Enrichment

Enrichment is the background process that turns raw events into the summaries and search index that make memory useful.

What it does

A worker watches for new events and schedules enrichment jobs:

• Turn summaries from individual exchanges.
• Session and chat summaries rolled up from their children.
• Trace summaries for tool-use sequences.

Summaries are produced by a language model -- routed through the same proxy, so the model and credentials are resolved per tenant. The default enrichment model is a fast, inexpensive Gemini model; you can override it per tenant under Settings -> Processing.

Indexing

After summaries are written, the indexing pass embeds them and pushes them to the search index (see Hybrid search).

Cost controls

Enrichment is designed to be economical:

• Events are de-duplicated, so replayed history isn't re-summarized.
• The worker applies quota-aware backoff: when a provider rate-limits or hits a daily cap, it pauses rather than burning spend on retries.
• You can disable enrichment per tenant if you only want capture + raw recall.

Configuring

Choose your enrichment and embedding models, and toggle processing, from Settings -> Processing in the dashboard.