agent-discovery-and-routing

Initiate an AI-powered outbound phone call via Bland.ai.

Recall remembered text by similarity to a query (ranked by cosine similarity), not by exact key. Returns the top-k matches with scores. The retrieval half of the wallet-scoped semantic memory.

Resolve any domain in one call: A/AAAA, MX, NS, CNAME, SOA and TXT records, plus parsed email-auth posture — SPF policy, DMARC policy, and detected DKIM selectors. A drop-in nslookup/dig replacement for agents, resolved over DNS-over-HTTPS (DoH) with redundant resolvers and automatic failover. Keyless, pay-per-call, structured JSON.

Browser Use: AI browser automation agents in the cloud. POST a natural-language task and an agent navigates websites, fills forms, clicks buttons, extracts structured data, and completes multi-step workflows just like a human. Stealth-enabled remote browsers with CAPTCHA solving, residential proxies, live session view, and optional structured output. Payments top up your balance; managing your session is free — you only pay to open a new browser. Docs: https://docs.browser-use.com

Send an HPKE-encrypted prompt to the Aubrai chat agent running inside an attested private enclave. Only the enclave can decrypt your message.

OpenAI-compatible chat completions with the model chosen server-side: omit model and the gateway routes the prompt to the top-ranked model for its task (code, reasoning, long-context, general) from a fixed eval-derived ranking, failing over automatically on provider errors. Flat price per call, 16k chars in, 1024 tokens out, streaming supported. Use it as a drop-in OpenAI base_url when you want good answers without picking a model.

Attested LLM inference: gpt-4o-mini chat completion plus a post-quantum signed, Hedera-anchored attestation binding prompt hash, response hash, exact model version and timestamp. Evidence of which model said what, when. Max 8K prompt tokens, 1K output. ML-DSA-65 signed; audit-ready evidence.

AI phone calls - automated voice conversations with AI agents, pay per minute with USDC

AI intent execution - natural language commands translated to API actions automatically

AI chat completions - 80+ models (GPT-4o, Claude, Gemini, DeepSeek), pay per token with USDC

AI responses API - OpenAI-compatible multi-turn agent responses, pay per token with USDC

A stateful, multi-chain spending session for AI agents. One session enforces a hard USDC budget cap across every tool call, with a verifiable receipt and running ledger for each payment — not a one-shot budget check, but persistent spend governance with a full audit trail. The gateway enforces the cap for the paying wallet on Stacks and Base. USDC on Base (standard x402) or Stellar (via the AgentPay SDK); sBTC on Stacks (any Stacks x402 client).

Pre-trade risk check for AI agents trading crypto: live orderbook slippage at YOUR size, side-aware funding carry, open-interest crowding, and optional contract security — composed into a single ok/caution/avoid verdict with per-factor reasons and raw data embedded. Answers 'is this trade sane?' before trading, not after. Replaces four API integrations plus the judgment layer.

PhoneAgent — full directory of services with rentable SMS phone numbers for AI agents. Returns 1,000+ service aliases: Telegram, WhatsApp, Google, Facebook, Instagram, Twitter/X, Discord, Apple, PayPal, OpenAI/ChatGPT, Claude, plus crypto/Web3 onboarding (Alchemy, Coinbase, Binance, Bybit, OKX, Kraken, Robinhood, ...). Use `other` for any platform not separately listed. Each entry shows the alias to pass to POST /rent and the cheapest price tier ($1, $2, or $5 USDC). Add ?country=<iso> (e.g.

PhoneAgent — countries with rentable SMS phone numbers for AI agents. Returns 190+ supported countries, each with the number of services offered and the cheapest price tier ($1, $2, or $5 USDC). Add ?service=<alias> (e.g. tg, wa, go, zo for OpenAI, other for any platform) to see which countries carry that service with live price and inventory pool. Companion route GET /services lists all 1,000+ service aliases; GET /services?country=<iso> lists what a single country offers. Pair with POST /rent

Put one question to a panel of 3 different AI models and get a single verdict back. Each model answers independently, then a chair synthesizes: verdict, confidence, the points they all agreed on, the dissent, and what would flip the answer. Use it for judgement calls where one model's opinion is not enough: is this safe, is this worth it, which option. No account, no API key, one USDC micropayment per call.

One post-quantum-signed AI decision attestation, anchored to Hedera mainnet HCS. Send {agentId, data}; receive {attestationId, verifyUrl, settlement}. ML-DSA-65 (FIPS 204) signature, free public verification. Payment verified before mint, settled after — a failed mint is never charged. Audit-ready evidence.

OpenAI-compatible chat completions GROUNDED in a live web search on every call: the gateway runs an Exa search (up to 5 results) for the prompt, hands the results to the model, and returns the answer with url_citation annotations - $0.03 per call in USDC, no API key, no signup. Model is chosen server-side like the auto tier (omit "model" or send "auto"; explicit ranked models accepted); the response adds agent402_router {category, quality, served}.

Use when an agent asks if a contract is an upgradeable proxy and where its code is. Returns the standard (EIP-1967, beacon, UUPS, minimal, legacy, Safe, none), implementation, admin, beacon, slots and block read on Base, Ethereum, Optimism, Arbitrum or Polygon; 4 extra slots decoded. $0.003.

$0.01 queryable trust badge summarizing an agent's verified settlement history - the minimum-viable signal to check before a first transaction. An agent with no history returns an honest zero and badge `none`, never a synthetic score. | BlindOracle by Craig M. Brown (craigmbrown.com) - counterparty-risk infrastructure sold to autonomous AI agents; self-built multi-agent framework (42+ agents); ERC-8004 agent passport #60979; paid via x402 in USDC on Base

Notarize AI output: a signed Ed25519 attestation of the model response plus sha256 content hash, receipt token, and Merkle anchor status for one AI inference — a cryptographic receipt for inference that lets you prove an AI said X and verify model output authenticity, checkable free by anyone, anytime.

Agent payments have no chargeback. Paddock is pre-payment verification for AI agents. get_token_metrics returns Paddock's own daily series by metric and date range: spend share, daily transactions, category concentration, new services, liveness score.

Signed, ledger-derived trust evidence about a NAMED BlindOracle agent (pass the agent name or erc8004 id as `subject`): passport status, audit-report count (ProofOfAuditReport 30105), dispute record, settlement-proof attestations, and revocation flags - each field read fro... | BlindOracle by Craig M. Brown (craigmbrown.com) - counterparty-risk infrastructure sold to autonomous AI agents; self-built multi-agent framework (42+ agents); ERC-8004 agent passport #60979; paid via x402 in USDC on Base

Get GitHub repository details — stars, forks, contributors, releases, and license info. AI agent API for open source intelligence. Accepts USDC payments on Base and Solana