Epstein's emails reconstructed in a message-style UI (OCR and LLMs)
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…
Epstein's emails reconstructed in a message-style UI (OCR and LLMs) launched on December 12, 2025 with 46 votes, #450 of 11,628 launches that month and more than 90% of that year's launches.
In plain words
This project reconstructs Epstein email records released by the U.S. House Oversight Committee, processing 23,124 image files and 2,800 OCR text files to extract individual messages from cluttered email screenshots. Using OCR and vision-LLM technology, it normalizes sender and recipient information, rebuilds timestamps, detects duplicates, and maps email threads. The output is a structured SQLite database queryable through a lightweight progressive web app with a phone-style interface, running client-side via WebAssembly.
written from the facts on this page · September 2026
From the sources
Contribute to Toon-nooT/epsteins-phone-reconstructed development by creating an account on GitHub.
In the maker’s words, at launch
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…
Does a similar job
all alternatives →
Jmail – Google Suite for Epstein filesDec 2025 · jmail.world · ▲1,557Hi everyone! My name's Luke and I made the original Jmail here alongside Riley Walz. We had a ton of friends collaborate on building out more of the app suite last night in lieue of DOJ's "Epstein files" release. Please AMA!
- OAOSS AI agent that indexes and searches the Epstein filesJan 2026 · epstein.trynia.ai · ▲211
Hi HN, I built an open-source AI agent that has already indexed and can search the entire Epstein files, roughly 100M words of publicly released documents. The goal was simple: make a large, messy corpus of PDFs and text files immediately searchable in a precise way, without relying on keyword search or bloated prompts. What it does: - The full dataset is already indexed - You can ask natural language questions - Answers are grounded and include direct references to source documents - Supports both exact text lookup and semantic search Discussion around these files is often fragmented. This…
- EFEpstein Files Organized and SearchableNov 2025 · searchepsteinfiles.com · ▲329
Hey all, Throwaway in case this is assumed to be politcally motivated. I spent some time organizing the Eptstein files to make transparency a little clearer. I need to tighten the data for organizations and people a bit more, but hopeful this is helpful in research in the interim.
PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o2024 · github.com · ▲191I've developed a Python API service that uses GPT-4o for OCR on PDFs. It features parallel processing and batch handling for improved performance. Not only does it convert PDF to markdown, but it also describes the images within the PDF using captions like `[Image: This picture shows 4 people waving]`. In testing with NASA's Apollo 17 flight documents, it successfully converted complex, multi-oriented pages into well-structured Markdown. The project is open-source and available on GitHub. Feedback is welcome.
- EFEpstein Files and images (4000 .png files)Dec 2025 · epstein-files-browser.vercel.app · ▲9
credit to @RhysSullivan on github for creating this
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, December 2025
the whole month →- GP
Life & fun · Dec 2025 · dosaygo-studio.github.io
Hi everyone! My name's Luke and I made the original Jmail here alongside Riley Walz. We had a ton of friends collaborate on building out more of the app suite last night in lieue of DOJ's "Epstein files" release. Please AMA!
Life & fun · Dec 2025 · jmail.world
PlanEat AI▲733AI turns your health goals into a 7-day menu & grocery list
AI · Dec 2025 · planeatai.com
Community, All the HN belong to you. This is an archive of hacker news that fits in your browser. When I made HN Made of Primes I realized I could probably do this offline sqlite/wasm thing with the whole GBs of archive. The whole dataset. So I tried it, and this is it. Have Hacker News on your device. Go to this repo (https://github.com/DOSAYGO-STUDIO/HackerBook): you can download it. Big Query -> ETL -> npx serve docs - that's it. 20 years of HN arguments and beauty, can be yours forever. So they'll never die. Ever. It's the unkillable static archive of HN and it's…
Dev tools · Dec 2025 · hackerbook.dosaygo.com
