Ac Agent Memory And Recall

Memory that outlives the session: what an agent writes down at the end of its work, how notes are shaped so recall works, promoting working knowledge to permanent memory, superseding facts instead of appending contradictions, staleness and dated facts, and the written memory record. It teaches the discipline of persistent agent memory; it never predicts what a model will remember in-context and never recommends a storage product. Use when asking "agent memory", "persistent memory", "memory file", "what should the agent remember", "note anatomy", "promote to memory", "supersede stale facts", "knowledge cleanup", "recall between sessions", "memory record", "note-taking system for agents". Not for in-window context budgeting and compaction (ac-prompt-engineer), not for vector index mechanics and chunking (ac-retrieval-and-vector-systems), not for mid-task session handoff checkpoints (ac-handoff).

jiayaoqijia Updated 81 repo stars

File contents

jiayaoqijia/cryptoskill commit aa92f40305

Frequently asked questions

npx get-skill add jiayaoqijia/ac-agent-memory-and-recall