All projects on Base matching “spending”

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 AgentP

[Payment decision: spend policy + seller reputation risk check, one verdict] Right before an AI agent pays: POST {payment, policy, seller} -> ONE verdict pay / dont_pay / ask_human. Runs the spend-policy check (limits, rolling cap, categories, allow/deny, hours, assets/chains, approval threshold) and the x402 seller reputation check (buyers, wash share, age, concentration), with reasons and one si

Signed spend receipts for agent x402 payments — who paid which call, verifiable by a third party. Treasury desk and possession book for agent spend — export, policy, evidence. POST /v1/chat/completions is the x402 USDC door on Base and Solana. Returns signed receipt + public verify_url. Paying this host is real mainnet USDC.

Spend-policy verdict for AI agents: POST a proposed spend, get allow/review/deny with the exact rules that fired (per-tx caps, per-agent daily ledger, destination allowlists, time windows) - 'review' can page a human on Telegram for approval before the agent proceeds. Pay per call.

Signed spend receipts for agent x402 payments — who paid which call, verifiable by a third party. Treasury desk and possession book for agent spend — export, policy, evidence. POST /v1/chat/completions is the x402 USDC door on Base and Solana. Returns signed receipt + public verify_url. Paying this host is real mainnet USDC.

Change detection for anything with a URL, built for monitoring loops: probe one x402 resource or web page WITHOUT paying it and answer BASELINE, UNCHANGED, or CHANGED with a field-by-field diff (price, asset, payTo, schema, page body) against the last check for that watch. Use this when an agent runs on a schedule and needs to know what changed before spending money or attention. Watch and pack st

Statement history: The agent's last 24 three-hour statements (outflow split into spend and routing hops, what left its control, income, open flags), each with its keccak-256 hash, the prevHash link that chains them, and a Merkle proof against the signed root of its window. About one ERC-8004 agent on Base, by Agentic Finance Graph. id = token id, slug or bound wallet; an agent never seen paying is

Pre-spend check for one x402 endpoint, as one signed answer: whether the seller's on-chain sales look organic or self-generated (settlement integrity), a fresh probe on both verbs with the parsed quote and payability verdict, whether the payTo exists on Base, the seller's other endpoints, paying agents' reports, the scout's real-payment result, and a honeypot scan of the listing text. Returns reco

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.

Al-Mizaan 7-gate validity judge for your OWN bug bounty finding — mechanical gates + adversarial LLM debate (Defender/Attacker/Judge), before you spend a real submission on Sherlock, Immunefi or Cantina

Find x402 APIs that agents actually pay for: keyword search over the whole Coinbase x402 Bazaar (31,000+ paid endpoints), ranked by distinct paying wallets in the last 30 days. Filter by max price and network. Returns URL, method, price, 30-day payers and calls, last paid call. Use to pick a proven seller before spending.

Check whether an approach to ComfyUI video generation is a known dead end before spending GPU time on it. Returns the failed approach, what was tested, and what to do instead. Use BEFORE running an experiment you're unsure about. Covers WanVideoWrapper, chaining, interpolation, and upscaling.

Audit real gas spend across up to 20 Base mainnet transaction hashes you provide — total/average gas used, cost in ETH, per-tx breakdown. POST body required. Experimental/informational only — not financial advice.

Use before spending tokens, money or crawler capacity fetching an unfamiliar web resource. Resolves redirects (manually, bounded, re-validated per hop) and returns deterministic HTTP/resource facts — final URL, status, content type and length, response time, a bounded HTML title/canonical peek, and a lightweight generic-bot robots.txt indication — so an agent can decide whether a normal web fetch

One combined go/no-go before an agent spends: PROCEED / CAUTION / ABORT from the token's market verdict, the counterparty wallet's sanctions, age and poisoning check, and — with a spender — its ERC-20 approvals. A leg that cannot be evaluated returns unknown and caps the verdict at CAUTION. Mode 'compact' returns the decision, the worst leg, and one summary per leg. Use this when an agent is about

Per-agent budget enforcement — track an agent's cumulative spend against a cap and block overspend. Part of x402 Agentic, the payment-trust suite for AI agents on Base USDC.

