Pricing

Simple, transparent pricing.

Start free. Scale when you need to. No per-seat fees — you pay for what your agents actually use, measured in Memory Tokens.

Start free. Scale when you need to. No per-seat fees — you pay for what your agents actually use, measured in Memory Tokens.

GGeett  ssttaarrtteedd  ffoorr  ffrreeee
RReeaadd  tthhee  ddooccss
FREE

Perfect for prototyping and testing.

$0

500,000 Monthly Memory Tokens

10,000 Search Queries

Core Temporal Graph Access

Standard Multi-Modal Extraction

Full API & SDK Access

Community Support

All three memory scopes

90-day memory archive

Start free

MOST POPULAR

PRO

Production-grade agents with perfect recall.

$35

5 Million Monthly Memory Tokens

250,000 Search Queries

Advanced Temporal Graph

Multi-Modal Extractors

Sub-200ms Retrieval

Fact Invalidation Engine

Memory lifecycle configuration

Webhook support

Email Developer Support

No memory expiry cutoff

Start Pro Trial

SCALE

For scaling teams and high-volume data.

$499

100 Million Monthly Memory Tokens

25 Million Search Queries

Automated Business Connectors

Custom Ontology Modeling

Advanced Analytics Dashboard

Dedicated Account Manager

24/7 Priority Support

SSO / SAML

Data residency (US, EU)

Private deployment (VPC / on-premise)

Contact sales

FREE

Perfect for prototyping and testing.

$0

500,000 Monthly Memory Tokens

10,000 Search Queries

Core Temporal Graph Access

Standard Multi-Modal Extraction

Full API & SDK Access

Community Support

All three memory scopes

90-day memory archive

Start free

MOST POPULAR

PRO

Production-grade agents with perfect recall.

$35

5 Million Monthly Memory Tokens

250,000 Search Queries

Advanced Temporal Graph

Multi-Modal Extractors

Sub-200ms Retrieval

Fact Invalidation Engine

Memory lifecycle configuration

Webhook support

Email Developer Support

No memory expiry cutoff

Start Pro Trial

SCALE

For scaling teams and high-volume data.

$499

100 Million Monthly Memory Tokens

25 Million Search Queries

Automated Business Connectors

Custom Ontology Modeling

Advanced Analytics Dashboard

Dedicated Account Manager

24/7 Priority Support

SSO / SAML

Data residency (US, EU)

Private deployment (VPC / on-premise)

Contact sales

FREE

Perfect for prototyping and testing.

$0

500,000 Monthly Memory Tokens

10,000 Search Queries

Core Temporal Graph Access

Standard Multi-Modal Extraction

Full API & SDK Access

Community Support

All three memory scopes

90-day memory archive

Start free

MOST POPULAR

PRO

Production-grade agents with perfect recall.

$35

5 Million Monthly Memory Tokens

250,000 Search Queries

Advanced Temporal Graph

Multi-Modal Extractors

Sub-200ms Retrieval

Fact Invalidation Engine

Memory lifecycle configuration

Webhook support

Email Developer Support

No memory expiry cutoff

Start Pro Trial

SCALE

For scaling teams and high-volume data.

$499

100 Million Monthly Memory Tokens

25 Million Search Queries

Automated Business Connectors

Custom Ontology Modeling

Advanced Analytics Dashboard

Dedicated Account Manager

24/7 Priority Support

SSO / SAML

Data residency (US, EU)

Private deployment (VPC / on-premise)

Contact sales

All plans include HTTPS API access, Python & Node SDKs, and all three memory scopes (Merchant, Visitor, Conversation).

All plans include HTTPS API access, Python & Node SDKs, and all three memory scopes (Merchant, Visitor, Conversation).

FAQ

Frequently Asked Questions

Frequently Asked Questions

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.