cd /news/ai-agents/i-built-a-self-hosted-ai-agent-with-… · home topics ai-agents article
[ARTICLE · art-20621] src=dev.to pub= topic=ai-agents verified=true sentiment=↑ positive

I built a self-hosted AI agent with a 30-min self-improvement loop — here's what I learned

A developer released Hyper Nexus, a self-hosted AI agent built with FastAPI, SQLite, PyTorch, and a vanilla JS WebUI, designed to improve through a 30-minute self-improvement loop. The project, which comprises roughly 60,000 lines of Python code, prioritizes tool execution and state management over the LLM call itself. The developer acknowledged shipping version 0.1.0 without automated tests and is now working on an evaluation harness to measure the agent's actual improvement.

read1 min publishedJun 3, 2026

Six months ago I started building an AI agent I actually wanted to use.

Not another LangChain wrapper — a single, self-hosted system that gets

measurably better the more I work with it.

This week I cut the v0.1.0 release.

What it is

Hyper Nexus is a self-hosted AI agent with:

pip install

.Stack: FastAPI, SQLite, PyTorch, vanilla JS WebUI. ~60K LoC of Python.

Why I built it

When I started this, I thought: why not try to model something close

to how humans actually think? The result isn't fully polished, and

there are real shortcomings — but I'd love feedback so I can keep

improving it. This is going to be an open-source project, and I want

it to grow with the people who use it.

What I learned building it

Lesson 1: The hard part is not the LLM call.** It's everything around

it — tool execution, error recovery, state management, the agent's

"short-term memory" of what it's already tried, the user's long-term

context. The actual prompt is maybe 5% of the code.

Lesson 2: Tests matter even for solo projects.** I shipped v0.1.0

with zero automated tests. I regret this. If you're reading this and

considering the same — don't.

Lesson 3: Don't promise self-improvement you can't measure.** I have

a 30-min heartbeat that does something. Whether it actually makes

the agent better at your task is unmeasured. I'm working on an eval

harness to find out.

What's next

If you try it, please open an issue — that's the only way I can prioritise what actually breaks vs what I think breaks.

Let's make something meaningful.

GitHub: https://github.com/Hsosn/HYPER_NEXUS MIT licensed. PRs welcome.

── more in #ai-agents 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/i-built-a-self-hoste…] indexed:0 read:1min 2026-06-03 ·