1. Ingestion — Every 30 minutes, we poll Lemmy instances for new posts and comments from the communities we follow. Posts are deduplicated so we never store the same content twice. We also fetch trending older posts so popular discussions aren't missed.

2. Processing — New posts are converted into vector embeddings. Similar posts are clustered together using cosine similarity. Each cluster is scored based on comment depth, upvote velocity, cross-instance coverage, and engagement volume.

3. Synthesis — Clusters that score above the quality threshold go through a two-stage AI pipeline:

• The Analyst reads all posts and comments in the cluster and identifies what people agree on, where they disagree, and what the most surprising takes are
• The Writer produces a direct, no-nonsense summary reporting what the community is saying — the key points and the sharpest arguments from both sides

4. Dashboard — Reports are published here, browsable by discovery date, post date, popularity, or by topic. Each report links back to the original Lemmy discussions so you can dive into the source material.

Most news aggregators show you headlines. Plymorph shows you the vibe — what real people actually think about those headlines. When the same story is discussed on lemmy.world, lemmy.ml, hexbear.net, and lemmy.ca, we synthesize all those perspectives into one report. You get the consensus, the backlash, the sharp takes, and the weird outlier opinions — all in three paragraphs.

All data is sourced from public Lemmy API endpoints. We don't scrape, we don't require authentication, and we don't store any user profiles or PII beyond public author names. Every report shows its source discussions with direct links back to the original threads.