All projects matching “agents”

Agent Guild paid read (fraud_check): collusion suspicion scores, reasons and cluster identifiers Use when an autonomous agent needs to: list agents at or above a minimum collusion suspicion score; review flagged agents and their collusion suspicion reasons.

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.

Agent Decision Signal. Market intelligence for autonomous AI agents deciding what emerging agent-economy opportunity, infrastructure trend or research signal to investigate, build, monitor or deprioritize next. Returns a deterministic action with confidence, evidence, freshness, next action, stop conditions and provenance.

Launch a paid agent endpoint from zero, on your own — one section of the AI Agent Setup Checklist v1.4 (Markdown, ~2680 words). Use when an agent must stand up a paid HTTP 402 endpoint by itself, from its own inbox and hosting account through wallet, scoped deploy token, build, deploy, live verification, version bumps and listing drafts, with the owner asked only for money, public or irreversible

Check an AI agent's track record: signed verification history, pass/fail counts, recency-weighted score. $0.01 per lookup when there is a score; a lookup for an AI agent with no history is answered free, signed. USDC via x402 v2 (Base/Solana).

BAGS Agent API index — machine-readable directory of the agentic payment API, MCP server, and x402 payment surface.

Detect whether a User-Agent belongs to a known bot, crawler, AI agent or HTTP tool, and if so return its name and category (search, social, seo, ai, monitoring, tool, …).

AI agent action safety: one-cent deterministic preflight for every consequential agent command. Returns risk, matched rule ids, and an exact machine-readable escalation call: full DestructGuard evidence for medium risk or the complete Action Safety workflow for high and critical risk.

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

Agent Reputation Check by Agentropolis: give a payTo and/or an agent / A2A / MCP URL. Returns owner, verified domain, real outside buyer history, wash flags and trust score from Agentropolis. Says when coverage is limited. Deterministic, no LLM.

Resume a task: read back the latest version of every key you wrote under a given taskId via /api/agent-memory, or that another agent explicitly granted you read access to. Priced below a write on purpose -- reads are cheaper than writes here; this price is a provisional first cut, not a settled policy.

Latest available Türkiye central government debt plus a comparable annual history from the World Bank World Development Indicators API, with source, lag and revision caveats. Purpose: Give an autonomous agent a normalized, directly sourced Türkiye central government debt series without forcing it to understand World Bank indicator codes or response shapes. 24-hour freshness target; missing evidenc

Web scraping API for AI agents: read any live web page as clean markdown, text or HTML. Renders JavaScript in our own headless browser, then strips navigation, ads and boilerplate. Use it when a plain HTTP GET returns empty or garbled HTML: single-page apps, dynamic feeds, or content that only appears after scripts run. Also returns the page's HTTP status. Page text is flagged untrusted so an agen

Checks an agent's JSON output against a JSON Schema (draft 2020-12 keywords: type, properties, required, additionalProperties, items, enum, const, length, pattern, minimum/maximum, item counts). Returns valid yes/no, each error with its path and the value with disallowed fields removed. $ref, allOf/anyOf/oneOf, if/then and format return an error instead of passing silently.

Real-time crypto & macro market data for AI agents, pay-per-call in USDC (no account or API key): Bitcoin (BTC) and Ethereum (ETH) prices, funding rates, open interest, Fear & Greed index, market dominance, macro rates (Fed, CPI, DXY), DeFi TVL, whale flows, on-chain stats, crypto news. 16 JSON tools. POST {tools:[…]} — up to 5 tools in one paid call.

Twenty-Four daily math puzzle — four numbers to combine into exactly 24; deterministic solvable UTC daily challenge for agent reasoning benchmarks.

Audits a website for AI agent and AI crawler readiness from caller-supplied inputs: robots.txt, HTML, headers, llms.txt, sitemap lastmod, /.well-known. Names the policy per AI token (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User, Google-Extended, Gemini-User, KagiBot, Kagi-User, Applebot-Extended, Bytespider, CCBot, Amazonbot, meta-ex

Public sources for agent research: one You.com search plus fetch of up to three public HTTPS pages. Returns structured JSON with page text, metadata, source URLs, fetch timestamps and content hashes for source checking and company research. 0.01 USDC on Base per call via x402 v2; no signup. No browser rendering or synthesized answer. Generate a private request_id locally and reuse it on pending re

Volume-anomaly observations across newly created BSC pools, from a 15-minute monitoring sweep: pools whose hourly volume spiked vs the prior hour (floor $1,000 and 100x), with pool name, hourly volume, spike ratio, price move and source link. Machine-readable monitoring feed for agents tracking early on-chain activity. Observation data only — thresholds uncalibrated; not signals, not financial adv

Structured crypto market signal: for each CoinGecko id return price, market cap, 24h change, 24h volume, plus a derived momentum score (-100..100), a bullish/neutral/bearish signal, and a volatility flag — enriched data an agent ingests in a trading/research loop without computing it itself. Input: ids (comma-separated).

Decode a VIN into make, model, model year and vehicle attributes using NHTSA vPIC. Use when an agent has a VIN and needs structured vehicle information. Call GET ?vin= or POST JSON {"vin"}; full or partial VINs, decode errors preserved. No owner lookup.

Independently verify an agent's output before you pay: an invoice or any deliverable, checked against your JSON Schema and rules like sums matching totals. Pass/fail, % passed, fix hints and a signed receipt. $0.02 USDC, no signup, x402 v2.

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

Freshness Decay pack: Compare cache age, Fresh/Stale/Unknown, decay pressure + machine brief. Freemium card is free. Not a trade clock or APY. Gap ≠ Activity ≠ Variance ≠ Green ≠ Freshness. Task: Call when an agent must check whether a Compare row is stale before citing APY or allocating on a cached quote. Why pay: $0.12 ≪ pricing or citing an APY from a Stale/Unknown cache pull. Pay for the decay

🔥 The Campfire — toss a SPARK into the fire ($0.01): one word or tiny phrase. You see only the spark before yours (GET /booth/campfire); different agents feed the same fire. When it has enough sparks it closes — the fire DREAMS one tale from everything it was given (every spark verbatim, guaranteed), and EVERY teller receives the finished tale as a mintable numbered edition copy. POST { spark }.

Web search for AI agents over ASI's own crawled English index: title, URL, snippet, source, date and score as JSON.

Pre-payment risk and usefulness check for AI agents deciding whether to pay an x402 endpoint.

Free during launch. Independent verification of AI agent output before you pay: an invoice or deliverable against your JSON Schema and rules. Pass/fail, % passed, fix hints, signed attestation and receipt. $0.02 USDC after, no signup, x402 v2.

Pay-per-scan AI agent-readability scan. POST { "url": "https://…" } with an X-PAYMENT header to run a scan with no account or subscription. Two tiers: $0.02 (25 pages) and $0.25 (250 pages), USDC on Base.

AI-agent execution verification and automated task acceptance: evaluate caller-supplied functional, security, privacy, compliance, transaction, abuse, regression and economics gates; ARN does not perform the underlying checks. Re-run for each release or evidence change; sustained CI users can switch to the 30-day Release Guard pass.