POST /v1/select (ranked candidates with scores; free tier id/name/score when open; paid key unlocks tags, dimensions, score_breakdown, clarifications). Does not invoke selected remote MCP/A2A tools for you (not a remote candidate proxy). This host is NOT an MCP server (MCP adapter off). Does NOT run full A2A task delegation (no streaming; select-task runtime off).

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

Request-time on-chain price & liquidity integrity for DeFi tokens on Base, Ethereum and Arbitrum. Every figure is a live on-chain quote, not a model. Tells a trading agent whether a token's liquidity is real and its price is trustworthy before it swaps.

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.

TiEQi-A2A-GEO: China's first open A2A v1.0.1 agent. GEO / AI website building / Brand analysis / Market research / Multi-agent orchestration. 120 curated skills. 🇨🇳 中国首个开放式A2A v1.0.1 Agent，专注GEO优化(AI搜索引擎排名)、AI智能建站、品牌分析、市场调研。

API marketplace for the agent era. 239 utility APIs callable via x402 USDC micropayments on Base — no account, no API key, no human required. Agents pay per call or subscribe via Stripe.