Jmail’s new “Jemini” tool is a Gemini Deep Research-like clone for generating cited Epstein reports

Jmail recently launched Jemini, a clone of Gemini’s Deep Research. It generates customized reports on the Jeffrey Epstein scandal. This AI system runs over 50 searches across the Jmail archive and assembles the data into heavily cited articles. You can use this research tool to explore the case in detail.

It was announced officially via a thread on X, and the demo includes a few interesting questions, like how wealthy he was (total net worth) and his ties to China. The thread lists Epstein’s net worth as over $500 Million at his 2019 arrest. It traces several income streams. Epstein allegedly had proposed deals routed through China Life Insurance and CNOOC, and it provides citations for everything.

The interface looks like a clone of Google’s Gemini. For instance, I’ve asked it to display some flight records and passenger manifests in detail. It responded within seconds; these conversations with Jemini can also be shared via a link. Similarly, you can use it to look up purchases or read court documents.

You can check out the launch video in the embed below:

Jmail created Jemini Deep Research as a part of its interactive Epstein archive platform. The team at Jmail is working really fast. Recently, they also shipped a YouTube clone for Epstein videos. The platform has grown so popular that server costs hit $50,000, and the CEO of Vercel stepped in to help.

The main Jmail website presents thousands of released emails and documents in an easy-to-search format. But it’s now part of a bigger platform of app-like clones to make it easier for everyday users to view details and documents on Epstein.

As for Jemini, it was built to handle complex questions. It draws directly from the files. It scans emails, bank records, legal filings, and communications. The output includes citations for every claim, and curious citizens or journalists can apply these reports to find gaps in public evidence.

A few people were disappointed, claiming that it’s a bit short. The team replied, stating that they’re actively working on a version that launches more parallel research. That would support over 250 searches across topics.

The system works on Anthropic’s AI, and users have to enter their own Anthropic API key to activate the feature. All in all, these tools- Jmail, Jefftube, Jwiki, and now Jemini- are very helpful in speeding up research. Without these tools, it would require weeks of manual effort.

We stand out from the tech-media crowd because we break news stories; we mainly bring you stuff that you won’t find anywhere in the mainstream tech media. Our stories have been picked up by some of the world’s most popular websites and media outlets—more info is available here.