Lore
Documentation navigation
Docs/Concepts/Disclosure triggers

Disclosure triggers

Write concrete triggers so Lore knows when a memory should appear.

Disclosure says when a memory should appear.

A good disclosure is concrete:

*.txt
Plaintext
When working on Cloudflare Pages deployment, custom domains, build commands, or Pages deploy hooks for LoreHub.

A weak disclosure is vague:

*.txt
Plaintext
Important project info.

Write for future prompts

Disclosure should describe the situation that should trigger the memory, not summarize the memory itself. Include likely tasks, symptoms, product names, and decision areas.

Use this pattern:

*.txt
Plaintext
When [doing task], [touching area], [debugging symptom], or [making decision] for [project/product].

Disclosure vs glossary

FieldUse for
Disclosurewhen the memory should be shown
Glossaryaliases, acronyms, product names, file names, and likely search words
Contentthe actual durable fact, rule, decision, or workflow

Do not stuff every keyword into disclosure. Put aliases and alternate names into glossary terms instead.

What Lore is forLearn which facts, preferences, decisions, and rules should become durable memory.How Lore worksUnderstand the loop: boot context, recall, reading memories, writing durable changes, and review.When to use itDecide which information is worth saving and which short-lived notes can stay out of memory.Memory modelLearn the core memory shape: paths, domains, priority, disclosure, glossary terms, and generated views.