Supermemory
A memory and context platform that helps AI agents learn and improve continuously
- Also known as
- supermemory
Available worldwide
What is Supermemory?
A memory platform for AI agents that automatically extracts facts from conversations, maintains user profiles, and injects relevant context in real time. Includes RAG capabilities and real-time synchronization with external services.
Supermemory pricing
Plans, per-tier features and add-ons, dated and linked to live pricing. Pricing changes often; always verify at source before you rely on it.
Free tier ($0 + $5 credits/mo) through Scale ($399 + $600 credits/mo). Usage-based charges on top of included credits. All plans share same rate card: memory $0.005-0.010 per 1K tokens, operations $0.10 per 1K. Startups program offers Scale plan free for 3 months.
Free
Free- monthly_credits
- $5
- Full search and memory API
- 1 team seat, unlimited end users
- Email support
Pro
- monthly_credits
- $20
- Everything in Free
- Auto top-up
- Plugins (Claude Code, Cursor, Hermes, etc.)
- 3 team seats
- Priority support
Max
- monthly_credits
- $130
- Everything in Pro
- 6x the credits of Pro
- Gmail connector
- Plugins and priority support
Scale
- monthly_credits
- $600
- Everything in Max
- Auto top-up and spend caps
- S3 and web crawler connectors
- Unlimited team seats
- Dedicated support
- SOC 2
- HIPAA BAA
- Self-hosted option
Custom
Contact sales- unlimited_usage
- True
- Everything in Scale
- Custom metering and billing
- Custom integrations and SSO
- Forward-deployed engineer
What Supermemory does
The capabilities that matter for agent memory, normalised so it lines up with every alternative. “-” means we haven't confirmed it, not that it's missing.
- Architecture model
- Managed cloud API
- Graph based entity relationship extraction
- ✓
- Automatic context window rolling summarization
- ✓
- Semantic vs episodic event chronological memory
- ✓
- Cross session and multi thread user persistence
- ✓
- Memory conflict resolution and fact updating
- ✓
- Multi tenant user and agent isolation
- ✓
- Native langchain and llamaindex memory classes
- -
- Time decay and recency weighted retrieval
- ✓
- Zero data retention and pii redaction layer
- -
- SOC2 type ii
- ✓
- Mit or apache permissive oss license
- -
- Pricing model
- Usage based per req
Platform & deployment
Independently observed- CLI
- macOS
- Web
- Linux
- Cloud / SaaS
- Hybrid
- Air-gapped
- Self-hosted
Integrations (16)
Independently observed- Linear⇄•
- Airtable⇄•
- Figma⇄•
- HubSpot⇄•
- Vercel⇄•
- Sentry⇄•
- Notion
- Google Drive
- Gmail
- GitHub
- OneDrive
- S3
- Web Crawler
- Slack
- Granola
- Custom sources
Security & compliance
Known vulnerabilities: 0 (0 in the last 12 months) sourcea count reflects scale & disclosure, not quality
Supermemory FAQ
Common questions about Supermemory, answered from independent, dated evidence.
What is Supermemory?
A system that enables AI agents to remember information across conversations, automatically extract and organize facts, and stay synchronized with external tools. It combines memory storage, knowledge retrieval, user profiling, and data connectors into one service. It is indexed under Agent Memory.
Source: https://supermemory.ai/pricing/
Is Supermemory free to use?
Supermemory is open source, so it can be self-hosted and used at no licence cost. It is released under the MIT licence. A commercial or hosted edition starts at $0.00. Prices are published openly on the vendor's own pricing page. Pricing changes often, so verify at source before relying on it.
Source: https://supermemory.ai/pricing/
What platforms does Supermemory support?
Supermemory supports the web, macOS, Linux and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.
Source: https://supermemory.ai/pricing/
Can Supermemory be self-hosted?
Yes. Supermemory can be deployed cloud / SaaS, hybrid, on-premise, air-gapped and self-hosted, so it does not have to run on the vendor's infrastructure.
Source: https://supermemory.ai/pricing/
What does Supermemory integrate with?
We have confirmed 10 integrations for Supermemory, including Notion, Google Drive, Gmail, GitHub, OneDrive, S3, Web Crawler and Slack, plus 2 more. This is what we could verify from public sources, so the vendor may support others we have not indexed.
Source: https://supermemory.ai/pricing/
What security certifications does Supermemory have?
We have independently confirmed SOC 2, HIPAA and GDPR for Supermemory. Certifications we do not list are ones we have not been able to verify from public sources, which is not the same as Supermemory not holding them. Always confirm compliance directly before you rely on it.
Source: https://supermemory.ai
Is Supermemory open source?
Yes. Supermemory is published under the MIT licence, a permissive licence that generally allows commercial use and modification. Licence terms can change between releases, so verify against the repository for the version you intend to use.
Where is Supermemory available?
Supermemory is available worldwide. Its primary market is the United States.
Source: https://supermemory.ai/pricing/
Supermemory alternatives
Other agent memory we track, ranked by the same independent score.
