Memory that scales
with your agents.

One atomic fact stored in the vault — 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 desktop app shows the count in real time.

One read tool call: korely_search, korely_get_related, korely_read_item, korely_list_notes, or korely_list_folders. Write tools (save_note, create_task) don't count as queries — only against the memories quota. The monthly counter resets the 1st of every month at UTC midnight.

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 tiers — the agent memory product (cloud MCP, OAuth, graph, vector store) ships hosted only. If your environment requires on-prem deployment, email enterprise@korely.ai with a one-line description and we'll handle it case-by-case.

Hetzner Helsinki, EU data residency, on every public tier. Never US — Korely was built to be CLOUD-Act-safe by design. On-prem deployment for regulated industries is handled case-by-case via enterprise@korely.ai.

The cloud MCP infrastructure (OAuth multi-tenant, API key issuance, agent namespaces, R2 sync) lands in Q3. Drop your email on any cloud tier card above and we'll email your API key the moment it goes live.

These aren't packaged into the public Hobby/Developer/Team tiers — at our current team size we don't want to make standing SAML/audit/BAA/SOC2 promises we can't reliably keep. If you need any of them, email enterprise@korely.ai with a one-line description of your environment (team size, deployment preference, compliance 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 MCP. Different tiers, different metrics, different audiences. You can subscribe to either, or both.