memory-compactor

memory-compactor

Version: v1.0.0

Temporal conversational memory compactor for your custom mem0-python-server.

What it does

• pulls conversational memories for one user_id
• clusters by time windows
• extracts a compact summary + structured facts per segment (Groq)
• writes summaries verbatim to POST /memories/raw
• appends extracted facts into the summary text (non-empty only)
• preserves full extracted facts in metadata alongside the summary
• injects metadata.created_at so summaries sort correctly without date prefixes
• optionally deletes older intermediate entries (safe budget + dry-run first)

Safety defaults

• dry-run by default (no writes/deletes)
• keeps recent memories (--min-age-days)
• delete cap per run (--max-deletes)

Run

cd /home/lucky/.openclaw/workspace/memory-compactor
python3 compactor.py --user-id main

Apply changes:

python3 compactor.py --user-id main --apply

Environment

The compactor auto-loads .env from this directory (useful for cron). At minimum set:

GROQ_API_KEY=your_key_here

Useful options

• --base-url http://192.168.0.200:8420
• --gap-minutes 45
• --min-age-days 2
• --max-deletes 50
• --segment-max-items 15
• --max-summaries 1 (limit created summaries for testing)
• --skip-ephemeral (skip obvious weather-like chatter)

Next improvements

• semantic clustering (embeddings) beyond time windows
• better resolution detection (state machine)
• reversible snapshots before apply
• cron wrapper + run history logging
• future milestone: capture a pre-change snapshot + restore option before deleting memories