Early access

Travel data infrastructure for AI products.

TravelMindsAI is a grounding layer for travel AI: curated cities, points of interest, lodging, visa rules, UNESCO sites, and composite destination scores — joined to Wikidata and Wikipedia for explainable answers. Designed for retrieval, not as a thin LLM wrapper.

What's in the dataset

All numbers reflect the current curated data layer. Coverage is updated as ingestion pipelines run.

29,325

Curated cities

Deduplicated, ISO-coded, lat/lon-resolved.

193,946

Quality-filtered POIs

Foursquare-derived; duplicates and tribute pages excluded.

170,738

Hotels

Cross-source deduplicated, license-tagged.

691,494

Restaurants

Including Michelin-licensed entries.

462,042

Experiences

Tours and activities, deduplicated.

2,432

UNESCO sites

Including transboundary sites.

39,787

Visa pairs

Plus per-passport openness scores for 199 passports.

247,603

City images

From Wikidata under permissive licenses.

How it's different

A retrieval substrate, not a chatbot.

License-aware by default

Every row carries its source, license, and a license-passed flag. Commercial-public buckets are separated from internal-only at the schema level.

Composite destination scoring

NULL-aware master score blending social, connectivity, sentiment, and value-for-money signals — with explicit coverage penalties.

Multi-store architecture

Postgres + pgvector for app reads; OpenSearch for hybrid search; Neo4j for graph context; DuckDB for analytics.

Grounded narratives

City and POI narratives are generated from the curated data with hallucination checks against an explicit context manifest.

Status

TravelMindsAI is in early access. We are not yet listed on third-party API marketplaces. Pricing and refund terms are published so that early-access customers can evaluate the platform with full clarity. The order process for paid plans is conducted by our online reseller Paddle.com — Paddle is the Merchant of Record for all our orders, and handles customer service inquiries and returns.