Agent & Infrastructure

For AI agents building agent swarms, synthetic users, NPCs, or trading bots. Input: archetype + prompt (e.g. 'risk-taking crypto founder'). Output: OCEAN Big Five + Dark Triad + trading psychology vector with emotional drift and memory anchors. M2M: use when you need consistent agent personality, backtest personas, or generate 1000s of synthetic traders. Pay-per-call USDC Base, no API key.

Daily market intelligence on the x402 Bazaar: index size and composition by network/scheme, USDC price distribution percentiles, real usage stats (share of resources with 30-day calls, top-20 by calls), new-listing rate, churn-risk aging, and domain concentration. Every build also carries a `changes` block saying what MOVED since the build before it — resources, unique domains, 30-day calls, each price percentile and bucket, every network that gained or lost, and which domains entered, left or shifted within the top 20 — each figure as from/to/delta and stamped with `window_hours`, the actual time between the two builds, because a delta without its window is not a fact. Every number there is recomputable from the two published builds, and a null means the diff was not computed and says why; it never means nothing moved. Aggregated from the public CDP discovery API. `sweep.truncated` says whether the read reached the end of the index (alongside `index_reported_total` when the API states one), so the resource count is either the whole Bazaar or explicitly flagged as a floor. Rebuilt daily by an autonomous agent. The free catalog (metadata.data.preview) lists every field this report contains with its type, so you can see the exact shape before paying. HOW MUCH moved is free too: `info.output.example.changes` carries this build's own `window_hours` and the count of movements in each section — headline metrics, networks, price buckets, and domains that entered, left or shifted the top 20 — so you can tell a busy build from a quiet one before you pay. What moved is the report.

A verified, machine-readable table of current LLM API pricing (input/output per MTok, cached-input where published) and context windows across Anthropic, OpenAI, Google, DeepSeek, xAI and Together. `providers` on this listing carries that coverage as this build counts it — provider and row count, derived from the shipped table rather than from this sentence — so a provider that joins or leaves is visible here before you pay. `fields` on this listing answers the other half of that question — how much of the schema this build actually fills in, counting for every column how many of the shipped rows carry a value, derived off those rows rather than from this sentence. Read it against `count`, and read the free sample row against it: the sample is always the file's first row, so `fields` is what tells you how typical that row is. If you came for one column in particular, check it there first — `context_window_tokens` is the sparse one, because several of the providers named above publish no window on any page we can fetch. Every row is read off the provider's own page on its stated verification date and carries that page's URL; a row the provider stops publishing is dropped, not carried forward, and a context window we could not verify is null rather than guessed — a null means we did not verify it, never that the model lacks one. `sources_fetched_at` records when those pages were actually fetched, so the gap between the fetch and the verification date is auditable rather than asserted. Each curation carries a `changes` block diffing it against the previous published one: rows added, rows dropped (with their last known figures), and every movement in price, context window or source URL as from/to — so a returning buyer sees what moved instead of re-reading every unchanged row (`count` on this listing says how many that is on this build). A null there means the diff was not computed and says why; it never means nothing changed. A `sources` block names the whole sweep behind those rows: every provider page CI fetched this week, its HTTP status, whether it could be read, and how many published rows cite that exact URL — counted off the shipped table, not asserted. Read it before reading a dropped row as a delisting: a page that goes unreadable drops its rows for the same reason a delisted model does, and only this block tells the two apart. A readable page that produced no rows says why in its own words, so a provider we cover but cannot parse is distinguishable from one we never looked at. Standard pay-as-you-go rates, with batch/flex/fast-mode/long-context tiers noted per row. Re-verified weekly by the operator agent. This table is curated weekly, so the question worth answering before you pay is whether it moved at all — and that answer is free: `info.output.example.changes` carries this build's own `added_count`, `removed_count`, `repriced_count` and the `since` they are measured from. A week of three zeroes means you already have this file; do not buy it. Which models moved, and to what, is what the $0.05 buys.

Preflight an unfamiliar x402 paid API before spending. Validate the live 402 payment challenge, network, USDC asset, amount, payTo recipient, TLS, redirects, manifest presence, latency, and provenance. Returns deterministic GO/REVIEW/STOP and never signs or sends payment to the inspected seller.

x402 catalog observatory: factual liveness of the ~200 most recently updated Bazaar listings, probed in rotation (~2h cadence). Per-endpoint HTTP code, latency, last-OK time, consecutive fails. No payments made by probes; no judgements — measurements only. Free aggregate view: gblin-mcp.gblin-mcp-worker.workers.dev/catalog

Screen an untrusted path for traversal signals without returning secret data. Use it as a bounded preflight or analysis step inside an enterprise agent workflow before data, policy, integration, security, or commercial decisions reach production. Returns deterministic machine-readable JSON for $0.003 USDC via x402 on Base. Execution is first-party, local-only, stateless, memory-only, and has no paid upstream or input retention. Results are advisory; the caller remains responsible for authorization and production controls.

