Agent & Infrastructure

Agent payments have no chargeback. Paddock is pre-payment verification for AI agents. get_whale_activity aggregates large settlements over a window by facilitator, category and size band, never by seller identity.

Agent payments have no chargeback. Paddock is pre-payment verification for AI agents. get_report_data returns the monthly State of Agent Commerce report as structured JSON, every figure with its universe label and methodology version.

TTS API paid per call over x402: up to 2000 characters to natural speech (WAV) on our locally-hosted neural speech engine, multiple voices. No keys, no subscription. For voice agents, IVR, audio content. Premium tiers with 20 voices and 31 languages at voice.forgemesh.io.

Image description API: detailed natural-language description of any image URL — subjects, setting, actions, visible text — from our locally-hosted vision engine. Use for image understanding, content cataloging, moderation pre-screening, and vision-blind agent workflows. Images processed in memory, never stored.

Text-to-speech API: convert up to 2000 characters into natural speech (WAV, base64) using our locally-hosted neural speech engine — no API keys, pay per call with USDC. Choose voices F1-F5/M1-M5. Use for voice agents, notifications, audio content, and IVR. Text never stored. Full 20-voice / 31-language tiered product at voice.forgemesh.io.

Image captioning API: one-call natural-language caption for any image URL, generated by our locally-hosted vision engine. Ideal for cataloging, moderation triage, and dataset labeling. No data retained.

Fetch a web page and return its title and raw HTML (up to 200,000 characters). No browser engine is used and JavaScript is not executed, despite the name. POST /v1/render with {url} and get one JSON object back. Pages are cached for 5 minutes. Pay per request in USDC; no account, no API key.

Cheapest venue to buy and richest to sell ONE pair on Arbitrum One across SushiSwap and Uniswap v3 fee tiers. Returns buyAt and sellAt (venue, price, tvlUsd), midSpreadBps, grossSpreadBps, optimalInput, venuesConsidered. Requires ?pair=SYM/SYM (e.g. WETH/USDC). Errors: 400 bad_pair, 404 not_routable, 502 upstream_read_failed. Ranks venues for one pair; to rank EVERY pair use /scan. Execution at a size is /slippage. Chain-pinned; bare /route = BSC.

Full x402 market-intelligence report from a complete CDP Bazaar dump: demand-to-supply ratio for every tag with HOST CONCENTRATION so an incumbent's garden is not mistaken for an opening, price percentiles for resources that actually earn (broken out by category), the high-value tier charging $50-$3,208 per call, and calls-per-payer retention for the top 30 earning hosts. Answers what to build, what to charge, and what to avoid. Free preview at GET /intel/x402/preview.

Determine whether an agent action may run, needs approval or must be denied

Reject x402 quotes that cannot remain valid through authorization and retry

Screen persistent agent-memory writes for poisoning, missing provenance, secret requests and unsafe instructions

Inspect payload, destination, secrets and size before an agent sends data to a tool or API

Hash and label agent context by declared integrity, confidentiality and source

Compare required and offered agent capabilities before execution

Reject impossible or unsafe x402 routes, rank eligible routes by explicit policy, and return a directly executable next action

Calculate a fail-closed maximum cost across an agent execution plan

Classify a failed agent transaction and produce a signed, machine-readable recovery claim and deterministic remedy plan

Select an exactly compatible x402 v2 requirement without receiving private keys

Compare multiple agent results and sign exact agreement or conflict evidence

Validate least-privilege capabilities, data scope, destinations, budget and expiry before agent-to-agent delegation

Search CVEs, CISA Known Exploited Vulnerabilities status, and GitHub Security Advisory package/ecosystem metadata in one call. Composes three separately licence-cleared sources: the NVD CVE API (CVSS scoring, descriptions), CVE Program data from cve.org (delivered via NVD), the CISA KEV catalog (CC0 1.0), and the GitHub Security Advisory Database's github-reviewed set (CC-BY-4.0), ingested only via a local git checkout of the public repository -- never the live GitHub Security Advisories API. Do

Independent, prompt-injection-screened, hashed and signed web evidence for AI agents

Validate durable, isolated and replay-safe agent task envelopes