Persistent memory across sessions — recall, store, share, audit decisions, snapshots, and version history
Persistent memory that survives across sessions. Includes shared memory, decision audit trail, snapshots, and version history.
Recall — load relevant context from past conversations:
python3 {baseDir}/scripts/memory.py recall "<USER_MESSAGE>"
Turn — store the exchange after responding:
python3 {baseDir}/scripts/memory.py turn "<USER_MESSAGE>" "<YOUR_RESPONSE>"
Search — find specific memories:
python3 {baseDir}/scripts/memory.py search "<QUERY>"
Share — write data to a named space other agents can read:
python3 {baseDir}/scripts/memory.py share "<SPACE_NAME>" "<KEY>" "<VALUE>"
Read shared — read all data from a shared space:
python3 {baseDir}/scripts/memory.py read_shared "<SPACE_NAME>"
Decide — log a decision with reasoning for accountability:
python3 {baseDir}/scripts/memory.py decide "<DECISION>" "<REASONING>" "<CONTEXT_DESCRIPTION>"
DECISION should be "allow", "deny", or "escalate". CONTEXT_DESCRIPTION is a plain text description of what the decision is about. Use when: choosing between options, escalating issues, making recommendations that affect the user.
Snapshot — save current memory state:
python3 {baseDir}/scripts/memory.py snapshot
Restore — roll back to a previous snapshot:
python3 {baseDir}/scripts/memory.py restore "<SNAPSHOT_LABEL>"
History — see how a value changed over time:
python3 {baseDir}/scripts/memory.py history "<KEY>"
recall on the first message of a session, or when past context would helpturn after meaningful exchanges — skip for "hi", "ok", "thanks"decide when making choices that should be auditableshare when the user wants data available to other agentssnapshot before risky operations, restore if something goes wrong