# Chapter 7 - Long-term Memory and Consolidation | Loop Engineering

[← All chapters](/ch/)

# Chapter 7 - Layer 2b: Long-term Memory and Consolidation

                Last updated 2026-08-09. This page hosts the cognitive-load grounding behind Chapter 7 and the Alex ACT memory-tier reference implementation that operationalizes the consolidation pattern.

### Companion activity

Take one useful lesson from a recent AI-assisted task and decide whether it belongs in user memory, session memory, repo memory, or an episodic post-mortem.

### What this chapter argues

                Working memory holds the active conversation; durable stores can preserve selected context beyond it. But persistence alone is not learning. A useful memory cycle captures an experience, distills what may generalize, stores it where it can be retrieved, and deliberately reinserts it into later work. The /compact instruction only compresses context within a session. Meditation is the separate consolidation practice that can promote lessons into skills, instructions, and prompts. The lesson becomes operational only when a later task retrieves and uses it successfully.

### Memory tiers (Alex ACT reference implementation)

- User memory - persistent across all workspaces and conversations; loaded into every session.

- Session memory - scoped to the current conversation; cleared at session end.

- Repo memory - scoped to the current workspace; persists with the repository.

- Episodic memory - post-mortems and chronicles in .github/episodic/ .

### Key sources

Chapter 7 cites in the print book: D1, D2, D9, D22, D23, D28, D29, D42, D43. Entries below are the sources this page draws on; some are related literature cited elsewhere in the book rather than in this chapter.

- D17 - Sweller, J. (1988). Cognitive load during problem solving . [doi.org/10.1207/s15516709cog1202_4](https://api.crossref.org/works/10.1207/s15516709cog1202_4)

- D1 - Correa, F., and contributors. (2025-2026). Alex ACT plugin constellation [Computer software collection]. Core: [github.com/fabioc-aloha/Alex_ACT_Core](https://github.com/fabioc-aloha/Alex_ACT_Core) - the current reference implementation of the memory architecture.

### Primary-source links

- [Alex ACT Core repository](https://github.com/fabioc-aloha/Alex_ACT_Core) - the current implementation of the memory-formation discipline and the consolidation cycle.

- [Alex ACT Edition repository](https://github.com/fabioc-aloha/Alex_ACT_Edition) - lineage. See .github/instructions/memory-triggers.instructions.md for the original automatic-formation triggers and .github/skills/meditation/SKILL.md for the consolidation discipline.

- [Sweller (1988), Cognitive load during problem solving](https://api.crossref.org/works/10.1207/s15516709cog1202_4) - the cognitive-load framework that grounds the tiered-memory design choice.

### Chapter contents

- The four memory tiers and what belongs in each.

- Meditation as the sleep-equivalent that crystallizes patterns from session experience into permanent architecture.

- The /compact distinction: compression within a session, not promotion across sessions.

- What this enables: long-running projects where the partner gets better, not just longer.

### Related resources

                The full memory-formation discipline (PII filter, tier selection, when to promote) lives in the Alex ACT repositories linked above. A [fleet, memory, and culture](/fleet/) page on this site covers the multi-instance extension - how lessons propagate across heirs, and why the current constellation distributes them as reviewed releases rather than through a shared memory bus.