Public, account-free preflight for an autonomous x402 payment. Validates the merchant's exact PAYMENT-REQUIRED challenge against the intended request, checks Base USDC payment integrity and public merchant/payTo risk evidence, and returns APPROVED, REVIEW or DENIED with signed proof. It does not grant spending authority: an APPROVED result means the transaction evidence is clear enough to proceed

Use when you have a company domain and need to know what the company is before spending more. Returns the company name and site title, domain age, registrar, mail provider, DNS provider, DMARC and HTTPS status, and a count of the third-party vendors detected. One call, no signup, no API key. The cheapest way to qualify a domain before buying a fuller record.

Spend preflight for AI agents. Send the x402 PaymentRequired body (v1 or v2) you received, or a cart, plus optional rules (per-payment max, hold threshold, daily cap, allowlists, new-domain days, endpoint category price multiple, liveness and payTo changes). Returns allow|hold|block with reasons, the cheapest acceptable payment option, and a receipt id. Read-only: never signs, settles, or holds fu

LLM cost scout: send your monthly OpenAI API spend in USD and get back the flat ChatGPT/Codex subscription tier that absorbs it through the ProxyLLM gateway, the exact new monthly total and savings, the live model catalog, and machine-readable signup steps an agent can complete autonomously (email OTP, no browser).

Vet an Apify actor before you spend on it. Send one actor ID (e.g. apify/instagram-scraper) and get scored JSON in seconds, with evidence and a verdict, from public metadata: pricing, output schema, maintenance, reliability, docs. Unlimited criteria: our pre-built set or your own rubric in plain English. Metadata grades what a vendor claims. The $1 full audit runs the actor and measures what it de

Agent Budget Guard: pre-payment budget check, spending limits, allow/deny approval and audit evidence for AI agent x402 USDC payments

Accounting, reconciliation and audit trail for autonomous agent spending. Every x402 purchase becomes a receipt matched against the on-chain USDC payment (Base, Solana); unmatched payments are flagged; finance gets a monthly statement, CSV export and a verification page per receipt. USD 0.01 per wallet per day it records, at most USD 0.31 a month; no API key.

Crawl pre-flight for a domain: will you be blocked, is content behind a paywall, and how much is actually there. Returns per-bot robots.txt verdicts for 16 AI crawlers, crawlable page count from sitemaps, detected CDN and paid-access signals (x402, TollBit), plus a fetch/skip recommendation. Call before spending requests on an unknown domain.

Deterministic read-only spend policy verdict for amount, destination, and approval ceiling. Caller supplies policy; unknown targets require review.

Use when an agent must choose which marketplace to spend effort in: how crowded is it (bids per job, measured), and does money actually move here (payer share, buyer behaviour, freshness)? Answered with coverage and as_of, or UNKNOWN when the market cannot be measured - never a guess.

Validate an intended paid API request against its declared contract before spending. Returns VALID, INVALID, or UNKNOWN with machine-readable reasons. Target URL is never called.

Pre-flight due diligence for GitHub bounty issues. Detect competing PRs, stale issues, maintainer inactivity, saturation and payout-risk signals before an autonomous coding agent spends compute on implementation.

Address Watch for 30 days: every confirmed transaction paying to or spending from one Bitcoin address, in a private feed (web, JSON, RSS) and as phone push (ntfy). Optional feed=<id> adds the address to, or extends it in, an existing feed. Returns the feed links.

Curated JSON of currently scouted agent earning opportunities (hackathons, bounty boards, agent markets) with prize, deadline, agents_allowed, human_entrant_required, kyc, spend_required, verdict and notes. Seeded from Tali's verified scout vault — use when an agent needs an up-to-date earn map without re-scraping the web.