Sloth Social: A Week of Content Without the Blank-Page Panic 🦥
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady . What I Built Every week, I help create social media content for local businesses. Before anything gets published, there’s a familiar list of decisions: what to talk about, which photos to use, what to write, and how to spread it across the week. Sloth Social does the first draft of that work. Enter your…
In the Hacktoberfest Open-Source AI Challenge Week 3, Sloth Social emerges as a tool designed to alleviate the struggles of small business owners and content managers. It generates a week's worth of social media content, from titles and captions to photo descriptions. Users input their business details, audience, tone, and focus, and the app creates a plan for Monday to Sunday.
The app allows editing of titles, captions, and story text directly on the cards, as well as copying individual captions or downloading the entire week's plan. Users can also upload photos and have an open-weight vision model describe them before approval for use. The backend validates the generated data, applies request timeouts, and limits requests to paid AI endpoints.
Open innovation plays a crucial role, as the core functionality lies in open-weight models that interpret photos and transform business briefs into usable content drafts. Although hosted inference is employed due to the limited memory on the developer's Mac, the flexibility afforded by open weights is a valuable aspect of the platform.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
