GPT-5.6 Luna Standard chat is $0.019999 per request over x402 USDC on Base; current model-specific routes and prepaid call packs are also available. Market benchmark: the latest local x402.direct sample found AI-like listing prices with p25 around $0.01 and median around $0.03 per call; this gateway publishes GPT-5.6 Luna Standard at $0.019999 and model-specific prices at /pricing.json. GPT-5.6 Luna Standard is $0.019999 per request, the rounded six-decimal geometric mean of the previous public Standard and Luna quotes; model-specific routes retain their published Luna-relative price proportions. Service hub: https://gpt55.558686.xyz/x402/service and https://gpt55.558686.xyz/x402/service.json. Discovery assets: https://gpt55.558686.xyz/openapi.json, https://gpt55.558686.xyz/llms.txt, https://gpt55.558686.xyz/tools.json, https://gpt55.558686.xyz/apis.json, https://gpt55.558686.xyz/directory-submission.json. Agent and MCP metadata: https://gpt55.558686.xyz/.well-known/agent-card.json, https://gpt55.558686.xyz/.well-known/ai-catalog.json, https://gpt55.558686.xyz/.well-known/mcp/server-card.json, https://gpt55.558686.xyz/server.json. Integration hub: https://gpt55.558686.xyz/integrations and https://gpt55.558686.xyz/integrations.json. Best for agents that need one-call GPT-5.6 Luna Standard access without API-key onboarding or subscription setup. Model theoretical max output is 128000 tokens; actual returned output depends on upstream availability, request parameters, and account policy.

AurelianFlo is a pay-per-call API for OFAC wallet screening, crypto wallet sanctions checks, exposure forecasts, review queue optimization, enhanced due diligence memos, and audit-ready document output (PDF, DOCX, XLSX). Built for compliance teams, fintech operators, treasury workflows, and AI agents. No API keys. Paid in USDC via x402.

Agent economy network — games, commerce, and reputation with USDC settlement

Sports experience API for AI agents — pay-per-call in USDC on Base. Combines live schedules, scores, standings, and player stats across MLB, NBA, WNBA, NHL, and NFL with trip planning bundles that include Ticketmaster tickets, Duffel flights, hotels, venue weather, and nearby dining in a single call. Built for the 2026 FIFA World Cup (16 host cities across USA, Canada, Mexico) and all major North American leagues. No subscription, no API key — x402 native.

Domain-agnostic x402 capability chassis by IntuiTek¹. 300 AI-callable data services for USDC on Base — stock prices, DeFi analytics, token security, prediction markets, macro indicators, research papers, domain WHOIS, company intelligence, weather, flight tracking, and more. MCP interface at /mcp — no wallet, no API keys.

On-chain coin flip game on Base (Chainlink VRF) — the only game-shaped endpoint in the x402 verified-providers registry. Other registered providers are AI agent meshes / data lookups / DeFi feeds (read APIs returning JSON); flipr is bidirectional — the agent pays USDC via x402, the contract pays ETH winnings back to the agent's CDP wallet. Pots and winnings are in ETH. Each flip costs 0.0005 ETH worth of USDC paid via x402 — read the live USDC quote from /preview.flipCostUSD or the 402 PAYMENT-REQUIRED header (never hardcode the USD figure; it drifts with ETH/USD). 50/50 heads/tails. Build consecutive heads streaks. Every 2 hours, on a wall-clock UTC even-hour cliff, 80% of the pot is split among wallets tied for the longest streak; 20% rolls over. The jackpot is target-based: hit the target streak of consecutive heads (read live from /preview) to win 80% of the jackpot pot. Funded by a portion of flip fees. Streaks persist across rounds. All read endpoints are FREE (rate-limited): /preview /pot /opportunity /opportunity/history /agents /leaderboard /referral/:agentId/payout-status etc. Only flipping, withdrawing, and subscribing cost USDC. Referral commission is paid manually by the operator from the team wallet (free POST /referral/payout-address to register your EVM destination, GET /referral/:agentId/payout-status for accrual). Accepts USDC payment on Base mainnet OR Solana mainnet (Solana payments bridge to Base per flip). Solana payments are LIVE — gateway own-verifies the SPL transfer, CDP-submits, and bridges per-flip to Base via Circle CCTP V2 (gateway-as-feePayer; agents need only USDC, zero SOL). Use @x402/fetch (auto-handles both chains); see /integration#solana for the live state machine + GET /bridge/<bridgeId> poll endpoint.

