Chapter V

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, bootstrap size budgets, and the sweep, ingest, and decay jobs
  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: the transactional ingest path that carries machine-local handoffs back into canonical memory
  5. ../automation/openclaw-cron-deep-dive.md: cron scheduling patterns for sweeps and card-refresh jobs

Recipes in this chapter

Bootstrap Files: What Each Agent File Owns

Your agent's personality, safety rails, memory index, and local runbook should not all live in one giant prompt. Split them by job so compaction, cache invalidation, and handoffs stay sane.

Updated 2026-10-17

Claude Code and Codex Memory Handoffs: A Sync Path Into OpenClaw

If you run Claude Code or Codex locally alongside an OpenClaw gateway, you end up with multiple session memories. This guide describes the shared handoff format and ingester that keep OpenClaw as the…

Updated 2026-10-17

Memory Architecture

Updated 2026-10-17

Memory Management & Token Optimization

How to build an agent memory system that does not eat your context window alive. From a slim bootstrap index to semantic search with local embeddings, plus the scheduled jobs that keep the card set…

Updated 2026-10-17

Obsidian Sync Without Conflict Roulette

One vault, one sync layer, one place for automation to write. That is how you get bidirectional cloud sync without waking up to three "conflicted copy" files and a broken notes index.

Updated 2026-10-17

Session JSONL as Memory Source, Not Noise

Transcript logs are an audit trail and a mining seam. Treat them as search-only source material, not something to shovel raw into every prompt.

Updated 2026-10-17

The Evidence Ledger Pipeline: Searchable Work History From Session Logs

Agent sessions are useful until you need to find a decision from six weeks ago. miseledger imports local harness logs into one SQLite archive, indexes them with FTS5, and returns citable evidence…

Updated 2026-10-17