Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

OSS AI agent that indexes and searches the Epstein files

Details

External ID
46611348
Source
HN
Company
—
Product
OSS AI agent that indexes and searches the Epstein files
Website domain
trynia.ai
Launched
Jan. 14, 2026
Cohort
—
Upvotes
211
Upvotes percentile
0.9631093544137023
Tags
—
Fetched at
Sept. 7, 2026, 9:25 p.m.
Updated at
Sept. 7, 2026, 9:25 p.m.

Description

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 searchDiscussion around these files is often fragmented. This makes it possible to explore the primary sources directly and verify claims without manually digging through thousands of pages.Happy to answer questions or go into technical details.Code: https://github.com/nozomio-labs/nia-epstein-ai

Enrichment

Theme
searchable public records and archives
Vertical
Horizontal
Function
Search & retrieval
Audience
B2C
AI stance
AI-native
Project type
Hobby / open-source project
Normalized one-liner
ai agent search for epstein files
Manually corrected
False

Could you build this?

Yes This is a classic RAG (Retrieval-Augmented Generation) pipeline parsing document dumps, generating vector embeddings, and running hybrid search via an off-the-shelf vector database. These workflows are textbook use cases for AI-assisted vibe coding.

Discussion

20 comments analyzed.

Competitors mentioned: epsteinos.net, OpenAI models, Gemini, Claude, Grok

Concerns raised: Censorship and content filtering limitations, Regional differences in model behavior, AI-generated harmful content (CSAM) implications, Pricing and cost compared to alternatives, Model speed and performance

Feature requests: Less censored/more uncensored responses, Better handling of political/controversial topics, Consistent behavior across regions

Competitors

Other products that read as similar to this one — 101 launches clear the similarity bar, closest 8 shown.

Attention rank: #6 of 102 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 75 days after the earliest competitor.

Other launches for this product