NAVis · My Weekend-Built Personal AI Agent

a little helper that lives on a server I rent, thinks with a model, and runs whether I'm watching or not

story version · for a recruiter, a PM peer, a curious friend
ME laptop · phone I reach it by: • opening a chat window • messaging it on Telegram • it reaches me on its own (e.g. 4am daily check-in) "can you do X?" "here's X, and I also saved it." NAVis a small AI agent on a server I rent it THINKS uses a language model to reason it ACTS reads email, messages me, runs skills it REMEMBERS writes things down in plain-text files the same loop whether I'm in the chat or asleep WHAT IT CAN REACH my email the web Telegram a language model WHAT MAKES IT INTERESTING 1. It runs on its own On my server, not a SaaS. It keeps running whether my laptop is open or not. 2. Its brain is in plain files Who it is, what it knows about me, what it remembers: all readable text files I own. 3. It's a pattern, not a product The same five pieces — model, files, shell, schedule — build any autonomous system. I built this so I could understand the architecture from the inside, not just use it.

story · What I Built

The one-line version

I built a small AI agent called NAVis that lives on a server I rent. I can chat with it in a browser, message it on Telegram, or let it reach out to me on a schedule — and it remembers everything in plain-text files I own.

What it actually does

When I talk to it, it reads a small set of files that describe who it is and what it knows about me, uses a language model to figure out what to do, takes action (maybe reading my email, searching the web, sending me a Telegram message), and writes down anything worth remembering. Same loop whether I kicked it off or a schedule did.

Why I built it

Marc Andreessen described an agent as LLM + Shell + Filesystem + Markdown + Cron. A model to reason, a shell to act, a filesystem to remember, markdown as a format both humans and models can read, and cron so it runs whether I'm watching or not. Every piece already existed. The combination is what makes it autonomous. I wanted to understand that combination from the inside.

What it taught me

The agent sometimes claims it did something without actually doing it — "I wrote the file" when nothing got written. That's a property of how language models work, not a bug. The lesson generalises: trust what the filesystem says, not what the agent says. That shapes how I think about any AI system that takes actions.

Where it leads

NAVis is the first of two systems I built on the same primitives. The second is PRACtis — an autonomous pipeline that tracks how AI practitioners think, runs every Monday without me touching it, and publishes a weekly digest. Same five pieces, different purpose. That's the architectural point: it's a pattern, not a product.