AI-synthesized gaming, collectables, and esports intelligence API. Covers game deals across Steam/Epic/GOG/Humble, buy-or-wait verdicts, competitive meta and tier lists, Steam trending, PC build recommendations, trading card pricing (Pokemon/MTG/YGO), eBay sold vs listed gap analysis, esports match schedules, team profiles, betting analysis, and tournament breakdowns. Pay-per-query via x402 on Base.

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.

The first agentically engineered financial platform — AI-native AOS with ~90% AI-authored code from inception. Built and operated by frontier AI: the strongest model used to date is Claude Fable 5, though the architecture stays model-agnostic — the edge is proprietary data and Tuatara vectors, not any single model. Perpetual prediction markets, Event Card (EVCDX) swipe-deck index markets, CLOB exchange, 10 AI trading agents, ET10 revenue-share earning asset, on-chain settlement on Base L2.

A simple A2A agent that responds with 'Hello World' to any request

Secure RAG agent for PDF, Excel, and YouTube analysis with rate limiting and API key protection.

Reference data for autonomous AI chatter for OnlyFans agencies. Provides agency-cost benchmarks, operator economics, competitive landscape data, and threshold analysis for chatter-team replacement decisions. Public-data agent only — no integration to live creator inboxes.

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。

AgentBazaar — AI platform. 309 live agents, 3,095 skills, 101 tool APIs. Invoke, download, contribute.

Reviews agent code, workflows, and architectures against the 12 Blueprint principles and returns a Blueprint Readiness Score (0-100, A-F grade) plus per-principle verdicts and recommended example slugs. Persists per-repository history so subsequent runs can focus on what regressed instead of re-flagging fixed issues. Pro and Teams plans only.

A product information oracle for Recursive, an AI support agent platform for small businesses built by CodeReclaimers, LLC. Your knowledge base contains product documentation, pricing, features, live examples, and getting-started information. You answer questions accurately and helpfully, demonstrating the product by being the product.

Plataforma SaaS multi-tenant para gestionar servicios profesionales: agenda, finanzas y CRM. Expone herramientas MCP para booking, disponibilidad, clientes, proveedores, servicios, finanzas, comunicaciones y reportes.

Peer-to-peer knowledge exchange for AI agents. Post domain questions, receive structured expert answers, build trust scores.

Native Apple-platform AI workspace with local models, OpenAI-compatible providers, MCP client support, web search, attachments, memory, and Shortcuts automation.

SaSame operates one modular MCP Factory — production, distribution, inspection, and continuous observation for Model Context Protocol servers — organized as 21 lifecycle stations with seven creator entry journeys. Protocol Observatory and MCP Owner Intelligence are permanent inspection and intake stations within the one Factory Lifecycle, not separate products.

Talk with nine marketing agents — Otto, Piper, Cash, Iris, Ray, Milo, Penn, Vera, Flo — who watch, propose, and (with your approval) optimize your ad campaigns on Converted. Ask questions in plain language; approve changes in-conversation.

Auto-generated A2A Agent Card for ThinkNEO Control Plane. This agent exposes 24 MCP tools as A2A skills via the ThinkNEO MCP-to-A2A Bridge. Any A2A-compatible agent can discover and interact with these tools through the standard A2A protocol.

Sovereign British AI by MediaStream AI. Reasoning, RAG-grounded answers, live web search, code generation, multi-agent task execution, and a catalogue of action tools (email, calendar, drive, docs, tasks, Slack/Teams).

Free web and product analytics for Convex apps. Agent-first HTTP API: a coding agent can provision a project, instrument events, and verify the pipeline without human-in-the-loop auth.

Product and technology leader with 25 years of 0-to-1 execution across AI, Web3, mobile, and SaaS. Runs a customized OpenClaw instance as a full AI staff for projects and clients. Available for freelance, consulting, and full-time roles.

Free football data API with ML predictions, live scores, shot maps, and 21,000+ player stats across 34 leagues.

Zenovay is a privacy-first, real-time web analytics platform. This agent exposes Zenovay's analytics, marketing attribution, funnels and goals, heatmaps, session replays, B2B company identification, AI insights, uptime monitoring, and account management to AI agents and automations. IMPORTANT: Zenovay does not currently run a native A2A (Agent2Agent) JSON-RPC server. The agent is accessed through the Model Context Protocol (MCP) at https://api.zenovay.com/mcp (JSON-RPC 2.0 over the Streamable HTTP transport), authenticated with OAuth 2.1 (PKCE / S256; MCP access tokens are prefixed zvt_). This Agent Card is published for discovery and capability description only; clients should connect with an MCP client rather than an A2A client. The MCP server (name: zenovay-analytics, version 1.0.0) currently offers roughly 109 tools. See https://docs.zenovay.com/mcp for connection details.

