Temporal memory, not a pile of facts
An agent should remember facts—and know which ones stopped being true.
Update facts, recover exact details from raw conversation, and explain every selection and rejection.
- guided tour runs in your browser
- no language model call
- public demo data is hard-deleted after 60 minutes
Instant guided tour
See one memory change end to end
This is an explicitly labelled interactive walkthrough.
Live engine
Run supersession and retrieval on the real service
The public service calls no model provider.
Conversation
Choose a scenario when the engine is ready.
Memory delta
—
Result and reason
—
Developer mode: edit structured events, raw turns, and queries
Last API request and response
nothing yet
Why it works this way
Three boundaries matter more than a feature list
Only explicit replacements close old values
Ambiguity is preserved, not guessed away.
Compression is lossy, so raw turns remain
Exact artifacts remain recoverable from raw turns.
Rejection must be explainable
Selected and rejected candidates both carry reasons.
Evidence and limits
Read the numbers with their constraints
The held-out number is a frozen single shot, not an unseen-set margin over a baseline.
For developers
A local-first memory layer agents can call
REST API
Write, search, timeline, evidence, raw fallback, and capability manifest.
MCP Server
Every tool requires an explicit user_id.
SQLite + FTS5
Single-file raw and structured memory.
Reproducible
Configuration, source, outputs, and audit evidence are fingerprinted.