- CogneeGraph-based memory layer enabling AI agents to retain and recall information across sessionslow · 25%
- ZepA platform that organizes enterprise information into knowledge graphs for AI agentsmedium · 55%
- Mastralow · 45%
- MemaryA knowledge graph-based memory system that helps AI agents store and retrieve information beyond their context window limitslow · 19%
- Mem0Memory infrastructure that enables AI agents and applications to retain and recall information across multiple sessions and contextsmedium · 53%
- GraphitiFramework for creating evolving knowledge graphs with temporal awareness for AI agentslow · 32%
Compare Supermemory
Side by side against other agent memory, attribute by attribute, with a source on every value.
The vioscaleAI score: one lens on the evidence
Not user reviews and not a paid placement: a confidence-weighted blend of the independent signals below (adoption, activity, security posture, and more), which you can sort and re-weight yourself. Vendors can correct their listing but can never move their rank, and stars are weighted low as a vanity metric. It is one way to read the evidence for Supermemory, not the verdict.
| Signal | Score | Weight | Contribution | Evidence |
|---|---|---|---|---|
| Capabilities | 92 | 0.10 | 9.0 | ✓ |
| Release cadence | 99 | 0.08 | 8.0 | ✓ |
| Development activity | 52 | 0.14 | 7.0 | ✓ |
| Security posture | 55 | 0.12 | 6.7 | ✓ |
| Pricing transparency | 100 | 0.05 | 5.4 | ✓ |
| Stars | 84 | 0.05 | 4.0 | ✓ |
| Price level | 50 | 0.04 | 2.1 | ✓ |
| Integrations | 34 | 0.05 | 1.8 | ✓ |
| Reliability | 0 | 0.07 | 0.0 | - |
| Dependent projects | 0 | 0.05 | 0.0 | ✓ |
| Package downloads | 0 | 0.04 | 0.0 | - |
| Security score | 0 | 0.05 | 0.0 | - |
| Developer Q&A activity | 0 | 0.14 | 0.0 | - |
Computed . Re-weight it by intent, or see the full method.
All data & sourcesshow ↓
Every value we hold, with its source, retrieval date, and confidence. This is the evidence behind the score: don't trust it, verify it.
Activity
| Attribute | Value | Evidence |
|---|---|---|
| Commits last 30d | 44 | mediumsource · 2026-09-14 · 65% |
Adoption
Content
| Attribute | Value | Evidence |
|---|---|---|
| Faq | 8 items | mediumsource · 2026-09-10 · 62% |
Features
| Attribute | Value | Evidence |
|---|---|---|
| Capabilities | Soc2 type ii: Yes · Pricing model: usage_based_per_req · Architecture model: managed_cloud_api · Multi tenant user and agent isolation: Yes · Time decay and recency weighted retrieval: Yes · Graph based entity relationship extraction: Yes | mediumsource · 2026-09-14 · 60% |
Integrations
| Attribute | Value | Evidence |
|---|---|---|
| Count | 14 | mediumsource · 2026-09-14 · 60% |
Language
| Attribute | Value | Evidence |
|---|---|---|
| Primary | TypeScript | highsource · 2026-09-14 · 90% |
License
| Attribute | Value | Evidence |
|---|---|---|
| Spdx | MIT | highsource · 2026-09-14 · 95% |
Market
| Attribute | Value | Evidence |
|---|---|---|
| Availability | HqCountry: US · PrimaryMarkets: … · AvailabilityScope: global · AvailableCountries: … · NotAvailableCountries: … | highsource · 2026-09-14 · 75% |
Pricing
Release
Security
| Attribute | Value | Evidence |
|---|---|---|
| Soc2 | Yes | mediumsource · 2026-09-14 · 60% |
| Gdpr | Yes | highsource · 2026-09-14 · 75% |
| Hipaa | Yes | mediumsource · 2026-09-14 · 60% |
| Vulnerabilities | Count: 0 · Source: https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=supermemory-openai-sdk&per_page=100 · Last 12m: 0 | highsource · 2026-09-14 · 90% |
Is Supermemory the right choice for you?
Tell us the job, the constraints and what you weigh most, and we will rank Supermemory against the rest of the agent memory we index, using the same dated evidence weighted your way.
Free to run, no account needed to start. How the evaluation works
Is this your product?
This profile was built from public sources without asking you. You can take the badge below and use it anywhere, and you can claim the profile to correct anything we got wrong. Both are free, and neither moves Supermemory up or down: nobody can buy rank here, including you.
Take the badge
Live, always current, and free to use on your own site. It shows Supermemory's independent score and links back to this profile.
<a href="https://www.vioscale.ai/software/supermemory" target="_blank" rel="noopener">
<img src="https://www.vioscale.ai/badge/software/supermemory.svg" alt="Supermemory, verified on vioscaleAI" width="330" height="76" loading="lazy" />
</a>Markdown, for a README →
[](https://www.vioscale.ai/software/supermemory)Claim the profile
Verify you control the domain, then point us at the pages that state the facts about Supermemory and add your own description and media. Free, and it does not change the score.
- Correct anything wrong, with evidence
- Point our crawler at the pages that matter
- Write your own description and add media
Not the owner? How vendor profiles work