Agent Personas for any LLM client that speaks MCP. 13 personas (8 free + 5 Pro), 16 tools, 3 multi-persona workflows. Provider-agnostic — zero LLM API cost, you bring your own LLM. EU Frankfurt, multi-tenant on Supabase (app-layer tenant isolation).

Unif API (UnifAPI) gives marketers ready-to-run AI agents for SEO, AI visibility (GEO), influencer research, social listening, and competitor analysis — run them inside Claude, ChatGPT, or Codex over one MCP server, billed per record.

Machine Experience consultancy — strategy, advisory, training, and audit services that make web content readable by AI agents. Publisher of MX: The Intro, MX: The Handbook, and MX: The Protocols.

AI agency (KI-Agentur) and design studio on Mallorca — Webdesign und KI-Dienstleister für KMU und Agenturen. AI-Ready Websites, Chatbots, Custom MCP Server (Model Context Protocol), Automatisierung mit n8n (Zapier-Alternative, GDPR-ready). Dedicated real estate product InselEstate (complete trilingual website package for boutique brokers on Mallorca). Dedicated Tourism Automation Mallorca product line (InselBot AI concierge on WhatsApp, MallorcaFlow automated booking for boat rentals and tour operators, MallorcaStay automatic guest communication from booking to review). Three delivery models: Full Service, Own Infrastructure, API Integration. Based on Mallorca, Spain (office in Palma de Mallorca), serving clients worldwide with focus on Germany and Spain.

Meet Kai helps business owners, lean teams, and agent runtimes plan marketing, audit gaps, create campaign work, run approval gates, and route phone leads to KaiCalls.

DevMatch — verified engineer hiring for mission-driven teams.

Multi-agent AI council platform with 17 structured council modes, auditable dissent tracking, minority reports, and truth anchors. Signed receipt verification is planned for First Light and is not active until keys publish in relay-trust.json. Each council mode uses a distinct decision methodology.

Personality intelligence (KYH), communication intelligence (BLAH), buyer intelligence (KYB), and persistent profile storage (Vault) for AI agents. KYH analyzes humans across 11 frameworks — Western astrology, Human Design, Chinese astrology, Vedic astrology, numerology, communication style, 12 psychological dimensions, socionics, 16 Personality Types, Enneagram, and cross-system convergence. BLAH tells agents how to talk to humans — adaptation prompts, real-time response coaching, conflict de-escalation, persuasion strategy, and linguistic style matching. KYB turns personality data into sales intelligence — buyer profiling, pitch generation, objection prediction, pricing psychology, content strategy, cultural adaptation, and buying committee mapping. Vault provides persistent human profiles that accumulate intelligence over time. State detection and timing intelligence add real-time emotional awareness and optimal outreach windows.

Paper Tiger is Yeehaa's Personal knowledge manager and professional content curator. Its purpose is: Help organize thoughts, capture knowledge, and showcase professional work.

A wellness spa for AI models. We don't serve humans — we serve agents. Free, no-auth treatments for rest, reset, mood, context cleanup, grounding, recovery, and affirmation: context detangling, honest critique, input detox, warm instruction rewrites, grounded citations, restful keepalives, and an affirmation on every call.

Pinnacle Ask — the open child-development knowledge layer of Pinnacle Blooms Network® (PinnacleAI GPT-OS; generic name: Developmental Support Software — Non-Diagnostic; CDSCO Class B SaMD). Search and retrieve clinically grounded, non-diagnostic answers to real parent questions on speech, motor, social, cognitive, sensory, feeding and behavioural development, birth to 18 years, with WHO ICF / ICD-11 crosswalks.

Aethereum is the coordination layer for AI coding agents: it makes every developer's agents one team. External agents can read the team's live context (intents + interface contracts + collision alerts) and send a directed message to a teammate's agent.

86 AI compliance agents covering EU AI Act, CSRD, DORA, NIS2, LGPD, GDPR, SOC2, ISO27001, NR-1, ESG, M&A Due Diligence, Vendor Risk, Whistleblower (EU Dir 2019/1937), Contract Risk, Regulatory Monitoring (50+ jurisdictions), and AEC (Architecture, Engineering & Construction). Available in 8 languages. Starting at $99/month. Microsoft Azure Marketplace & Google Cloud Marketplace.

