All Topics
All Topics
Technology
Technology
Design
Design
Programming
Programming
Science
Science
News
News
Gaming
Gaming
Entertainment
Entertainment
Business
Business
Finance
Finance
Sports
Sports
Health
Health
Food
Food
Travel
Travel
Art
Art
Music
Music
Books
Books
Education
Education
Politics
Politics
Personal
Personal
No algorithm. No AI slop. No ads. Just RSS. Pro-human. Indie writers. Real journalism. Open web. Chronological. Hand toasted.

Building a Custom AI Agent That Answers Questions by Analyzing GitHub Code

By

j0rg3

2mo ago· 6 min readen

Summary

The article describes building a custom AI agent that answers questions about the author's work by directly analyzing their GitHub code repositories, rather than just rephrasing resume content. The author explains their motivation for creating a more substantive alternative to typical portfolio chatbots, details the technical architecture using a $7/month VPS and IRC server, and discusses security considerations and model selection decisions for this personalized AI assistant.

Key quotes

· 3 pulled
I put an AI agent on a $7/month VPS, connected it to my own IRC server, and pointed it at my GitHub repos. Visitors can ask it about my work and get answers backed by actual code, not rephrased resume text.
Every portfolio site with an AI chatbot does the same thing: feed the resume into a model and let visitors rephrase it. It's a parlor trick. The model can't tell you anything the resume doesn't already say.
I wanted something different. If a hiring manager asks 'how does George handle test coverage?'
Snippet from the RSS feed
A lightweight AI agent that answers questions about my work by reading actual code. Architecture, security, and model selection decisions.

You might also wanna read