home

epstein-data
Research ▼
🔍 SearchFull-text document search 🤖 Ask AIAI research assistant 🔎 Evidence MapFBI serial resolution 📷 Reverse Image SearchCLIP + face across 614K images 🧑 Find Face BETASearch 29K faces by photo 💻 Run Your OwnDownload & search locally
Explore ▼
📚 Full Text Corpus1.39M docs, 2.77M pages 🌎 Global Heatmap145 countries mentioned 📈 Coverage MapWhat's here 🌌 AtlasSemantic map · 1.29M docs ⚖ Cases53 federal & state cases · per-case briefings 🎤 DepositionsTranscribed audio & video 💬 Hear from the SurvivorsSurvivors in their own words 📖 Cover to Cover-Up24-hour public reading, synced to the video ✉ Wolff–Epstein Emails2,009 messages · 2009–2019
📷 Images92K analyzed photographs 🔍 Multi-DB SearchSearch all databases individually 🗃 All Databases14 searchable databases
Entities Reports
News ▼
📰 NewsCoverage & reporting ⚖ Justice MonitorArrests, charges, lawsuits, firings
Source ▼
🏛 DOJ ProductionOfficial EFTA disclosures 📜 EFTA Law TextPublic Law 119-38 📁 Source Data (GitHub)Open source databases
🌐 Community ResourcesCurated external projects ✉ ContactGeneral · privacy · DMCA · press
❤️ Donate 🎧 Podcast

Research

🔍 Search Documents 🤖 Ask AI 🔎 Evidence Map 📷 Reverse Image Search 🧑 Find Face BETA 💻 Run Your Own Investigator

Explore

📚 Full Text Corpus 🌎 Global Heatmap 📈 Coverage Map 🌌 Atlas ⚖ Cases 🎤 Depositions 💬 Hear from the Survivors 📖 Cover to Cover-Up ✉ Wolff–Epstein Emails 📷 Images 🔍 Multi-DB Search 🗃 All Databases

Entities

👥 Entity Directory

Reports

Browse All Reports 📰 News ⚖ Justice Monitor

Source

🏛 DOJ Production 📜 EFTA Law 📁 Source Data (GitHub) 🌐 Community Resources ✉ Contact
🎧 Podcast & Newsletter ❤️ Donate Privacy Policy
Home / Run Your Own AI Investigator

No Tech Skills Required: Run Your Own Local AI Investigator

Run the same autonomous agentic AI tools that produce the reports on epstein-data.com. Databases, reports, and the methodology that drives the analyses, run locally on your machine. No coding required.

The walkthrough below uses Claude with Claude Code for Desktop. Once set up, you can ask questions in plain English and the AI will search across 2.8 million pages of DOJ documents, cross-reference databases, and cite specific source documents — exactly the infrastructure used to establish and maintain this project.

~17 GB free disk space  ·  Paid Claude subscription
If you have experience with command-line interfaces, you may prefer our CLI walkthrough.
  1. Create a project folder

    Create an empty folder anywhere on your computer. Your Documents directory works fine. Call it whatever you want.

  2. Install Claude

    Download the Claude desktop app from the Claude Code Desktop Quickstart. Install it, open it, and sign in. On Windows, you will also need Git for Windows installed.

  3. Open Code mode

    Click the Code tab at the top right of the Claude window. You will need a paid subscription to Claude to use Claude Code.

  4. Select your folder

    Click the folder button below the chat box and select the folder you created in step 1.

  5. Download the data

    Copy and paste the following prompt. Claude will clone the repositories and download 6+ GB of databases.

    Paste this to Claude
    Hi there! Can you please clone both of the following two repos, download the DB releases, then read CLAUDE.md to set everything up for me here? https://github.com/rhowardstone/Epstein-research-data and https://github.com/rhowardstone/Epstein-research

    Claude will ask permission to run commands. You can approve each one individually, or set it to auto-approve in the selector below the chat box. The first setup takes time — downloading and decompressing 6+ GB of databases will not be instantaneous. Estimate 15–30 minutes.

  6. Orient the AI

    Once the download finishes, paste the following. This tells Claude to read the methodology files and build itself an index of everything available.

    Paste this to Claude
    Please read the CLAUDE.md files, take a look around the repos to orient yourself, then store in your memories enough to index and understand the repository structures, and how we can use this data to search about anything to do with the Epstein files.

    Claude will build itself a table of contents for all available reports and databases. It may ask for a few more permissions.

  7. Start investigating

    You now have an AI Epstein investigator, running agentically on your computer, that can conduct any number of autonomous actions for you. Ask it anything in plain English. It will search across all databases, cross-reference findings, and cite specific EFTA document numbers that you can verify on justice.gov.

Example usage

Have Claude conduct a complete fact check against the corpus for a particular article of your choice (replace the URL below before running):

Paste this to Claude
Hi there, please read the following article and run our fact-checking protocol, writing up a completely sourced article in markdown including a full corpus and external reporting reconciliation of verifiable facts, then render as pretty HTML for us to read. https://substack.com/home/post/p-190252508

Good to know

If something breaks

Start a new chat in the same folder. You don't need to download everything again.

Disk space

The full setup requires approximately 17 GB for all databases and report files.

Subscription

Claude Code requires a paid Claude subscription. It works with whichever model tier your subscription provides.

Keeping up to date

Reports and data are updated frequently. To pull the latest, just ask Claude using the update prompt below.

Update prompt

Paste this whenever you want to pull the latest reports and data:

Hey, can you make sure our local versions are up-to-date with: https://github.com/rhowardstone/Epstein-research-data and https://github.com/rhowardstone/Epstein-research please, including all data releases?

If you have found any of this work helpful, I would greatly appreciate if you would ❤️ buy me a coffee.

Source Data Investigation Reports DOJ EFTA CC BY-NC-SA 4.0 Contact
Powered by Datasette  ·  ❤️ Buy me a coffee

You are leaving epstein-data.com

You are being redirected to an external website not operated by this project. We are not responsible for the content or privacy practices of external sites.

Powered by Datasette