# Shared context. Shared responsibility.

Effective October 3, 2026. These terms cover Temri’s admin-managed pilot; billing is deferred.

## Pilot access

Use Temri only through an account or installation authorized by your pilot administrator. You are responsible for credentials and the namespace grants you issue. Do not bypass permissions or access another workspace. Access may be revoked for abuse or pilot administration.

## Your content

Submit only content you have permission to store and share. You retain your rights in your content and permit the processing needed to store, retrieve, correct and delete it. Do not upload provider credentials or material that violates others’ rights.

## Evidence is not a guarantee

A candidate is an observation. An asserted or verified record reflects an authorized attestation, not a promise that the world is correct or unchanging. Evaluate evidence and uncertainty before relying on returned context. You remain responsible for decisions made by your product or agent.

## Pilot limitations

The pilot is provided as available, without a promised availability, accuracy or quality level. Interfaces and limits can change. Maintain your own source records and recovery plan. Do not use this pilot as the sole basis for safety-critical, medical, legal or financial decisions.

## Corrections and deletion

Correction preserves temporal history. Deletion suppresses affected online reads and tracks sink cleanup through a receipt; it cannot erase external copies or backups controlled by others. Read the privacy notice before storing sensitive content.

## Questions and updates

Contact the administrator who granted access for pilot questions and account requests. These terms are limited to the current pilot and will be reviewed before broader customer enrollment or paid plans.

## 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.
- [How Temri works · From evidence to memory](https://temri.ai/how-it-works): Follow a memory from its source to a candidate, verification, historical retrieval, correction and deletion receipt.
- [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.

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