# A memory is a record. Keep its story.

From the first observation to the next correction, each step leaves the context you need to understand it.

## 1. Choose a boundary

Select a workspace you belong to and create a namespace for a product, project or shared subject. Namespace permissions follow explicit parent nodes. Similar names do not imply shared access.

## 2. Keep the source

Record an exact excerpt and its source locator as evidence. Evidence is immutable and content-addressed. Copying an excerpt does not turn one source into two independent sources.

## 3. Save an observation

Write a claim, episode or procedure as a candidate. Add evidence references and the time from which it applies. Recorded time comes from the server. Verify only when you have the authority and evidence to attest to the exact claim.

## 4. Recall with two clocks

Use as_of for when it applied and known_at for what had been recorded. Current recall uses the server’s current time by default. Search results are authorized and hydrated from the ledger before their content is returned.

## 5. Correct without losing the past

A correction checks the expected generation, preserves unaffected intervals and invalidates dependent memories. The earlier recorded view remains available unless the content has been purged.

## 6. Forget with a receipt

Deletion suppresses affected content from current and historical reads first. A receipt tracks cleanup of online storage and search sinks. External copies and backups have separate retention limits; the receipt is not proof that every copy everywhere has vanished.

> The illustration on the homepage is synthetic. It explains the clocks and never reads or writes a workspace.

## Continue reading

- [Temri · Memory with a sense of time](https://temri.ai/): Shared temporal memory for products and agents. Keep source-backed facts in protected namespaces and distinguish what applied then from what was known then.
- [Developer documentation · Temri](https://temri.ai/docs): Connect to Temri through REST and MCP. Learn workspace permissions, evidence, temporal queries and bounded retrieval.
- [Create your first memory · Temri quickstart](https://temri.ai/docs/quickstart): Use an enrolled Temri workspace to create a namespace, record evidence, save a candidate and recall it with explicit time controls.
- [The two clocks · Temri temporal semantics](https://temri.ai/docs/temporal): Understand as_of and known_at, half-open intervals, correction history, server-owned recorded time and deletion suppression.
- [REST API · Temri developer docs](https://temri.ai/docs/api): Authenticate Temri REST requests, select authorized workspaces, use mutation idempotency and handle pending, denied and partial results.
- [Connect an agent · Temri MCP docs](https://temri.ai/docs/mcp): Connect to Temri’s authenticated MCP resource with narrowed scopes. Discover operations and verify your client before sharing memory.
- [Privacy, retention and deletion · Temri](https://temri.ai/privacy): What Temri stores, which services process it, how namespace access works and what a deletion receipt does and does not cover.
- [Pilot terms · Temri](https://temri.ai/terms): Terms for Temri’s admin-managed pilot, responsible use, source-backed claims, service limitations and account access.

[OpenAPI](https://temri.ai/openapi.json) · [Workspace](https://temri.ai/app)