Knowledge management

How durable knowledge flows: cards, indexes, handoffs, sync. The goal is “future-me can pick up cold.”

Start here

If you want the full memory operating model this repo uses, read in this order:

1. memory-token-optimization.md: physical layout, local embeddings, and why the memory index stays tiny
2. memory-architecture.md: trust hierarchy, stale-claim handling, and the decay loop for cards
3. ../ai-stack/self-improving-agents.md: memory sweep workflow that promotes recent session history into cards and rules
4. claude-code-memory-handoffs.md: scheduled ingest path for machine-local handoffs back into canonical memory
5. ../automation/openclaw-cron-deep-dive.md: cron scheduling patterns for sweeps, ingest jobs, and card-staleness scans