Taylor Moore

Taylor Moore

Building Raptor Data (raptordata.dev).
12 points

About

Former Australian fighter pilot turned software engineer. After retirement from the Air Force at 28, I picked up coding again and started applying my high stakes training to software. I run a software consultancy in Brisbane and spend my nights building developer tools. Raptor started as a solution to my own pain points while making software that uses AI and it represents the solutions I develop internally that I think would benefit the community. When I'm not coding, I'm probably driving too fast or planning my next adventure.

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking

Maker History

  • Raptor
    RaptorHot patch, cache, protect your for LLM API. Built in Rust.
  • 🎉
    Joined Product HuntNovember 19th, 2025

Forums

Taylor Moore

2mo ago

Raptor Data - Protect, cache and hot patch your LLM APIs. Built in Rust.

Rust-powered AI gateway that actually slaps. Semantic caching: 500ms → 8ms. Semantic firewall: catches jailbreaks and malicious actors by intent, not keywords. Hot-patch: fix hallucinations without redeploying. One line change. Free tier. Your API bill will thank you.
Taylor Moore

2mo ago

Stop re-embedding the whole world. Introducing Raptor Data: The "Git" layer for RAG.

We all know the feeling. You build a RAG prototype, it works beautifully, and you deploy it.

Then the "Day 2" reality hits:

  1. The Bill: Your OpenAI/Pinecone costs start creeping up.

  2. The Maintenance: Users update documents. You have to write script after script to handle versions.

  3. The Inefficiency: You realize that when a user fixes a typo in a 500-page contract, your pipeline is re-embedding all 500 pages.

The "Day 2" Problem in RAG: Why don't we treat documents like code?

We ve all built the "Hello World" RAG app. You upload a PDF, chunk it, embed it, and chat with it. It works great.

But what happens on Day 2 when the user uploads Contract_v2.pdf with a single typo fix?

View more