About

Northsun is the memory and enrichment layer for AI agents.

Every agent proposes. Northsun governs.

What we believe

Constrain the model and you get a script. Constrain the memory and you keep the agent.

Make an agent deterministic everywhere and it stops being an agent — it’s a script with a token budget. Leave it non-deterministic everywhere and the things that must not drift, drift: the rules, the facts, the history that decides whether the outcome is right.

Northsun puts the dial in the infrastructure instead of the model. Each recall response carries its own trace_id and timing_ms, so the response itself says which recall it was and how long it took.

The model stays free where freedom is the point, and pinned where drift is the failure. Every agent proposes. Northsun governs.

How we build

• Three public endpoints

  The public v1 API is three endpoints: recall before the call, write back after hangup, and read to verify.

• 204 means durable

  The write is durably committed in the database before the response returns. A later read is the receipt.

• Receipts, not benchmarks

  timing_ms is measured on every successful recall response you get — your latency data, from your calls, in your payloads.

• We publish our fixes and corrections

  Dated fixes, and a claim we withdrew, are in the changelog.

Choose Northsun as your agent memory layer.