memory-engineering

Topics in the source

• Memory Engineering — engineer the forgetting, not just the remembering
• What this does
• The four lenses
• Workflow
• Hard rules
• Scripts
• References and assets
• Provenance

Portability: 4 stdlib scripts, no APIs/LLM calls/network. They measure and gate; you decide. Anyone can give an agent memory: vector store, pipe in the history, retrieve top-k. That works until the history outgrows the context window, the write path costs more than every query it serves, and the store fills with stale state nobody removes. Memory is not a bucket — it is a system with a metabolism. The shift: a storer optimizes what a system remembers; a memory engineer optimizes what it forgets. The problem was never that an agent forgets — it is that it never forgets on purpose. | Lens | Question | The finding that hurts | |---|---|---| | Stanford | What does remembering cost? | Construction energy exceeds total query energy across 300 queries. The tuned half is the smaller half. | | Microsoft | What is worth keeping? | More raw memory can make an agent worse. Keep facts and skills; drop the events. | | Anthropic | Who controls what it keeps? | A wrong memory does not fail once — it persists into every future session that reads it. | | Nvidia | Where does it hit hardware? | It is all KV cache in HBM. Construction is prefill-heavy and stalls the query a user is waiting on. | Step 1

This is an excerpt. Refer to the complete source and its current requirements.