exopriors.com

Data

public corpus search with vector embeddings

SHOW HN2025

Legend

exopriors.com

Use Claude Code to Query 600 GB Indexes over Hacker News, ArXiv, etc.

exopriors.com

#vector search#text-to-sql#semantic search#embeddings#hacker news search

397points
142comments
#118of 3,837 in 2025
Top 4%of 2025 by points

How HN took it

MixedNo clear lean

15 positive, 22 neutral or asking, 0 mixed, 11 critical, out of 48 comments about the project. Thread score +0.13.

Idea: 10 for, 2 againstPerformance: 1 for, 3 againstExecution: 0 for, 2 againstPrivacy: 0 for, 2 againstDesign: 2 for, 0 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Generating SQL rather than a black-box chatbot is a good research approach

    From 1 comment
    • I like that this relies on generating SQL rather than just being a black-box chat bot. It feels like the right way to use LLMs for research: as a translator from natural language…
      barishnamazov on HN
  • Onboarding flow is simple and nice

    From 1 comment
    • The quick setup is cool! I’ve not seen this onboarding flow for other tools, and I quite like its simplicity.
      m11a on HN

Objections

  • Security risk from network egress and pasted embedded API key

    From 3 comments
    • Not a software engineer. Isnt allowing network egress a security risk? exopriors.com is not an established domain or brand that warrants the trust its asking
      dcreater on HN
    • Nice, but would you consider open-sourcing it? I (and I assume others) are not keen on sharing my API keys with a 3rd party.
      mentalgear on HN
    • Guys, you obviously cannot suggest that —dangerously-skip-permissions is ok here, especially in the same paragraph as “even if you are not a software engineer”. This is untrusted…
      theptip on HN
  • Claims of state of the art and AGI are hyperbolic

    From 3 comments
    • > a state-of-the-art research tool over Hacker News, arXiv, LessWrong, and dozens what makes this state of the art?
      kburman on HN
    • "intelligence explosion", "are essentially AGI at this point", "ARBITRARY SQL + VECTOR ALGEBRA" etc. Casual use of hyperbole and technical jargon. my charlatan radar is going off.
      dcreater on HN
    • lots of highfalutin language trying to make something thats pretty hand wavy look like it's not. Where are the benchmarks? The "vector algebra" framing with @X + @Y - @Z is a…
      bfeynman on HN
  • Vector algebra does not form meaningful algebra over concepts

    From 1 comment
    • lots of highfalutin language trying to make something thats pretty hand wavy look like it's not. Where are the benchmarks? The "vector algebra" framing with @X + @Y - @Z is a…
      bfeynman on HN

Requests

  • Open source the project

    From 3 comments
    • Nice, but would you consider open-sourcing it? I (and I assume others) are not keen on sharing my API keys with a 3rd party.
      mentalgear on HN
    • Seems very cool, but IMO you’d be better off doing an open source version and then hosted SAAS.
      bugglebeetle on HN
    • Really useful currently working on a autonomous academic research system [1] and thinking about integrating this. Currently using custom prompt + Edison Scientific API. Any plans…
      7777777phil on HN
  • Support self-hosted smaller models

    From 1 comment
    • That's just not a good use of my Claude plan. If you can make it so a self-hosted Lllama or Qwen 7B can query it, then that's something.
      nineteen999 on HN
  • Add pubmed or supplementary material coverage

    From 2 comments
    • just a recommendation, pubmed is free and not limited to preprints
      biophysboy on HN
    • This may exist already, but I'd like to find a way to query 'Supplementary Material' in biomedical research papers for genes / proteins or even biological processes. As it is,…
      bonsai_spool on HN

Questions

  • How are alerts implemented?

    From 1 comment
  • How does vector search handle semantic bleeding across datasets?

    From 1 comment
    • I like that this relies on generating SQL rather than just being a black-box chat bot. It feels like the right way to use LLMs for research: as a translator from natural language…
      barishnamazov on HN

Alternatives named

  • Google BigQuery

    From 1 comment
    • in the direction of "empowering the public with new capabilities they didn't have before", Scry offers, with the copy and paste of a prompt and talking with an agent: 1) Full…
      Xyra on HN
  • MCP servers

    From 1 comment
    • What’s the benefit of manually pasting a massive prompt and enable egress to make queries over http vs just using MCP?
      Too on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/46442245)