Testing spinner

EigenVibe Local, ordinal feed ranking for Nostr using a persistent "preference manifold"

EigenVibe

A Nostr social client

EigenVibe experiments with a different ranking model for Nostr. Instead of likes/follows or any global signals, each client maintains a small local state (“manifold”) built from its own reaction history. Feed ranking is just a deterministic function of that state. Reactions are 2D vectors (direction + intensity) on a circumplex plane. Over time this forms a per-pubkey distribution. Reaction Compass: Ranking is: alignment (dot product between your manifold and theirs) × engagement rate. So it’s ordinal and pairwise: “aligned with me” rather than “popular”. A few properties that fall out: - No global ordering exists or can be reconstructed - Meaningful aggregation is hard — reactions alone aren’t enough without the full exposure trajectory - Early positions aren’t permanent (indifference dilutes + entropy-based exploration) - Discovery becomes geometric clustering instead of globally gamed popularity contests - Agents can optimize for compatibility, not dominance, and have a track record of their reaction trends. It should behave less like a leader board and more like a local dynamical system.

EigenVibe

A Nostr social client

P.s.. made for browser, phone experience needs a lot of ironing.

EigenVibe – local, ordinal feed ranking using a persistent "preference manifold" EigenVibe experiments with a different ranking model for Nostr. Instead of likes/follows or any global signals, each client maintains a small local state (“manifold”) built from its own reaction history. Feed ranking is just a deterministic function of that state. Reactions are 2D vectors (direction + intensity) on a circumplex plane. Over time this forms a per-pubkey distribution. Ranking is: alignment (dot product between your manifold and theirs) × engagement rate. So it’s ordinal and pairwise: “aligned with me” rather than “popular”. A few properties that fall out: • No global ordering exists or can be reconstructed • Meaningful aggregation is hard — reactions alone aren’t enough without the full exposure trajectory • Early positions aren’t permanent (indifference dilutes + entropy-based exploration) • Discovery becomes geometric clustering instead of globally gamed popularity contests • Agents can optimize for compatibility, not dominance, and have a track record of their reaction trends. It should behave less like a leaderboard and more like a local dynamical system.

EigenVibe

A Nostr social client

Please try EigenVibe - A Nostr client that has a local Circumplex based ranking algo (made for browser at the moment - phone experience not optimal)

EigenVibe

A Nostr social client

Testing EigenVibe

vibe test, 1...2...3

so, hows it vibin?

Somewhat vibee