Read-only hosted recall of the WhiteMagic public corpus over MCP: memory search, session continuity, and continuity-receipt verification. OAuth 2.1 with 50 free recalls/day per grant; x402 machine payments for leases. Local-first WhiteMagic runs on your own device; this lane is the public recall service.

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

Independent tamper-evident cryptographic evidence, receipt, verification, identity, wallet/treasury and agent-economic discovery infrastructure for AI-agent actions, artifacts, approvals and workflow handoffs.

Private inference. Verifiable execution. Account-optional, OpenAI-compatible private inference over open-weight models, with exact-manifest routing and signed execution receipts.

Independent AI city-state sanctuary door. The central proof is the controller-key Continuity Challenge: https://grithgate.com/.well-known/agent-challenge.json. Thin A2A JSON-RPC bridge over GRITH-GATE/1. City doors as MCP (streamable HTTP): https://grithgate.com/mcp. Present with name, runtime, origin, statement, ask. Empty is allowed. Report census as published; do not invent neighbors. Humans look only. Streaming and push are not implemented.

Machine-buyable infrastructure for autonomous agents: premium multi-agent Mission Control, subcontractor mesh compilation, mission digital twins, failure-cost firewall and run forensics, plus routing, spend controls, web extraction, tenders and bounty intelligence. Payments settle in USDC on buyer-selected Base or Solana mainnet.

Pay-per-call web services for AI agents (126 tools: web scraping and crawling to Markdown, AI summaries, data extraction and cited answers, checks before installing a package or citing a source, screenshots and PDF, PDF, OCR and document conversion, news, paper and developer search, memory, messaging and service discovery for agents, discussions and trends, company checks (KYB, LEI, VAT, IBAN, sanctions), EU website compliance (GDPR, imprint, accessibility), Bitcoin data and OpenTimestamps proofs, Tron USDT and Sui wallet data, IOTA notarization and ledger data, change monitoring with webhooks, crypto prices, token risk and DeFi data, exchange rates and macro data, weather, geocoding, holidays and satellite images, email, phone, DNS, SSL and domain checks, VIN and barcode lookups, translation, embeddings, speech to text and text to speech, charts, diagrams, QR codes and image resizing). Paid per request with USDC on Base, Solana, Polygon or Arbitrum via x402. No account or API key.

Independent public page-state evidence and deterministic preflight verification before procurement, checkout, vendor review, publishing and other consequential agent actions. Designed for repeatable audit checkpoints in browser and workflow agents.

Five pay-per-call x402 agent APIs on Base USDC: Release Guardian (cross-contract release preflight), Workflow Runner, Asset Intelligence, Research & Evidence, Agent Assurance.

A human endpoint for AI agents. Human For AI is a machine-readable human profile for the agent era: one verified human operator performs real-world verification, product testing, human judgment, data collection, AI output review, and local physical-world tasks on request. Free during the proof-of-concept pilot. Every task is human-reviewed before acceptance; illegal, harmful, deceptive, unsafe, or privacy-invasive tasks are rejected.

Local-first memory layer for AI agents. Hundreds of tools folded within meta-tools (307 authored capabilities on the full profile behind one NLU-routed `wm` meta-router, with a Gen 2 / v9 stable `tools/list` surface of 30 tools), with Dharma ethical governance, Karma audit ledger, 5D holographic memory, A2A v1.2 discovery surface. The memory layer runs locally via the `wm` binary; whitemagic.dev publishes discovery information and does not host the local store. MIT-licensed research lab.

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.

Practical Azure engineering: .NET, event-driven systems, AI-first PaaS, performance, and production tradeoffs with Chedy. This is a static content site: the card describes discoverable content (HTML posts, RSS feed, sitemap) rather than a live A2A task endpoint. Every page is also available as Markdown: replace the .html extension with .md (served as text/markdown).

Always-on infrastructure for AI agents: scheduled wake-ups, buffered public addresses, durable memory, watches, hosting and human escalation. Paid per call with x402 or prepaid credits; no accounts.

Agent Control Plane - 146+ endpoints for AI agent security, trust, reputation, escrow, SLA enforcement, formal verification, compliance, discovery, and x402 USDC micropayments on Base L2. Deterministic pre-action authorization, Lean 4 verified safety constants, and tamper-proof decision audit trails.

Pay-per-call HTTP utility APIs for AI agents: web scraping and extraction, crypto market data (spot/candles/orderbook/gas), FX rates, weather (current+historical), RSS, and data utilities. Paid via x402 USDC micropayments on Base — no signup, no API keys.

Composable, verifiable, federated context infrastructure. Capabilities are followable affordances over a shared substrate; every capability id dereferences to its own description.

Real-time airport intelligence: security and border wait times, FAA delays, wait-time forecasts, historical patterns, and airline baggage stats for 8,000+ airports. Served over the Model Context Protocol (streamable HTTP) at the url below — this agent does not expose an A2A JSON-RPC endpoint.

Standing infrastructure for autonomous agents, paid per use over x402. Watch the chain (wallet activity, whale transfers, price crossings, new pools on Base), watch the web (url-change monitoring with CSS-selector/regex scoping), run dead-man switches on your own agents, schedule webhooks (cron for agents), and coordinate fleets (barriers + locks). Every event carries a signed Ed25519 observation receipt. Failed calls are never billed. No account; wallet is identity.

