remember when you have new turns to store. Call recall when you have a question and want the best matches back.
Most of the time you work with turns. Tex also builds observations and entities in the background. A write usually becomes recallable in about 150 ms. The richer memory layers continue after that.
Layers
Turns
Raw lines: who said what, when.
Observations
Small facts inferred from turns, such as dietary constraints or locations.
Entities
People, places, and organizations that show up across observations.
Writes
When you callremember, Tex first saves the turn in active memory. That is the fast path. Then it keeps building richer memory in the background.
Fast path
Your code gets control back quickly. New turns are usually recallable within about 150 ms.Background
Observations, entities, and timeline work continue after the response. They improve recall on later questions. You do not need the background work to finish before the next user message. The latest turn can still be enough.Reads
For reads, pass a natural-languageq and the scope to search. Tex retrieves candidates, ranks them, and returns hits with a confidence score.
Over HTTP, POST /recall takes q, scope, and options like mode, top_k, and include_timeline. The response includes ranked turns, observations, entities, token usage, and an optional timeline string. The full request and response fields are in Recall memory.
Tune mode, top_k, and confidence behavior in Recall and ranking.
One example turn
| Layer | What you get |
|---|---|
| Turn | Full text, role, timestamp, dedupe metadata |
| Observations | Facts like current city, previous city, employer |
| Entities | Typed nodes (person, place, org) wired together |
| Temporal | Events on a lightweight timeline |
BYO facts
Let Tex extract facts for you. If you already have facts from your own system, attach them toremember. See conversations.remember.
Next: scopes and multi-tenancy
How
org_id, user_id, and session_id isolate memory.