AI & Agentic Systems · Level 3 · artefact
Artefact — Memory in two layers · Engram and Headroom
Memory is split by purpose — Engram stores what should persist and Headroom keeps what should not persist out of the context window.
- Engram
- Headroom
- SQLite
- JEV
Artefact — Memory in two layers · Engram and Headroom
Status: stub. A redacted session handoff and a before-and-after context measurement land in Phase 7.
What the artefact is
Engram is local-first storage for curated summaries, decisions, prompts and session handoffs in SQLite, so a conversation can be resumed in any project; it is integrated with JEV for fast compaction. Headroom is token control: it strips, cleanses and analyses code and logs before they reach the model, compressing rather than truncating.
What it proves
Two distinct problems recognised as two — persistence and window economy — instead of one tool asked to do both.
When it is delivered
Phase 7. Both tools are part of Sam’s own workflow; they are deliberately not part of the public assistant, which is stateless by decision (see reference/decisions.md D11).
Artefacts behind this page
- Artefact — Guardrails · hooks in the model path running
- Artefact — House AI hub service topology running
- Artefact — Model routing and cost control running
- Artefact — Paperclip and n8n pipelines in production running
- Artefact — Retrieval corpus and query graph running
- Artefact — Voice pipeline · speech in and speech out running