AbhisumatK/Epstein_Files_RAG

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

Python

51

14

1 contributors

MIT License

FeaturedAdvertise to 180K+ monthly visitors

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast AbhisumatK/Epstein_Files_RAG is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 12 – Nov 6, 2026

Stars +2 in 56 days

1

Forks +0 in 56 days

Merged PRs 0 in 56 days

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 12Sep 19Sep 26Oct 3Oct 10Oct 17Oct 24Oct 31

Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day	Stars gained	Forks gained	Merged PRs
Sat, Sep 12, 2026	+1	+0	0
Sun, Sep 13, 2026	+0	+0	0
Mon, Sep 14, 2026	+0	+0	0
Tue, Sep 15, 2026	+0	+0	0
Wed, Sep 16, 2026	+0	+0	0
Thu, Sep 17, 2026	+0	+0	0
Fri, Sep 18, 2026	+0	+0	0
Sat, Sep 19, 2026	+0	+0	0
Sun, Sep 20, 2026	+0	+0	0
Mon, Sep 21, 2026	+0	+0	0
Tue, Sep 22, 2026	+0	+0	0
Wed, Sep 23, 2026	+0	+0	0
Thu, Sep 24, 2026	+0	+0	0
Fri, Sep 25, 2026	+0	+0	0
Sat, Sep 26, 2026	+0	+0	0
Sun, Sep 27, 2026	+0	+0	0
Mon, Sep 28, 2026	+0	+0	0
Tue, Sep 29, 2026	+0	+0	0
Wed, Sep 30, 2026	+0	+0	0
Thu, Oct 1, 2026	+0	+0	0
Fri, Oct 2, 2026	+0	+0	0
Sat, Oct 3, 2026	+0	+0	0
Sun, Oct 4, 2026	+0	+0	0
Mon, Oct 5, 2026	+0	+0	0
Tue, Oct 6, 2026	+0	+0	0
Wed, Oct 7, 2026	+0	+0	0
Thu, Oct 8, 2026	+0	+0	0
Fri, Oct 9, 2026	+0	+0	0
Sat, Oct 10, 2026	+0	+0	0
Sun, Oct 11, 2026	+0	+0	0
Mon, Oct 12, 2026	+0	+0	0
Tue, Oct 13, 2026	+1	+0	0
Wed, Oct 14, 2026	+0	+0	0
Thu, Oct 15, 2026	+0	+0	0
Fri, Oct 16, 2026	+0	+0	0
Sat, Oct 17, 2026	+0	+0	0
Sun, Oct 18, 2026	+0	+0	0
Mon, Oct 19, 2026	+0	+0	0
Tue, Oct 20, 2026	+0	+0	0
Wed, Oct 21, 2026	+0	+0	0
Thu, Oct 22, 2026	+0	+0	0
Fri, Oct 23, 2026	+0	+0	0
Sat, Oct 24, 2026	+0	+0	0
Sun, Oct 25, 2026	+0	+0	0
Mon, Oct 26, 2026	+0	+0	0
Tue, Oct 27, 2026	+0	+0	0
Wed, Oct 28, 2026	+0	+0	0
Thu, Oct 29, 2026	+0	+0	0
Fri, Oct 30, 2026	+0	+0	0
Sat, Oct 31, 2026	+0	+0	0
Sun, Nov 1, 2026	+0	+0	0
Mon, Nov 2, 2026	+0	+0	0
Tue, Nov 3, 2026	+0	+0	0
Wed, Nov 4, 2026	+0	+0	0
Thu, Nov 5, 2026	+0	+0	0
Fri, Nov 6, 2026	+0	+0	0
Total	+2	+0	0

#1 on the list
Rank that day
Not trending

Social mentions

Recent discussions about this repository across the web

Nov 25 posts8 posts
- Idea for the Epstein RAG app: a confidence note on answers. When retrieval only finds weak matches, the answer should say so up front instead of sounding sure.
  Read full on X, posted by @AbhisumatKundu
  @AbhisumatKundu · x.com
- A good RAG system is a librarian, not a biographer. It does not decide what the documents mean. It finds the right pages, shows you the shelf marks, and lets you read.
  Read full on X, posted by @AbhisumatKundu
  @AbhisumatKundu · x.com
- My RAG app starts you with a small slice of the archive on purpose. A modest index with answers you can sanity check beats a giant one you never finish setting up.
  Read full on X, posted by @AbhisumatKundu
  @AbhisumatKundu · x.com
- Why RAG and not a fine tuned model for the Epstein files: the documents are the product. Retrieval keeps the source passages there at answer time, ready to be read and checked, instead of blended…
  Read full on X, posted by @AbhisumatKundu
  @AbhisumatKundu · x.com
- Why court documents as the dataset: public records only matter if people can actually inspect them. A careful tool for reading them, with sources shown for every answer, is worth getting right.
  Read full on X, posted by @AbhisumatKundu
  @AbhisumatKundu · x.com
- Why build in public about a project that reads public documents: the work should be as inspectable as the material. The code, the mistakes, the thinking. Open about the open.
  Read full on X, posted by @AbhisumatKundu
  @AbhisumatKundu · x.com
- The unglamorous part of a RAG pipeline: deciding where a document can be split. Cut in the wrong place and the answer to a question ends up in two pieces that never meet.
  Read full on X, posted by @AbhisumatKundu
  @AbhisumatKundu · x.com
- Why the Epstein RAG indexes text instead of page images: a document you can search word by word beats a picture of one. OCR noise and all, searchable text is what makes real questions possible.
  Read full on X, posted by @AbhisumatKundu
  @AbhisumatKundu · x.com
5 months earlier
May 281 post
- I made a RAG on Epstein Files You can explore names, timelines, mentions, connections, locations, etc. way faster now. Repo: . . . . . . . . . . . #lamansiónvip #EPSTEİN #EPSTEINElites #عيد_الأضحى…
  Read full on X, posted by @AbhisumatKundu
  @AbhisumatKundu · x.com

Ringmast4r/Epstein

Python

Public-records archive and research tools for the DOJ Epstein files, with document indexes, manifests and visualizations. https://ringmast4r.github.io/Epstein/flights.html

537

maxandrews/Epstein-doc-explorer

JavaScript

a graph explorer of the Epstein emails

598115

rhowardstone/Epstein-research

Python

Distilled documents to assist

13517

randallscott25-star/epstein-forensic-finance

HTML

Epstein Financial Forensics Automated forensic financial reconstruction from 1.48 million DOJ EFTA documents + 503K cataloged media items

6713

yung-megafone/Epstein-Files

Public archive index for the DOJ Epstein Files releases (Datasets 1–12), aggregating official downloads, community mirrors, torrent magnets, and integrity verification to ensure long-term accessibility.

589101

cfinke/EpsteOut

Python

See which of your LinkedIn connections appear in the Epstein files.

63842

harvard-lil/olaw

JavaScript

AI + Legal APIs: A Tool-Based Retrieval Augmented Generation Workbench for Legal AI UX Research.

16640

walkerdb/supreme_court_transcripts

Python

8521

AI4CharityPL/kancelaria-lex

Python

Fully local AI for Polish legal case files - zero fabricated citations by construction. Free; please support a Wroclaw animal shelter instead.

598