developer pricing

Pay for the layer
that compounds.

Free to start. Solo for the dev piping build logs into a CLI. Team for the squad sharing one codebase brain. Enterprise for VPC, SOC 2, BYOK. Every tier ships dream consolidation and per-task context.

+15.33pp SWE-bench Lite · n=150 · p<0.05

Opus 4.7, seed=42, temp=0, official swebench 4.1.0 docker evaluator. 30.0% → 40.7% strict, CI [+9.33, +22.00]. Full methodology →

Continuity API

Choose your plan

Monthly Annual Save 20%
Free
$0 /month (forever)

 

Kick the tires. Wire the CLI into a side-project repo.

  • 1,000 memories
  • 50 Dream Engine runs / month
  • 10,000 recalls / month
  • 1 namespace
  • REST API + 1 webhook
  • OSS SDKs — Python, Node (Apache-2.0, repos coming Q3 2026)
  • playground_* namespace only on demo keys
Start Free

No credit card required.

Enterprise
Custom

Talk to us

VPC + SOC 2 + BYOK for regulated orgs and monorepos.

  • Everything in Team
  • Unlimited memories / dreams / recalls
  • SSO (SAML, OIDC)
  • BYOK (AWS KMS / GCP KMS / Azure Key Vault)
  • Dedicated VPC deployment or self-hosted (annual license)
  • SOC 2 Type I in flight (target Q4 2026) Roadmap
  • HIPAA BAA available on Enterprise
  • 99.9% uptime SLA with credits (higher per-contract targets negotiable)
  • Dedicated Slack / MS Teams channel
  • Data residency: US-East live; EU and APAC roadmap (Enterprise dedicated on request)
Contact dev@remlabs.ai

Add-ons

Self-serve, attach to any paid plan.

SSO · SAML / OIDC Available on Team
Need SAML for your IdP? Add SSO to Team for $99/mo. Okta, Azure AD, Google Workspace, OneLogin, JumpCloud, custom OIDC. No need to jump to Enterprise.

Overage pricing

Transparent. No surprises.

Memories over quota
$0.005 / 1,000
Dream runs over quota
$0.10 / run
Recalls over quota
$0.001 / 1,000

Hard-cap toggle available in /console to prevent overage (default on for Free + Solo).

No credit card
required for Free tier.
30-day refund
on any annual plan.
Best-rate upgrade
mid-cycle credits unused portion to new plan.
Downgrade self-serve
any time from /console.
Free data export
OAMS JSON, CSV, Markdown. Your data follows you.
No lock-in
self-host parity means you can move off REM anytime.
Every Plan

What's included in every plan

No feature gates on the fundamentals. Every tier gets the full platform.

Unlimited Storage

We never charge for storing memories

8 Search Modes

Semantic, keyword, hybrid, temporal, and more

Knowledge Graph

Automatic relationship mapping between memories

API Access

Full REST API with SDKs for Python and Node.js

MCP Server

Connect to Claude, Cursor, and any MCP client

The Upgrade That Matters

Dream Engine is the difference

Most memory systems store and retrieve. The Dream Engine runs nightly consolidation cycles that deduplicate, contradict-detect, and synthesize new structure across your namespace — so the next call returns a denser, cleaner answer than the last.

Free

1 cycle / day

Basic consolidation to keep your memories organized

Solo

Unlimited cycles

All 9 strategies + tournament refinement + scheduled digests

Compare Plans

Full feature comparison

Feature Free Solo Team Enterprise
Memories stored10K1MUnlimited
API calls / month10K1MUnlimited
Dream Engine cycles1 / dayEvery 6hContinuous
All 9 strategiesYesYesYes
Contradiction detectionYesYes
Brain Glow scoreLimitedFull (team)Full (org)
Scheduled digest webhookWeeklyDailyDaily
FederationYesYes
RBACYesYes
WebhooksYesYes
WebSocket streamsYesYes
MCP protocolYesYesYes
Self-hostYes
SSO (SAML / OIDC)+$99/mo add-onIncluded
Audit logsYesYes
SLA99.9%99.9% (per-contract higher available)
SupportCommunityPriority emailDedicated Slack + phone
Annual invoiceYesYes
SOC 2Type I roadmap (Q4 2026)Type I roadmap (Q4 2026)Type I in flight (Q4 2026); Type II planned (Q2 2027)
Data residency optionsYes
Uptime creditsYesYes
Knowledge graphYesYesYes
Namespaces110Unlimited
Tournament refinementYesYes
8 search modesBasicYesYes
Slack/Notion deliveryYesYes
Custom integrationsYes
BAA / DPAYes
API rate limit10 req/s200 req/sCustom
30-day refundYesCustom
Calculator

What plan do I need?

Tell us about your app and we'll recommend a plan.

How many users will your app have? 100
1 100 1K 10K 100K
How much does each user interact? (conversations, facts, preferences stored) 50
10 50 200 1K 5K
Total memories: 5,000
Recommended plan: Free
Monthly: $0 Annual: $0/yr
High-volume API

Pay-as-you-go

For high-volume API users who'd rather pay per operation than per tier.

