Paid services on Base matching “agent-tools”

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.

Repariert die typischen Fehler aus Sprachmodell-Ausgaben und Fremdsystemen: Markdown-Zaun, haengende Kommas, einfache Anfuehrungszeichen, unquotierte Schluessel, Kommentare, typografische Anfuehrungszeichen, unsichtbare Zeichen, fehlende Klammern, NaN und Infinity. Liefert das geparste Objekt und ein Protokoll jeder einzelnen Reparatur.

Fetch a public web page and return just the main article as clean Markdown, with title, byline and excerpt. Menus, ads and footers are removed. Use when you need to read, summarise or quote a web page cheaply without parsing HTML yourself. Returns JSON {title, byline, siteName, excerpt, markdown}. Errors: 400 bad or private URL, 422 no readable article, 502 site returned an error.

Checks one email address and returns valid, risky or invalid with the reasons: address format, whether the domain can receive mail (live MX lookup), known throwaway domains (mailinator and others, invalid), shared inboxes like info@ or sales@ (risky), likely typos such as gmial.com with the fix in didYouMean, and free providers such as gmail.com (flag only). Does not ping the mailbox (no SMTP), so

Email validation for signup forms, lead lists and CRM cleanup: checks syntax, MX mail servers, disposable or temporary domains, role addresses (info@, sales@) and free providers. Returns a deliverable_guess. No SMTP probe, no data stored.

Parse JSON or profile a JSON value. Returns canonical JSON, a SHA-256 fingerprint, structural metrics, and an inferred shape.

URL to Markdown API for AI agents. Converts a public web page into clean Markdown for LLMs and RAG pipelines: main content only (no nav, ads or scripts), absolute links, plus title, description and language metadata. Suited to AI agents that read, cite or summarize web pages. Respects robots.txt; only successful reads are charged. Search intents: url to markdown, web page to markdown api, web scra

Test that your x402 client can pay AUN: one call returns a deterministic paid receipt that the purchase was delivered (a liveness check, not downstream business-value proof). Use it as a first test call; once it works, the same client and wallet can call vendor-intelligence (company research), domain-trust-score or web-read-batch with no setup. $0.001 USDC per call on Base.

Routes requests across open-weight models using task fit, tool calling, vision, JSON format, context, output capacity, provider availability, and price. Send POST application/json with model set to ai-open-models/auto and a non-empty messages array. task_type is optional; when omitted, Auto classifies the request. Supports function tools, JSON responses, and mixed text/image messages using public

Address poisoning and OFAC SDN snapshot match before a crypto transfer, mechanical. GET chain (base/polygon/solana/xrpl), to; opt. expected, token. Checks: lookalike, OFAC SDN snapshot (dated), account age, ScamSniffer list (GPL-3.0). allow, warn or block per check. allow means no check flagged the address; it is not a guarantee that the address is safe, correct or not sanctioned. Not advice. Bad

Use to extract the main article or document text from a single-page URL. Not for homepages or hubs (Web Index Cleaner) and not a link inventory (Link Extractor). Server HTML only; JavaScript is not run. Output is text or markdown. If the requested extract has no main content, the other profile is tried once in the same request. The HTTP body has correlation_id and data. The item array is data.resu

Use before paying any x402 endpoint, so you don't pay a dead or mispriced one: checks it is alive, correctly payment-gated, its price/network/asset, latency, and whether it fits your max_price_usd. Sends one unpaid request, never pays. ~9% of paid listings we scanned were dead. Errors (never charged): 400 bad input, 422 source could not be fetched or parsed, 429 rate limited (30/min), 502 upstream

Read a public static HTTPS webpage as clean text with headings, links, timestamp and content hash. Use to ground an answer or ingest documentation. Respects robots.txt; no JavaScript or login.

Procure a missing capability across AgentResolver, provider manifests, 402 Index, PayAI, Circle and MCP, then perform at most two unpaid live verification probes for supported MCP/x402 candidates before returning an evidence-backed recommendation. L402/MPP remain discovery-only until protocol-specific verifiers exist.

Browser screenshot, rendered HTML, metadata, PDF and signed artifact receipt. Service-clock time; no independent timestamp or completeness guarantee. Exact-host loading; other-host assets and redirects excluded.

Find a DST-aware meeting window inside shared local business hours for 2 to 8 IANA time zones.

Repairs malformed LLM JSON: strips Markdown fences and prose wrappers, fixes trailing commas, converts Python literals (True/False/None) and single/unquoted keys, removes comments, recovers balanced JSON from truncated output. Body {input} -> {ok, repaired, applied}.

GENESIS Release Guardian (quick)

Canonical GitHub bounty viability check for agents: issue state, repo trust, payout evidence, age, claims and competing PRs. Prevents wasted coding on stale or fake rewards.

Return a USD spot-price consensus for BTC, ETH, SOL, or USDC using fixed public CoinGecko, Coinbase, and Kraken routes.

Lint any x402 endpoint before you pay it: fetches the unpaid 402 challenge (v1 body or v2 PAYMENT-REQUIRED header), decodes price/network/asset/payTo, flags non-USDC assets, testnets, missing bazaar metadata and malformed fields.