Hacker News: yeag123

New comment by yeag123 in "Ask HN: What are you working on? (May 2026)"

yeag123 — Mon, 11 May 2026 21:52:59 +0000

I've been working on this for about a year and a half, and decided to finally open source it.

I wanted an intelligent document processing SaaS (Document AI, Form Recognizer, the various PDF-to-JSON tools) that you could run on your own hardware.

The interesting bits:

- Three-tier extraction: PyMuPDF for digital PDFs (~50ms), Docling layout-only for scanned-but-readable, Docling+OCR for the rough stuff. Auto-fallback based on extracted character count. - Smart templates use vector similarity (Qdrant) to classify docs, then LLM extraction for fields — no regex, so layout drift doesn't break templates. - Local Ollama or Azure OpenAI, switchable per-user.

Built on top of Cole Medin's local-ai-packaged. Apache 2.0.

https://github.com/nickyeager/fetchtext

New comment by yeag123 in "Ask HN: What Are You Working On? (March 2026)"

yeag123 — Mon, 09 Mar 2026 03:24:05 +0000

I’m working on a tool to automate manual document workflows, specifically for industries like manufacturing where accounting paperwork is still a manual burden.

The workflow: Upload doc → LLM extracts structured data → Generate new doc from template.

It’s API-first, includes webhooks, and is built to be self-hosted/self-provisioned for privacy. Still very much a WIP, but looking for feedback on the feature set and the extraction accuracy.

URL: https://fetchtext.io

New comment by yeag123 in "Ask HN: What are you working on? (February 2026)"

yeag123 — Mon, 09 Feb 2026 01:22:03 +0000

Working on either a self hosted, or self "provisioned" document extraction platform. Trying to make it as flexible as possible, so businesses

I worked with manufacturing companies, and the amount of manual document extraction and manipulation, particularly from accounting documents, was always a large burden.

The goal is upload a document → extract structured fields via LLM → generate new documents from templates. Has a dashboard, with an API, along with a webhook, very much a WIP.

https://fetchtext.io

New comment by yeag123 in "Ask HN: Who is hiring? (October 2019)"

yeag123 — Tue, 01 Oct 2019 16:22:32 +0000

Quoteapro is helping increase the global recycling rate by automating the complex world of scrap metal brokerage. We work with scrap yards and end processors to safely broker containers of recycled material worldwide. We build tools to grow domestic scrap processors network of buyers and automate tasks needed to sell in the export market.

Full job posting: https://angel.co/l/2iPxPG

Ideally you'd be:

-Detail and process oriented -As excited about developing innovative software as we are -Want to be part of a team of creative, confident, thoughtful people who are enthusiastic about increasing the level of global recycling -Comfortable working in an early-stage startup environment where things move extremely fast and requirements change frequently -Comfortable and have previous experience working with distributed team members

If you're interested please email nick@quoteapro.com.

New comment by yeag123 in "Ask HN: Once you have the skills, how do you start getting freelance jobs?"

yeag123 — Sun, 03 Jul 2011 20:57:01 +0000

Odesk sort of does this with feedback ratings: https://www.odesk.com/ I'm sure there are other freelance sites that do as well.

New comment by yeag123 in "Twitter’s Shit Sandwich"

yeag123 — Wed, 18 May 2011 22:49:22 +0000

My understanding is that inorder for a developer to receive an xAuth application key, they have to first be vetted by a representative from twitter. This involves exchanging information regarding a summary of the app, how it will be using the API, etc. So there is still some existing measure of security regarding xAuth, although not nearly as much oauth.

New comment by yeag123 in "Get-shit-done - Easy way to stop distractions"

yeag123 — Wed, 04 May 2011 17:32:03 +0000

A Chrome extension that I use pretty regularly for this sort of thing is Stay Focused: http://goo.gl/gHWFQ