Give Instructor agents long-term memory with Crowkis

Instructor agents forget the moment a run ends, so every session relearns the user and re-pays for context. Crowkis gives them memory that lasts.

Recall known facts before the model call, store what you learned after. Memory is scoped to (agent, user), ranked by relevance blended with recency, and consolidating, a new fact that contradicts an old one retires it.

mem.remember("prefers email over phone")
mem.recall("how should I contact them?")   # semantic recall

It runs on bundled local models, so you can give Instructor agents memory without shipping conversations to anyone. Runs self-hosted with zero egress, nothing leaves your machine.