AI Memory Pricing
AI memory pricing starts at $19/month for a product in production and $99/month for teams running memory across products and tenants. Every plan includes add, learn, retrieve and forget behind one endpoint. Pro covers up to 50,000 stored memories; Scale raises that to 500,000 and adds tenant isolation, audit history, a bring-your-own store path and priority support. Billing runs through Stripe, and annual plans save 17%.
AI Memory Pricing
Memory plans that grow with your agents
Every plan runs the same memory layer. Pro covers a product in production; Scale adds tenant isolation, your own vector store and priority support.
Pro
Included
- 50,000 memories stored
- Unlimited agents and projects
- Graph memory and reranked retrieval
- Compression engine with token budgets
- TTL, redaction and delete by user
- Python and TypeScript SDKs
- Export the memory graph as JSON
- Bring your own model and framework
- Email support
Scale
Everything in Pro, plus
- 500,000 memories stored
- Tenant isolation and audit history
- Bring your own Postgres and vector store
- Dedicated worker and higher rate limits
- Self-host option with the same API
- Onboarding and migration help
- Priority support
Not sure which plan fits? Open the memory console to try add, search and forget on a seeded memory store, or read the frequently asked questions on storage, retrieval and export. Subscriptions renew automatically and can be cancelled from your billing settings at any time.