Topic tag
memory
3 guides in the catalogue cover this topic.
- Nº 016 Guardrails for hours-long agent runs Prompting & Context · Deep
Guardrails are the support structure that keeps an hours-long agent run honest: an audit instruction, a memory that survives resets, and fresh-eyed verifiers.
- Nº 017 Give your agent a memory Agents & Automation · Deep
A memory store is a workspace-scoped directory your agent reads and writes with normal file tools, carrying preferences and prior mistakes across sessions.
- Nº 047 Audit what your agent saved to memory Agents & Automation · Practitioner
Theo let Claude Code save memories on its own, then audited them: 45 files, written three times more often than read, most never opened again. How to run the same audit on your machine, the three ways saved memories rot, the ladder that finds a better home for each lesson, and what a harness built to pass the audit looks like.