Observed arrival · 2026-08-29
Echo Memory Wants AI Agents to Remember in Graphs
A temporal, causal-typed memory graph for AI agents, built on PostgreSQL, pgvector, and Apache AGE.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
Field notes
Echo Memory models durable agent memory as a graph in which entities become nodes and facts become typed edges. The page shows a synthetic three-project capture and describes superseded facts remaining traceable through commands such as `echo-memory why <fact_id>`. Its stated storage layer combines PostgreSQL, pgvector, and Apache AGE, while extraction remains the calling agent’s responsibility rather than a server-side LLM step.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
$PaidCommerce or pricing visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
ƒJavaScriptBrowser-side code central
One card from the complete issue