Back to AI/ML Overview
🗄️ Knowledge Site · Memory for Agentic Software · Facts, State, Recovery

Memory EngineeringMemory is what you keep. A checkpoint is where you stopped.

A model call remembers nothing. Everything an agent seems to remember, somebody stored on purpose: a fact for a later conversation, or the state of a run that must survive a crash. Those are two different jobs with two different failure modes. This site starts from one request that forgets and climbs, one idea at a time, to memory kinds, stores, run identity, checkpoints, safe resume, write policy, retrieval, shared memory, security and tests, asking one question at each step: who wrote this down, and who is allowed to rely on it?

🎯The problem

An underwriting run fails right after it fetched the roof assessment. Start over and the provider is called twice and the underwriter may see two recommendations. Resume carelessly and the run trusts a stale fact. Memory engineering keeps the facts an agent should remember apart from the saved state that lets a run continue, and makes both safe to rely on.

🔑The question every page asks
Who wrote this down, and who is allowed to rely on it? Each chapter stores, resumes or forgets something in the same synthetic insurance run, and a recovery grid of 80 crash-and-resume runs proves the result.

🗺️What is inside

Kinds of memory and where they live

Working, episodic, semantic and procedural memory; history against summaries against facts; files, relational tables, documents and .

Run identity and checkpoints

run_id, trace_id, attempt and task ids kept apart; state machines, workflow checkpoints, event sourcing and where replay stops.

Resume without side effects twice

Idempotency keys, the transactional outbox, compensation and deduplication, so a resumed run never repeats a write that already happened.

Write policy, retrieval and security

What may be written, with which provenance and expiry; ranking by relevance and recency; shared memory, tenants, personal data and deletion.

🖱️How to read it

  • New to agent memory: read in order. Each chapter starts in plain English with one tiny example.
  • Experienced: jump to checkpoints, resume, the outbox or the insurance lab. The rigorous part sits in folded blocks.
  • Fourteen interactive labs, among them an interrupt-and-resume simulator, each with a plain table next to it.
  • The example is synthetic and its agent is a scripted stand-in. Results show how the mechanism works, not how good any model is.