epstein-files

A RAG pipeline implementation built on the 'Epstein Files 20K' dataset from Hugging Face (Teyler).

Open source document processing pipeline for the Epstein case files. Download OCR, extract entities, deduplicate and export documents from the DOJ Releases

An open-source RAG platform to explore the unsealed Jeffrey Epstein court documents.

Play Bad Apple and DOOM on redacted Epstein files and other documents. Implemented using KNN and feature vector.

Chat with the Epstein Case files

A data-driven audit of the 'Geopolitical Thermostat,' documenting how timed information disclosure regulates public attention to enable structural shifts in policy and capital flows.

Epstein files API MCP

downloads .pdf files from DOJ website / epstein data-sets

🔍 Search Epstein court documents for mentions of your LinkedIn connections to uncover relevant insights into your network.

Download all of the Jeffrey Epstein court records with this Python script! Mirror of https://git.graveyard.sh/OfficialB/doj-epstein-crawler

Unofficial python wrapper for Epstein Exposed API

Ask questions about the Epstein Files using AI - A RAG pipeline with hybrid search, re-ranking, and Streamlit UI built on the Epstein Files 20K dataset.

A Python tool to automatically download and archive DOJ Epstein disclosure datasets, with support for resuming from a specific page and skipping already downloaded files. Designed for easy personal archiving and research purposes.

MCP server + CLI for the public DOJ Epstein Files Transparency Act release - search ~1.4M documents across 20 databases (emails, images, transcripts, OCR, knowledge graph), resolve any EFTA number to its official DOJ PDF, cross-check viral claims against a fact-checked registry.

This is a leisure project to search pdf files for specific information using LLMs.

Explore the Epstein files using Natural Language

discord bot that permit users search to epstein files

CLI tool to search, download, and analyze DOJ Epstein case documents

This analysis employs established methodologies from computational social science, legal informatics, and criminal network analysis, with all claims directly supported by primary Epstein Files Transparency Act (EFTA) document citations. It provides an overview of the materials suitable for use by researchers, journalists, and legal professionals.

Open-source extraction pipeline behind aretheyinvolved.com: multi-stage NER + LLM classification across 1.5M+ pages of publicly released Epstein documents.