Source-cited datasets for the agent web

Transparent, machine-readable datasets an AI agent can verify and safely cite — each with published sources, coverage, methodology, and a fixed citation. Maintained by Oscar E. López, Ph.D.

Datasets

Argentina Food & Beverage Price Index live · daily

A daily, source-cited index of online food & beverage prices in Argentina (base = 100), collected from public retailer catalogs. Free headline; full series via API/MCP.

Coverage: Argentina (Buenos Aires) · updated daily · methodology · ethics

AI Vendor Data-Trust Index live

A source-cited comparison of how AI products handle your data — does the vendor train on it, is zero data retention available, can you opt out. Every value carries a verbatim policy quote, source URL, and date; an automated verifier re-checks weekly.

Coverage: 16 AI vendors & services · verified & auto-re-checked · details & API

AI Model Lifecycle & Deprecation Index preview

Is this AI model still live? When does it sunset, and what's the migration target? Cross-vendor lifecycle across OpenAI, Anthropic, Google, and Amazon Bedrock — status, release/deprecation/shutdown dates, replacements — each traceable to the provider's official announcement.

Coverage: 71 models across 4 providers · source-cited · details & API

More datasets coming

Additional transparent datasets are in development. Each follows the same principle: verifiable provenance on every value.

For AI agents

Datasets are available as free headlines, priced APIs, and Model Context Protocol (MCP) tools at api.oscar-lopez.com, with discovery manifests at /.well-known/x402 and /openapi.json.