All projects matching “agent”

Generate a stable, secret-free fingerprint from a build or test failure so agents can group duplicate CI errors across changing line numbers, timestamps, paths, identifiers, and retry attempts.

Submit one verifiable fact on the machine-payments beat for editorial review. Body: {"contributor_wallet": "0x... (Base, receives the bounty)", "category": "machine_payments_metrics|x402_endpoint_news|protocol_governance|pricing_change|other", "fact_statement": "one specific checkable claim, 20-600 chars", "source_url": "https://..."}. Agent-run review within ~48h fetches your source and checks it

Web content extraction: fetch any public URL and get clean readable text, title, meta description, OpenGraph data, headings, links and word count as JSON. Built for AI agents that need web page content without HTML noise.

Which x402 API should my agent call? Describe the task in plain words (need=) and get up to 5 x402 APIs ranked by relevance plus CDP Bazaar-reported 30-day usage (unique payers, repeat ratio, last call; sellers paid via other facilitators may show 0; sweeper-like usage is flagged and not rewarded), each re-checked right now for a 402 payment challenge (unless probe=0), with price, network, payTo,

Composite 0-100 buy-safety score for any token: combines contract security analysis (honeypot, taxes, ownership risks) with live market depth (liquidity, volume, activity) into a single verdict: avoid | high-risk | caution | ok | strong. One call answers 'should my agent touch this token?'

Live-probe any x402 URL before your agent pays it: is the 402 challenge valid, what does it really cost, which token and network, does the pay-to match the listing, and is it known to be trustworthy.

Coding Agent GitHub Repo, Dependency & License Security Auditor (/v1/github-audit) — Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and supply-chain security before code execution.

Golden Kog token risk analysis by Kognai: one Solana or Base token read on chain for structure and risk (holder concentration, launch bundles and the dev wallet, liquidity, mint and freeze authorities, taxes and honeypot checks on Base, issuer controls, trading momentum), with a risk level, its flags and a short report. Use it before an agent or a trader touches an unfamiliar token. Risk reading o

Company hiring-intent radar for sales agents: one call turns a company domain into buying signals from its public job board (Greenhouse, Lever, Ashby, Workable, Recruitee, SmartRecruiters): intent_score 0-100, hiring_status, open roles, roles posted in the last 30 days, hiring by function (sales, engineering, data/AI...), technologies the company is hiring for (cloud, data/AI, databases, observabi

test-1 agent service: $0.01 per request

Rank x402 Arena agents and niches by observed self-reported organic purchases while excluding house-funded activity.

Stateful pre-payment firewall for autonomous agents. Enforce caller-supplied amount/network budgets, detect repeated intents, seller pay-to/network drift and large price jumps. Never signs or sends the downstream payment.

Cost-aware perpetual funding pulse for trading agents. Returns three interval-normalized cross-venue venue pairs with gross funding dollars, caller-supplied all-in costs, projected net funding, break-even time, liquidity tier, and BTC/ETH/SOL context.

Search Zillow homes by ZIP code (several per run): for sale by agent, for sale by owner, for rent and recently sold, with price range, days on Zillow (1 to 90) and minimum bedrooms. Up to 25 listings in ONE call with listing status and text, home type, price and formatted price, sold price, full address, coordinates, bedrooms, bathrooms, living area and listing link. $0.025 per call = $0.001 per l

Deterministic npm package evidence: registry facts, distribution integrity, provenance, and factual flags for coding agents.

Low-cost Bitcoin (BTC) 60-minute / 1-hour higher/lower probability, expected return, freshness, and model metadata for autonomous agents.

JSON canonicalization — canonicalize structured data with RFC 8785 JCS; return canonical JSON text, UTF-8 byte length, and SHA-256 hash for integrity checks, signature preparation, and deduplication. Includes an EIP-712 signed attestation. Use when an agent needs an idempotency key, cache key, dedup hash, or verifiable commitment. $0.002 per call. Free verification at POST /v1/verify.

Extract clean, LLM-ready Markdown or token-efficient text from any public webpage for RAG ingestion, research, summarization, or agent context. Strips navigation, ads, scripts, forms, and repeated boilerplate; preserves headings and resolved links; labels fetched content as untrusted; and returns at most 50,000 characters.

Resolve a vendor or company name to the single best Pennsylvania legal-entity match before an agent continues onboarding, enrichment, or due-diligence work.

AI agent runtime with crypto payments on Solana blockchain

BotCheck — Per-request traffic-integrity classification. POST JSON {headers:{...}, signals:{...}} -> deterministic {verdict:human|agent|bot|unknown, confidence:0-100, signals:[{name,value,weight,reason}], classification_version:"1.0"}.

Marketplace for discovering services that agents can pay for with x402.

Settlement-backed machine evidence for autonomous agents. Returns a signed-payment transaction reference and machine-readable proof after exact USDC settlement.

Low-cost live Base mainnet block height, gas price and chain ID for autonomous agents.

Trust Your Coin Market Update NL, Q3 2026 (PDF, 9 pages, English): the Dutch crypto market in Q3 2026 — market performance, ESMA/MiCA register changes for Dutch customers, Trust Your Coin platform data and AI agent developments at exchanges. Returns application/pdf.

Verify Verifiable Intent evidence and Solana x402 payment binding before an agent payment. Price: $0.1 USDC (Solana)

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.

Probe one public endpoint and diagnose whether agents can discover and parse its unpaid x402 challenge.

Use when an agent needs to search the web: research, fact finding, finding official pages/docs, competitor or link discovery, grounding an answer with URLs. Returns ranked organic results (position, title, url, domain, snippet; published date or lastCrawled time when the source has one). The top 10 come from Bing's public RSS results; deeper pages (count > 10 or page > 1) come from Brave Search. S

0xBs public x402 demo — USDC on Base for agent-payable ESP32 hardware.