Skip to content
All projects

Open source collective

Phoveus Lab

AI products, shipped free and open source.

A small group building AI products around one question: what is still harder than it needs to be? Everything ships free and open source. The first product out is Admission OPS, because university admissions is one of the most paperwork heavy moments in a person's life and most of it is deadline tracking that software should have absorbed years ago.

Role
I build here with a few other people. Nobody takes a title.
Period
2026, ongoing
Status
Admission OPS live, more incubating
Built with
Next.js · TypeScript · Python · LLM orchestration · Postgres
1
product liveAdmission OPS
Free
and open source, permanently
Hub and spokes
shared model, eval and design layer

The problem

What was actually wrong

Applying to university is a logistics problem wearing the costume of an academic one. Requirements differ per institution, deadlines are scattered across a dozen portals, documents get re-requested in slightly different formats, and the cost of missing one line item is a lost year.

Most people run it out of a spreadsheet and forty browser tabs. The work is not hard, it is relentless and unforgiving, which is exactly the shape of thing that should be handed to a machine.

Approach

What I built

Admission OPS parses documents, deadlines and requirements automatically, tracks every milestone on one timeline, and surfaces the next action before it becomes urgent. It reasons over a real profile to suggest where to apply and what to strengthen, and gives the applicant and everyone helping them a single view of where each application stands.

The lab runs as a hub with spokes. Model infrastructure, evaluation tooling, the design system and data pipelines are built once, so each new product starts where the last one finished rather than from scratch.

I am one of a few people doing this in our own time, because we think useful software should not be gated behind a price. Nothing here is a company and none of us take a title.

Next

FaceTube

Peer to peer video with emotion inference in the browser.