# Memory deserves clear boundaries.

Effective October 3, 2026. This notice describes Temri’s admin-managed pilot and its data handling boundaries.

## What is stored

Temri stores workspace identity links and membership, namespace grants, memory revisions, evidence excerpts and source locators, verification and correction records, and content-free operation receipts. Bounded usage records identify product, workspace and operation dimensions. Billing is deferred.

## Who can access it

Clerk authenticates accounts. Temri links identities by issuer and subject, then checks current membership and namespace capabilities. Signing in, using a matching email or belonging to another application’s organization does not grant a workspace. Treat granted read access as permission to copy returned content.

## Services involved

- Cloudflare hosts the service, workspace directory, temporal ledger and private evidence storage
- Clerk processes account authentication and session information
- When hybrid search is enabled, turbopuffer processes the rebuildable search projection and embedding processing is part of the search path; hybrid search is disabled in the initial development configuration
- Your agent or application receives content you authorize it to retrieve, under that provider’s separate terms

## Retention and deletion

Memory and evidence remain available until an authorized deletion or an explicitly configured retention policy applies. No universal automatic retention period is promised in this pilot. A correction preserves revision history; it is not deletion.

Deletion suppresses affected content from current and historical online reads first. The operation receipt tracks cleanup of ledger payloads, evidence storage and search sinks. Pending cleanup is shown as pending, not complete. Receipts retain no deleted private text.

Temri cannot erase copies already exported to an agent, product, source repository or external backup. Source and backup retention are separate from online sink cleanup. A removed Git file does not prove historical blob erasure. Confirm those retention obligations with your pilot administrator before storing sensitive information.

## Public site and private workspace

Customer memories and evidence are excluded from public documentation, SEO jobs, social images and readiness screenshots. The private workspace uses no session replay or acquisition analytics carrying private identifiers. Sign-out clears displayed private state.

## Pilot requests and changes

Ask the administrator who granted your pilot access about membership, data access, retention or deletion. Do not publish private data in public issues. This pilot does not promise a compliance certification, data residency commitment, perfect erasure or uninterrupted availability. Material policy changes will update this notice before broader enrollment.

## 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.
- [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)