Pricing
Simple, transparent pricing.
FAQ
What is a Memory Token?
Memory Tokens are consumed when reading from or writing to memory — ingesting facts, running retrieval queries, consolidating visitor profiles. One search query consumes tokens based on the scope and complexity of the retrieval.
What's the difference between the three memory scopes?
Conversation scope is your Redis-backed session context (ephemeral, TTL-managed). Visitor scope is your MongoDB-persisted personal profile per user. Merchant scope is a shared knowledge base accessible to all agents in your tenant.
What is the Fact Invalidation Engine?
When a new fact contradicts an existing one, the Fact Invalidation Engine automatically versions the stale fact and marks it superseded — so your agents always surface the current truth, never stale data.
What happens to my data if I cancel?
You have 30 days to export your data after cancellation. After that, it is permanently deleted. You can export at any time via the dashboard or API.
Can I self-host Agents Memory?
Custom deployment including VPC and on-premise is available on the Scale plan. Contact us to discuss your infrastructure requirements.
Is there a hard limit on the free tier?
Yes. At 10,000 search queries the API returns a 429 until the next billing cycle. You can upgrade at any time mid-cycle to remove the limit.
What is the Temporal Graph?
The Temporal Graph tracks how facts change over time using valid_from/valid_to timestamps with full version history and contradiction detection. Core access is available on Free; advanced querying and custom ontologies require Pro or Scale.
Is memory data used for model training?
No. Memory data is processed on your behalf and never used for model training. See our privacy policy for details.