Observed arrival · 2026-10-20
CORE9: Local Memory for Coding Agents
A local SQLite memory tool that gives coding agents project rules, decisions, and recalled notes using exact-token search.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Developers using AI coding agents on software projects
- Worth noticing
- The homepage separates durable project rules from mistake patterns, append-only decisions, and archival notes retrieved on demand.
Field notes
The memory model distinguishes material that should persist from material that can be fetched when relevant: the page lists 22 invariants, six mistake reflexes, six append-only ADRs, and an archival graph. It says the invariant, reflex, and ADR tiers use roughly 180, 90, and 120 tokens per prompt respectively; these are the site's own figures, not independently verified measurements.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
◎NicheUnusually specific use
One card from the complete issue