Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Epstein Graph

Searchable database of 1.3M+ documents with AI summary

Details

External ID
46961617
Source
HN
Company
—
Product
Epstein Graph
Website domain
epsteingraph.com
Launched
Feb. 10, 2026
Cohort
—
Upvotes
5
Upvotes percentile
0.10512129380053908
Tags
—
Fetched at
Sept. 7, 2026, 9:26 p.m.
Updated at
Sept. 7, 2026, 9:26 p.m.

Enrichment

Theme
searchable public records and archives
Vertical
Horizontal
Function
Search & retrieval
Audience
B2C
AI stance
AI feature
Project type
Hobby / open-source project
Normalized one-liner
searchable document database with ai summaries
Manually corrected
False

Could you build this?

Partial Building the Next.js search UI and flight log tables is straightforward, but collecting, OCRing, audio/video transcribing, indexing, and deduplicating 1.3M+ multi-modal investigative documents is a serious data engineering project.

What it would actually take: The architecture requires an extensive ingestion pipeline using Whisper for audio/video transcription, Tesseract/AWS Textract for multi-page PDF OCR, and an entity extraction pipeline (NER) to build knowledge graph relations. The backend needs a high-capacity vector and full-text search cluster (e.g., Elasticsearch, OpenSearch, or pgvector/Meilisearch) capable of managing terabytes of raw files and high-throughput search queries across over a million records.

Discussion

2 comments analyzed.

Competitors

Other products that read as similar to this one — 1278 launches clear the similarity bar, closest 8 shown.

Attention rank: #1134 of 1279 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 104 days after the earliest competitor.

Other launches for this product