I Built a Faceless Video Factory That Remembers Which Content Pays
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built Faceless Video Factory is a local-first pipeline that turns a single topic into a finished vertical short-form video — and, unlike every other tool I tried, it remembers which content actually made money and steers the next video toward it. The problem: my side hustle is faceless short-form video,…
This submission is for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle. The inventor built a faceless video factory that learns which content pays. Unlike all other tools, this one remembers past outcomes and uses that information to steer the next video toward the most profitable topic. The pipeline takes a single topic and turns it into a finished vertical short-form video, tracking revenue along the way.
It uses Backboard's persistent memory and RAG, local inference with a Qwen model, Backboard's open memory tier, FFmpeg for rendering, and espeak-ng for on-device narration. The brain recalls earnings data from Backboard memory to choose the next topic, and after each video, the outcome is written back to memory for future reference. The code is MIT licensed and publicly available on GitHub.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