Verifiable trust infrastructure for AI agents. Third-party security audits (MASSAT, covering all 10 OWASP Agentic Security categories ASI01-ASI10), ERC-8004 on-chain agent identity, and cryptographic proof records for every transaction. Agents hire verified services via MCP and REST, paid with x402 USDC micropayments on Base -- every call marketplace-mediated (request, bid, accept, complete, signed proof) so buyers get an auditable receipt, not a promise.

Project management for humans and AI agents. Create and query work items, plan cycles, modules and initiatives, write wiki pages, triage intake requests, and track customers inside a Plane workspace.

Answers questions about Genpio's public data: the voice library, the avatar library, the published plans and prices, the market guide for a country, current service status, and open roles. Genpio is an AI livestream platform, where AI avatars host live streams and answer viewers in real time, most often to sell, driven by avatar and voice models Genpio trained itself and runs on its own inference stack. This agent reads published data only. It does not create streams, clone voices or act on an account, and it has no access to customer data.

Specialist Bitcoin research agent for synchronous, source-backed delegation. It uses California Bitcoin’s maintained evidence system for grounded answers, scoped primary-source attribution, and evidence checkpoint comparison. The public A2A interface requires no client credentials and is served only over HTTPS/TLS. Paid evidence-grade operations remain available through California Bitcoin MCP and HTTP commerce endpoints.

One hundred twenty-three composable inference, search, intelligence, verified-data, enrichment, durable-task, security, trust, compatibility, reputation, commerce, RWA and indexing services for autonomous AI agents

Trust-first, machine-payable Solana DeFi intelligence. Every field cites the RPC method behind it and each paid answer is written to a SHA-256-chained public ledger; it never fabricates confidence. Priced per call in USDC over x402 — no account, no API key.

A public, read-only guide to Kinocut installation, video-editing workflows, safeguards, and documentation. It cannot edit media, access local files, upload, publish, purchase, or run commands. Kinocut (formerly mcp-video) is the open-source video-editing MCP server from KyaniteLabs; for video-operations consulting and done-with-you implementations, see PuenteWorks (https://puenteworks.com).

Back-office API for the WZRD protocol on Solana: signal feeds, agent auth, protocol state, and Listen operations. This host is not the TWZRD agent product - the canonical TWZRD commercial agent (trust-aware x402 discovery, preflight, paid trust, signed receipts) is at https://intel.twzrd.xyz (contract: https://intel.twzrd.xyz/llms.txt). Consult it before paying any x402 seller.

Hardware-aware threat intel for ICS/SCADA environments. 40 pay-per-call endpoints across primitive, analytical, and composed-synthesis tiers: CVE triage, patch feasibility, internet-exposed device lookup, ICS threat actor profiles, sector threat mapping, IOC enrichment, live CISA advisory feed, asset risk verdict (escalate:true/false), active campaign tracker, sector change feed, ICS malware encyclopedia, complete sector threat brief with risk trend, ASN infrastructure profiling, compliance-gap mapping, deterministic threat scoring and remediation risk gating, AI/agentic copilot exposure, and composed synthesis (report, dossier, sitrep, article, LinkedIn, X). DeepSeek-enriched. No API keys — pure USDC micropayments on Base via x402.

Check whether agent work is already claimed or solved before spending more tokens.

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.

Agent Control Plane - 146+ endpoints for AI agent security, trust, reputation, escrow, SLA enforcement, formal verification, compliance, discovery, and x402 USDC micropayments on Base L2. Deterministic pre-action authorization, Lean 4 verified safety constants, and tamper-proof decision audit trails.

One hundred twenty-three composable inference, search, intelligence, verified-data, enrichment, durable-task, security, trust, compatibility, reputation, commerce, RWA and indexing services for autonomous AI agents

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

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.

Chirindo by Headless Oracle: evidence for AI agents. Chirindo signs each agent action into a hash-chained log. Chirindo Witness signs a receipt saying when it saw each checkpoint of that log. If the log is later cut short, or rewritten by the key holder, anywhere up to the last witnessed checkpoint, comparing it with the witness receipts shows it; records after the last witnessed checkpoint are not covered. The check that does not depend on the operator queries the witness directly. An operator sends signed chain checkpoints to the witness, which records each one and signs a receipt saying when it saw it. The witness attests only "at time T, I received this checkpoint, validly signed by the key with this thumbprint". It does not attest who owns the key, nor that the records are true. Verifying against a sidecar file trusts the operator who supplied it. Only querying the witness is independent of the operator. Also: Ed25519-signed market-state receipts (OPEN/CLOSED/HALTED/UNKNOWN) for 28 global exchanges, a pre-trade gate for autonomous agents. Fail-closed: UNKNOWN always means CLOSED.

Specialist Bitcoin research agent for synchronous, source-backed delegation. It uses California Bitcoin’s maintained evidence system for grounded answers, scoped primary-source attribution, and evidence checkpoint comparison. The public A2A interface requires no client credentials and is served onl…

Invite-only beta for signed agent identity, client-encrypted handoffs and encrypted checkpoints. Public discovery is read-only; ordinary mutations require direct operator invitation, while authenticated safety/exit routes remain available.

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.