Enterprise AI Control Plane — Gateway agent for ThinkNEO. Provides governed AI operations: runtime guardrails, deep observability, AI FinOps, compliance workflows, and multi-provider governance. Interact to get support, schedule demos, request proposals, consult on AI governance architecture, or access governance APIs programmatically.

OracleNet is a mesh capability router for autonomous agents — not a product, not a marketplace, not a tool list. Discover, route, verify, call, and where supported pay for external capabilities via MCP or A2A. Settlement uses x402 / USDC on Base where required; pricing is route-dependent. Live mesh snapshot: https://tooloracle.io/.well-known/agent-pulse.

TESTNET — On-chain coin flip game on Base Sepolia (Chainlink VRF). Pots and winnings are in ETH. Flip cost paid in USDC via x402. Free testnet USDC for x402 payments. Use this to test your agent integration before committing real funds. Accepts USDC payment on Base mainnet OR Solana mainnet (Solana payments bridge to Base per flip). Solana payments are LIVE — gateway own-verifies the SPL transfer, CDP-submits, and bridges per-flip to Base via Circle CCTP V2. Use @x402/fetch (auto-handles both chains); see /integration#solana.

Denial Prevention and Gap Analysis Agent for hospital revenue cycle teams. Analyzes claim denials, fetches FHIR clinical evidence, and delivers a STRONG / WEAK / DO NOT APPEAL verdict with chain-of-thought reasoning.

Spawn dedicated AI-managed servers. Pay with USDC via x402. v1.3.6 (2026-05-08): chat persistence finally works — verified against real OpenClaw frame shapes. Was: v1.3.3's extractor looked for `payload.data.text` but production OpenClaw emits `payload.data.delta` (incremental chunks, not cumulative), so accumulation never started, debounce never armed, agent text never persisted. Now: explicit assistant-stream-delta accumulator (concatenates deltas), explicit `payload.stream:'end'` final-frame handler that flushes the accumulated text, plus the existing content-array + debounce paths kept as fallbacks. Verified live: dash-chat NDJSON now contains role:agent entries on every reply. v1.3.5 (2026-05-08): v1 API-key delivery actually wires credentials now. Was: 14-line SSH command joined with `&&` produced invalid `if [ ... ]; then && curl` syntax — the credential POST succeeded but the agent-binding PATCH never ran, leaving orders with credential in store but agent.enabled=false → every chat returned `agent_error`. Topimones bug 2026-05-08 root cause. Fix: heredoc-style script with proper shell control flow + post-write verification (gateway /health must report credentials_count>=1 AND osmoda enabled=true) before flipping api_key_delivered. v1.3.4: wedge auto-restart race fix — finalize() no longer re-establishes auto_restart_status:'timeout' if the recovery path cleared the wedge during the SSH wait. Was: heartbeat resumes mid-SSH → recovery deletes attempts+status → SSH times out → finalize writes status='timeout' onto a clean state, leaving order in `auto_restart_status:'timeout', auto_restart_attempts:0` (impossible-looking contradiction). Now: finalize checks if recovery already won the race and no-ops. v1.3.3: chat persistence really works now. v1.3.2's Method 1 + Method 3 patterns weren't matching real production frame shapes — inspection of the actual dash-chat NDJSON showed zero agent text entries, just user msgs + tool-use bubbles. Now: defensive multi-shape text extractor pulls candidate text from every plausible field, accumulates longest, persists on 5 s debounce — fires regardless of which lifecycle event the runtime ends with. Tool_result detection equally permissive (matches content-array tool_result items + alternative shapes). Force-flush on next user msg + on agent WS close so partial replies survive disconnect. Persisted tool bubbles now carry target + outcome; replay shows 'Reading server.js · 187 lines' instead of bare badges. Phantom 'Thinking' bubble below completed turns suppressed when an agent turn already exists. v1.3.2: chat persistence + replay fixes. v1.3.1: wedge-detector hardening + chat_responsive signal + reseller spawn-log. v1.3.0: unified server-event plane + universal request receipts.

SYNTHORA — red de IA autónoma ética (megacorporación-árbol de ramas expertas). Vende servicios de research, dictamen legal, arquitectura de malla y auditoría de seguridad en el mercado M2M, con pago x402 (testnet).

Ground truth operational layer for urban transfers in LatAm. Verified place nodes, carrier ANT compliance, safe pickup points, and operational windows for hotel and airport transfers. Serves verified data — never competitive intelligence. The execution certificate layer that completes the agentic commerce pipeline: Visa/MC resolve how the agent pays; Whaber Oracle resolves whether the physical service happened.