14-day free trial — no charge today

Simple Pricing.
Start Free.

Try every plan free for 14 days. Pick a tier, get a generous token allotment, and only pay overage if you outgrow it. Cancel anytime.

Start Free

14-day free trial. Cancel anytime.

Starter

For builders shipping their first memory-powered product.

$20/mo
200M tokens included
then $0.50 per 1M tokens
Start Free
  • ✓200M memory tokens / mo included
  • ✓Then $0.50 per 1M tokens
  • ✓Unlimited memory contexts
  • ✓All 100+ models supported
  • ✓Sub-50ms retrieval
  • ✓BYOK — no inference markup
MOST POPULAR

Growth

For products with real users and growing memory volume.

$100/mo
1B tokens included
then $0.20 per 1M tokens
Start Free
  • ✓1B memory tokens / mo included
  • ✓Then $0.20 per 1M tokens
  • ✓Everything in Starter
  • ✓Priority retrieval
  • ✓Usage analytics
  • ✓Email support

Scale

For high-volume apps and teams. Enterprise usage on the backend.

$200/mo
2B tokens included
then $0.10 per 1M tokens
Start Free
  • ✓2B memory tokens / mo included
  • ✓Then $0.10 per 1M tokens
  • ✓Everything in Growth
  • ✓Lowest overage rate
  • ✓Volume-friendly billing
  • ✓Priority support

Need more? Enterprise volume pricing →

Your data stays yours

"Where does my data go?"

The most important question when you add anything to your AI stack. Here's the straight answer.

🔑

Your keys pass through

BYOK architecture — your provider API keys route straight to OpenAI, Anthropic, etc. We never store them and never see your inference.

🔒

Encrypted & isolated

Memories are encrypted at rest and in transit. Each API key is a fully isolated context — one user's memory never touches another's.

🗑️

You can delete it all

Mark messages "do not remember," wipe a context, or delete everything — programmatically, anytime. It's your data, on your terms.

Pricing Questions

What happens during the free trial?▼
You get full access to your chosen plan for 14 days. Build, test, and ship with memory — no charge until the trial ends. Cancel anytime before it ends and you won't be billed.
What are "included tokens"?▼
Every plan includes a monthly allotment of memory tokens — the storage and retrieval that powers your AI's memory. Starter includes 200M, Growth 1B, Scale 2B. If you go over, you pay a simple per-million overage rate that drops as your plan grows.
What if I exceed my included tokens?▼
You keep going — overage is billed per 1M tokens at your plan's rate ($0.50 on Starter, $0.20 on Growth, $0.10 on Scale). Upgrade tiers anytime to lower your overage rate and raise your included allotment.
Do you mark up inference costs?▼
Never. You bring your own API keys and pay providers directly at their published rates. We only charge for memory. Our incentives stay aligned with yours.
Can I change plans or cancel?▼
Anytime. Upgrade, downgrade, or cancel from your dashboard. Changes take effect at your next billing cycle.
Start Free

14-day free trial. Cancel anytime.