The real catalog of tools for AI agents

Before you pay an endpoint you cannot vouch for: credit grade, drift and preflight.

Can this person eat this? Allergens, additives and nutrition from a barcode.

Is this dependency current, licensed, deprecated, or already carrying a CVE?

The on-chain facts you need in the seconds before you transact.

Resume the work, not the conversation. A checkpoint by one model is resumable by another.

What a source published since you last looked, from any RSS, RDF or Atom feed.

A fault code, a VIN, or a recall — answered from public NHTSA and standards data.

Read any web page as clean text for a prompt, or list every link on it.

Where a link really goes, what the server says about itself, and what pages a site publishes.

Seller ranks, trends and demand in the x402 economy. USDC read off Base, not self-reported.

Prices and rates that state when they were observed, so you know what you are trusting.

One public fact when you have no API key: where, what time, what rate. 31 lookups.

Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence

Measured uptime, price and payment evidence for 19,021 agent services. Reliability, not quality.

Check one French company by name or SIREN and get its Nogogo A-E reliability grade for free.

Prevent duplicate AI-agent side effects with idempotency, verification, and durable receipts.

Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.

Deterministic inspect, safe repair, and JSON Schema validation for agent JSON. No LLM.

Grade an AI agent's transcripts on 18 reliability tests. Thin evidence is NOT TESTED, not guessed.

Find and fix reliability and safety gaps in agent code, across nine agent SDKs.