Pay-as-you-go
Metered, no minimum, volume discounts at scale.
$0.001
per memory stored
$0.0005
per memory retrieved
$0.01
per Dream Engine cycle
1M+ ops → 20% off 10M+ ops → 40% off Annual commits available
Contact sales →
Monthly volume Stores Recalls Dreams
0 – 1M $0.001 $0.0005 $0.01
1M – 10M $0.0008 (20% off) $0.00035 (30% off) $0.008
10M+ Custom (contact) Custom Custom

Automatic tier promotion — your bill applies the best rate retroactively.

Cost estimator

Model your monthly bill in 30 seconds.

Three sliders. Real numbers. Based on PAYG rates. No sales call required.

Agents (how many AI agents/workflows will use REM?) 5
1 10 25 50
Memories stored per day (writes across all agents) 5,000
100 5K 25K 100K
Recalls per day (reads across all agents · /memory/ask + /memory-search) 20,000
100 10K 50K 200K
$0.00
per month
Stores $0.00 · Recalls $0.00 · Dreams $0.00
Recommended: Free
Just raised? Just launched? REM Labs offers 50% off Solo for 12 months to YC / Techstars / EF / Sequoia Arc / a16z companies. Verify your batch → apply.
Apply for startup discount

Free forever for universities and OSS maintainers.

Research labs at accredited universities, authors of OSS projects with 1,000+ stars, and published AI research teams qualify for a free Academic tier: all Solo features, unlimited cycles, mention in project acknowledgments. Email dev@remlabs.ai from a .edu or your project's maintainer email with a link.

ROI calculator

What will REM save you?

Hours spent re-grounding agents, re-prompting, re-finding context — priced honestly.

Hours/week spent searching for context 6
0 5 10 15 20
Hourly rate $120
$50 $150 $250 $350 $500
$0
You save per month
REM costs $20. Net gain: $0/mo.
Assumes 4 working weeks per month · one Solo seat · not adjusted for taxes or overhead.
Not sure which tier?

3 questions, 1 recommendation

1. How many AI agents will use REM?
2. Do you need federation or self-host?
3. Team size?
30-day money-back guarantee
No questions. Cancel in one click.
Cancel in one click
One click in /settings/billing. Your memories stay yours. Download everything as JSON/CSV before closing.
Downgrade anytime
What happens to my data if I downgrade? Your memories stay. Storage caps apply to new writes, never reads.
SLA

What we guarantee, per tier.

The same numbers that go on an Enterprise contract — visible before you talk to sales.

Commitment Free Solo Team Enterprise
Uptime Best effort 99.9% 99.9% 99.9% baseline; higher per-contract
Support response Community 24h email 4h email 1h (dedicated Slack)
Data backup Daily Daily Hourly Hourly + geo-replicated
Incident credit 10% for <99.9% 10% for <99.9% Up to 100% per contract
Security review Public docs Public docs Questionnaire SOC 2 Type I in flight (Q4 2026), pentest Q3 2026, DPA
Data residency us-east-1 us-east-1 us-east-1 us-east-1 live; EU/US-West/APAC roadmap, dedicated on request

See /sla for the full terms, credit math, and incident-reporting procedure.

Pricing FAQ

Common questions

Yes — upgrade instantly, prorated to the day. Your new limits apply immediately; you pay only the difference for the remaining days in your current billing cycle.

The Free tier is our trial. It includes all 9 Dream Engine strategies and MCP protocol so you can evaluate the core product end-to-end. When you're ready for higher limits, Solo is $25/mo ($20 annual) with a 30-day money-back guarantee.

One stored record: a fact, preference, message, or chunk you wrote via memory.set() or batch(). Vector + graph edges are included free. Compressed/consolidated outputs from Dream cycles do not count against your limit.

No. 4xx and 5xx responses don't count against your API call quota. Rate limits (429) also don't count. You only pay for operations that actually executed on your data.

Yes. SSO (SAML and OIDC) is a self-serve $99/mo add-on on the Team plan — works with Okta, Azure AD, Google Workspace, OneLogin, JumpCloud, and any standard OIDC provider. You don't need to talk to sales or jump to Enterprise just to wire your IdP. Enterprise still includes SSO at no additional cost alongside SCIM, BYOK, dedicated VPC, and SOC 2.

Yes, on Team and Enterprise. Plug in Claude, GPT-4o, Llama/Mixtral via Together/Fireworks/Groq, or a self-hosted Ollama endpoint. Dream Engine runs the 9 strategies against the model you configure, and we pass through token costs at provider price.

USDC (Base, Ethereum, Solana) is supported on annual Team and Enterprise plans — invoice-based, not self-serve. Email billing@remlabs.ai to set up.

30-day money-back on monthly plans, no questions asked. Annual plans are pro-rated to the unused months. Enterprise contracts follow the terms in your MSA.

Yes. 501(c)(3) non-profits and accredited academic labs get 50% off Solo and Team indefinitely; students with a .edu address get Solo free for 12 months. Email dev@remlabs.ai with verification.

We notify you at 80% usage. There is no hard cutoff — your app never goes down. You can upgrade instantly or we soft-limit until your next billing cycle.

Continuity API Reference · Enterprise Plans · Documentation · Compare Alternatives · Benchmark Results