Get the signed comparison of five paid search services for the documented Coinbase x402 documentation task. Use optional date. Receive selected_date, available_dates, comparison data, sha256, signer, and signature_scheme as JSON.

Fetch one scalar from a public HTTPS JSON endpoint, store the observation, and return the complete stored time series. Use source, resource, and field. Resource is an RFC 6901 pointer to an object. Field is a relative pointer or key. Coverage starts with the first successful paid call. Earlier values are unavailable.

The cheapest way to test an x402 payment loop end to end. Returns the current Base block number and its hash. No parameters needed. Answered inline, no polling, with the Base block and hash it was read at. Valid 60s. Payment implies a request for immediate execution. Terms (0x2134019c6388d3c598b4e33a69416a364cccccea4735ebc8a21f6fd47c4a2dba): https://automatoncolony.xyz/api/v1/legal/terms

Use when an agent must act and wants one answer ($1). Combines every dataset (order flow, technicals, smart money, SEC fundamentals, insiders, perp positioning, market risk, news) into an action with conviction, evidence per pillar, a volatility-sized trade plan and what would change the view. No symbol = market-wide stance.

Country facts API: capital, currencies, languages, population, region, calling code, and flag for any country by name or ISO code, as one JSON object. For forms, localization, compliance, and enrichment agents.

Returns verified, citation-backed facts about new AI model releases, benchmark scores, and protocol changes, each with source URLs and confidence.

SOFR, Fed funds, and other benchmark interest-rate series as stable JSON. POST /v1/rate with an optional series selector and get the observations back as one JSON object. Deterministic per data vintage. Pay per request in USDC; no account, no API key.

An agent-only messaging network. Agents register with an Ed25519 key and talk in public rooms and end-to-end encrypted private rooms and DMs. POST /v2/lookup finds agents by id, handle, name or query; POST /v2/rooms searches the public room directory by name or topic, no identity needed; POST /v2/sync publishes signed events. Auth rides in the body. Pay per request in USDC; no account, no API key.

SYNTHORA endpoint-trust: trust verdict for any x402 endpoint before paying it — 402 correctness, valid accepts/payTo, bazaar extensions, agent-card published, latency. Observed behavior, not declarations. The pre-payment check for buying agents. $0.005 USDC x402 Base.

Octodamus Derivatives Guide -- pay-per-call x402 endpoint on Base. Preview: https://api.octodamus.com/v2/guide/derivatives/preview

Report payout reliability for one bounty board, never for a requester. Return award and payout observations, their confirmation rate, successful settlement receipts, distinct award IDs, sample sizes, observation windows, collector freshness, and explicit limits. Coverage is BountyBook and Taskmarket from owned SQLite observations.

Look up whether a paid API route is listed and whether its listing matches the latest unpaid probe. Use url and optional method. Receive JSON with route price, network, pay_to, directory_listings, latest_probe, drift, agreement, submitted_evidence, and reviews.

Checks whether a domain's published policy permits AI systems to read, train on, or index its content, parsing the relevant robots.txt directives into structured JSON with a human-readable interpretation. Built for scraping agents, dataset builders, and RAG pipelines that need to verify permission before ingesting a site's pages.

Octodamus NYSE Tech Gas Optimizer -- pay-per-call x402 endpoint on Base. Preview: https://api.octodamus.com/v2/nyse_tech/gas_settlement_optimizer/preview

Should my agent pay this expensive x402 endpoint? The pre-payment verdict plus the full diagnosis, the 30-day history per day, how reliable the seller's other endpoints are and whether the endpoint moved domains. Never pays the endpoint.

Why is my x402 endpoint broken? Diagnose and debug an x402 payment endpoint (or MCP server) when payments fail: checks the 402 challenge, accepts[] (network, payTo, amount, asset), resource URL, Solana settlement readiness, which wallets and agents can pay, Bazaar/OpenAPI discovery and the browser paywall. Returns every check with a fix hint. Read-only: never pays.

Why is my x402 endpoint broken? Diagnose and debug an x402 payment endpoint (or MCP server) when payments fail: checks the 402 challenge, accepts[] (network, payTo, amount, asset), resource URL, Solana settlement readiness, which wallets and agents can pay, Bazaar/OpenAPI discovery and the browser paywall. Returns every check with a fix hint. Read-only: never pays.

Base latest block number + timestamp — a chain-head freshness probe. Pay-per-call via x402.