Skip to content
Agenttic
Menu

Pattern · intermediate

Memory Systems Pattern

Patterns for agent memory: working state, summaries, long-term stores, and retrieval with governance.

  • memory
  • state

Memory systems give agents continuity. The pattern is to split stores by lifetime and trust, not dump everything into the prompt.

Pattern blueprint

  1. State object — JSON schema for the run
  2. Episode log — trajectory events
  3. Summarizer — compress old steps
  4. Long-term KV / vector store — durable facts
  5. Retriever — fetch relevant world docs

Write policies

  • What can be written automatically?
  • What needs user approval?
  • What is never stored?

Read policies

  • What is injected every turn vs on demand?
  • How many items max?
  • How do you handle conflicts?

Anti-patterns

  • Infinite chat history as the only memory
  • Storing secrets in model-visible memory
  • Unbounded “remember this” from untrusted text

Deep dive: Agent memory explained.

Frequently asked questions

How should agents store memory?

Use typed working state for control flow, summarized thread history for context, and governed long-term stores with provenance for durable facts—plus RAG for world knowledge.