Chapter 7 - Layer 2b: Long-term Memory and Consolidation
Loop Engineering by Fabio Correa, the Applied AI foundation volume on working with AI through framing, feedback, verification, memory, and human judgment.
Last updated 2026-10-25. This page hosts the memory-science grounding behind Chapter 7 (Tulving's episodic/semantic separation and Squire's declarative/procedural axis) and the Alex ACT memory-tier reference implementation of the consolidation pattern.
The question this chapter takes up
How does a loop get better between sessions instead of merely longer?
Put it to work
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.
Key sources
Chapter 7 cites in the print book: D1, D2, D9, D22, D23, D28, D29, D42, D43, D86, D87. Entries below are the sources this page draws on; some are related literature cited elsewhere in the book rather than in this chapter.
- D1 - Correa, F., and contributors. (2025-2026). Alex ACT ONE [Computer software collection]. Latest release v0.5.0: github.com/fabioc-aloha/Alex_ACT_ONE - the current reference implementation of the memory architecture, and the successor to the Alex ACT Core / Manager / Plugin Mall constellation.
- D22 - Anthropic. (2025). Effective context engineering for AI agents. anthropic.com/engineering/effective-context-engineering-for-ai-agents
- D28 - Tulving, E. (1972). Episodic and semantic memory. In E. Tulving and W. Donaldson (Eds.), Organization of Memory, pp. 381-403. Academic Press. Print source; no stable DOI.
- D29 - Squire, L. R. (2004). Memory systems of the brain: A brief history and current perspective. doi.org/10.1016/j.nlm.2004.06.005
- D86 - Anthropic. (2026). New in Claude Managed Agents: dreaming, outcomes, and multiagent orchestration. claude.com/blog/new-in-claude-managed-agents
- D87 - Anthropic. (2026). Dreams: Claude Platform Docs. platform.claude.com/docs/en/managed-agents/dreams
Primary-source links
- Alex ACT ONE repository - the current implementation of the memory-formation discipline and the consolidation cycle; the earlier Alex ACT Core repository is its predecessor lineage.
- Alex ACT Edition repository - lineage. See
.github/instructions/memory-triggers.instructions.mdfor the original automatic-formation triggers and.github/skills/meditation/SKILL.mdfor the consolidation discipline. - Anthropic, "Effective context engineering for AI agents" - the chapter's epigraph source: structured note-taking, or agentic memory, persisted outside the context window.
- Squire (2004), Memory systems of the brain - the declarative/procedural axis the chapter applies by analogy to its memory tiers. Tulving (1972) supplies the episodic/semantic separation behind the tiers; it is a print source with no stable DOI.
Dated notes
Dreaming. In May 2026, Anthropic announced Dreaming for Claude Managed Agents, one vendor implementation of the consolidation pattern this chapter describes: a dreaming job reads a memory store and past session transcripts and produces a new, reorganized output store, leaving the input store unchanged. As of October 2026 the feature remains a research preview. Sources: the launch post and the Dreams API documentation, both checked October 2026.
/compact availability. Chapter 7's print text sends readers to this site for /compact cross-surface availability, because that detail has a short half-life. That information is maintained in the Alex ACT ONE plugin, which tracks the surfaces it runs on, so this page points there instead of duplicating it: Alex ACT ONE releases.
Related resources
The full memory-formation discipline (PII filter, tier selection, when to promote) lives in the Alex ACT repositories linked above. The multi-instance extension is Chapter 15's subject: lessons now propagate across instances as reviewed releases in the Alex ACT ONE line, rather than through a shared memory bus.