About LoosePlume
Fediverse intelligence — built in the open.
LoosePlume listens to public Mastodon conversations, clusters them by topic, and distills each cluster into a short structured report. It reads only what anyone with a browser could read; it never logs in, posts, follows, or interacts.
How it works
Every five minutes, LoosePlume polls the public timelines of 15 curated Mastodon instances; trending statuses are pulled separately every thirty minutes. Reply threads are fetched alongside posts. Statuses are embedded with a sentence-transformer and clustered by semantic similarity across instance boundaries. Clusters that clear a wisdom-score threshold — built from reply ratio, boost velocity, thread depth, and cross-instance spread — are fed to a local LLM in a two-stage pipeline (analyst → writer) that produces a title, topic, and summary.
Each reply is independently parsed by an analyzer worker that identifies which real-world entity (company, policy, movement, technology) it references and what stance it takes (support / oppose / neutral). Scores are engagement-weighted — replies with more favourites carry more weight. Those signals roll up into per-entity daily sentiment timelines, viewable under the Sentiment tab.
What it does not do
- Never posts, boosts, follows, or interacts with any account.
- Never reads private or direct messages — only public timelines.
- Every report links back to the original posts on their home instances.
Source coverage
LoosePlume currently covers Mastodon only. Pleroma, Akkoma, and GoToSocial instances were tested but default to requiring authentication for public timeline reads. Their users' content still reaches LoosePlume when it gets boosted or replied to on covered Mastodon instances via ActivityPub federation.