Memory that scales
with your agents.

One atomic fact stored in your cloud memory: a single statement the agent has decided is worth remembering. A 20-message conversation typically produces 10 to 30 memories, depending on how much new information the agent extracts. The dashboard shows the count in real time.

One read call: GET /v1/memories, POST /v1/memories/search, GET /v1/context, GET /v1/facts, GET /v1/users, or equivalent SDK methods (korely.search(), korely.get_context(), korely.get_facts()). Write calls (POST /v1/memories, PATCH /v1/memories/{id}) count only against the memories quota, not queries. Reads are retrieval, not generation: no generative model runs on the read path, which is why read quotas are an order of magnitude more generous than write quotas. The monthly counter resets the 1st of every month at UTC midnight.

No. An agent is a namespace for one of YOUR agent applications: your support chatbot is one agent, your sales copilot is another. The end users those agents serve are unlimited on every tier. Each memory and query is scoped to an end user via user_id, so a single support-bot agent can remember thousands of distinct customers. A user_id is just a label. An app with 10 users and one with 100,000 making the same API calls pay the same. What counts against quotas is total volume: memories written and queries made.

Soft cap with a 10% buffer, then rate-limited (429 response). You get an email alert at 80% of any quota (memories, queries, or agents) so you can decide whether to upgrade or trim before you hit the wall. We never auto-upgrade and we never bill overage.

Not on the public Hobby/Developer/Team/Scale tiers. The agent memory product (REST API, SDK, graph, vector store) ships hosted only. If your environment requires on-prem deployment, email [email protected] with a one-line description and we'll handle it case-by-case.

Your stored memory lives in our EU cloud, data residency on every public tier. AI inference on the write path (embeddings, graph extraction) runs through DPA-covered sub-processors, and you can erase everything about a user with one call. For zero third-country exposure, the air-gapped on-prem deployment runs every model locally, handled case-by-case via [email protected].

These aren't packaged into the public Hobby/Developer/Team/Scale tiers. At our current team size we don't want to make standing SAML/audit promises we can't reliably keep. If you need any of them, email [email protected] with a one-line description of your environment (team size, deployment preference, data-control needs) and we'll work it out case-by-case.

Same product, two surfaces. The consumer pricing at /pricing is for individuals using Korely as a desktop knowledge app (transcription, built-in AI chat, sync). The agents pricing here is for builders using Korely as the memory backend for their own agents via the REST API or SDK. Different tiers, different metrics, different audiences. You can subscribe to either, or both.