Epstein's emails reconstructed in a message-style UI (OCR and LLMs)

Details

External ID

46243658

Source

HN

Company

—

Product

Epstein's emails reconstructed in a message-style UI (OCR and LLMs)

Website domain

github.com

Launched

Dec. 12, 2025

Cohort

—

Upvotes

46

Upvotes percentile

0.8072519083969466

Tags

—

Fetched at

Sept. 7, 2026, 9:25 p.m.

Updated at

Sept. 7, 2026, 9:25 p.m.

Description

This project reconstructs the Epstein email records from the recent U.S. House Oversight Committee releases using only public-domain documents (23,124 image files + 2,800 OCR text files).Most email pages contain only one real message, buried under layers of repeated headers/footers. I wanted to rebuild the conversations without all the surrounding noise.I used an OCR + vision-LLM pipeline to extract individual messages from the email screenshots, normalize senders/recipients, rebuild timestamps, detect duplicates, and map threads. The output is a structured SQLite database that runs client-side via SQL.js (WebAssembly).The repository includes the full extraction pipeline, data cleaning scripts, schema, limitations, and implementation notes. The interface is a lightweight PWA that displays the reconstructed messages in a phone-style UI, with links back to every original source image for verification.Live demo: https://epsteinsphone.orgAll source data is from the official public releases; no leaks or private material.Happy to answer questions about the pipeline, LLM extraction, threading logic, or the PWA implementation.

• Source listing
• Website