What we shipped.

A new POST /v1/embeddings endpoint generates text embeddings from EU-sovereign or external models, OpenAI-compatible and metered per input token. See the embeddings guide for the full request shape and available models.

Connect Claude, or any MCP client, to your governed memory and knowledge over OAuth. The recall, remember, forget, and knowledge.search tools run scoped to one organization, metered, audited, and EU-resident. Read more.

An exact and semantic response cache for deterministic requests, configurable per organization. Repeat and near-repeat prompts return instantly and stop spending on inference.

Retrieval now supports multiple walled-off collections per organization. Pass a collection by slug on the request and keep indexes cleanly separated.

A trace explorer and metrics dashboards: span-level traces, percentiles, and per-model breakdowns, all EU-resident and metadata-only.

Full OpenAI request-body parity including tools and function calling, covered by the PII firewall and guard across every provider.