Skip to content
Signalcrest
← Back to feed
githubai

okf-agent-memory — Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embed

Adds persistent memory and sub-300µs BM25 search for AI coding agents.

Steady

16

signal score

Cooling

7-day est. ~0

Why this scored 16

every term, weighted
Velocity+0.0 / 40 max

Engagement gained per hour since the last capture, against the fastest item on its own source

Acceleration+11.4 / 25 max

Whether that velocity is itself speeding up, as a per-hour rate

Cross-source spread+0.0 / 25 max

How many independent communities are talking about the same entity

Recency+7.8 / 10 max

Decays to zero over 14 days

Saturation penalty3.6 / 30 max

Subtracted once something is big and old — we rank what's next, not what's peaked

Composite15.5

Weights are hand-tuned, not learned — we're calibrating them against realized trends as history accumulates. On a topic's first sighting there's no previous reading to compare against, so acceleration starts from a neutral prior rather than a measurement, and velocity falls back to engagement over its whole lifetime until a second reading exists. Full methodology

Outlook

low confidence · estimate, not a guarantee

7-day

~0

range 012

14-day

~0

range 014

30-day

~0

range 019

Signal history

7-day window (free)

— — projected trajectory (estimate, not a guarantee)

Entities

okf agent memory
Embed a live signal badge
Signalcrest signal badge
[![Signalcrest signal](https://www.signalcrest.app/api/badge/gh%3A1358571386)](https://www.signalcrest.app/topic/gh%3A1358571386)

Drop this in a README or blog post — it updates automatically as the score moves.