# A little context. A longer memory.

Give products and agents memory they can trace, question, and revisit in time.

Starting with Skynet. Creating a workspace requires pilot enrollment; workspace admins invite everyone else.

## Every memory starts with a source.

An observation arrives with the exact excerpt it came from. Temri keeps the claim, its evidence and its trust status together. New observations are candidates. Verification requires a separate authorized attestation; a stored memory is not automatically true.

## A palace of rooms. Every door granted.

A workspace is the building. Namespaces are its rooms: a product, a project, a shared subject. Explicit grants are the doors, and they decide who can read, contribute, verify, correct and forget. A similar name or a matching email address opens nothing.

## Remember what changed. And when.

Ask what applied at a moment with as_of, and what had been recorded by a moment with known_at. A correction learned today can change what you now know about last month without rewriting what you knew last month.

## Then it sleeps on it.

Every night, Skynet’s agents dream. The cycle rereads committed sources against what was remembered, merges duplicates, promotes candidates that were independently corroborated, lets unconfirmed ones expire after 45 days and retires notes reported as harmful. Nothing is quietly erased: every change is an event you can inspect later.

- Reread committed sources against memories
- Merge duplicate notes
- Promote, expire and retire, then back up

Skynet is Temri’s first integration. Its move onto the shared ledger brings these same rules with it, so a night’s decisions become part of the record rather than a rewrite.

## Recall, inside the lines.

An agent asks and receives a bounded context: only from namespaces it was granted, hydrated from the ledger, with sources, candidate status and both clocks attached. When retrieval is partial or degraded, the answer says so. Memory content is data; it cannot grant new permissions.

## Forget, with a receipt.

Deletion suppresses content from current and historical reads first. A receipt then tracks cleanup of online storage and search, and shows pending work as pending. Copies already exported and external backups have separate retention limits.

## Built for useful recall.

The temporal ledger and private evidence are authoritative. Hybrid search is designed as a rebuildable projection. High-volume events, telemetry and product working state stay in their own stores.

## Continue reading

- [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): Open a Temri workspace, 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, choose a workspace, and verify your client before sharing memory.
- [Privacy, retention and deletion · Temri](https://temri.ai/privacy): What Temri stores, including invitations and member details, which services process it, how access works and what a deletion receipt covers.
- [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)