Home / Directory / Agents & orchestration / AI agent memory / Supermemory
Supermemory
San Francisco memory engine for AI agents that extracts and updates memories from files, chats, and apps, offered through an API, plugins, and an MCP server.
Developers who want fast memory recall for agents and apps, a low monthly entry price, and a clear per-token rate card.
Regulated buyers who need compliance features on a low tier, or teams that want a long enterprise track record before committing.
Verdict
Supermemory is worth using for developers who want quick, low-cost memory for agents and apps with transparent usage rates. It suits teams moving off homemade retrieval pipelines. Regulated companies should plan on the Scale plan or an Enterprise contract.
Score Breakdown
How Supermemory scores in the categories that matter to its buyers.
Pricing
Supermemory publishes plan prices that include monthly credits, plus a rate card. Memory ingestion costs $5 per million tokens for plain text on every plan.
| Plan | Price | What stands out |
|---|---|---|
| Free | $0 | $5 of credits a month |
| Pro | $19 / month | $20 of credits, 3 team seats, priority support |
| Max | $100 / month | $130 of credits, Gmail connector |
| Scale | $399 / month | $600 of credits, advanced PDF extraction, S3 and web crawler connectors, SOC 2 and HIPAA BAA, self-hosted option |
| Enterprise | Custom | Air-gapped self-hosting, SSO, custom contracts, uptime SLA |
The Field at a Glance
How Supermemory compares with other AI agent memory vendors we reviewed, by Overall Score and relative typical engagement cost.
Supermemory scores 7.8 in AI agent memory, under Mem0 (8.0) and Zep (7.9), level with Letta (7.8), and ahead of Cognee (7.7). Relative cost lands lower for this subcategory.
Use-case matrix
| Use case | Fit | Notes |
|---|---|---|
| Recall latency | Strong | Median search server time is listed at 187ms. |
| Low entry price | Strong | Pro costs $19 a month with $20 of credits. |
| Published rate card | Strong | Per-token and per-query rates are public. |
| Self-hosting | Mixed | Self-hosting starts on Scale and Enterprise. |
| Compliance on low tiers | Weak | SOC 2 and HIPAA BAA start on Scale. |
| Long track record | Weak | The company raised its seed round in 2025. |
Who it’s for
Good fit
- AI app developers
- Coding agent and assistant builders
- Startups replacing homemade retrieval
Poor fit
- Regulated buyers on small budgets
- Teams wanting a long vendor history
- Projects without repeat users
Review Excerpts
Below are excerpts from public reviews. Our team scoured public reviews, forums, and chat rooms to get a balanced view of customers' experience with this company. Paid reviews and pay-for-play sites such as Clutch were excluded.
“We just ditched RAG completely and went memory only through supermemory. Reduced avg response time from 40s → 12s. Using about 40–50% fewer tokens.”
“supermemory let us scale usage without losing the thread of every conversation.”
Supermemory's advanced PDF extraction, S3 and web crawler connectors, and SOC 2 and HIPAA BAA coverage start on the Scale plan at $399 a month.
Company Facts
- Headquarters
- San Francisco (Supermemory)
- Key investors
- Susa Ventures, Browder Capital, SF1.vc (TechCrunch)
- Website
- supermemory.ai
Key Leadership
Dhravya Shah
Founder
Methodology
This page is an independent evaluation of Supermemory for buyers comparing options in AI agent memory. AI Industry Reviews accepts no sponsorships, advertising, or pay-for-placement fees. Supermemory did not pay for this review.
What we scored
The headline number is an Overall Score on a 0-10 scale. Eight criteria sit under it in two groups.
- Buyer outcomes (for AI agent memory)
- Recall speed
- Developer setup
- Usage pricing clarity
- Enterprise track record
- Company & commercial
- Innovation & product leadership
- Project management & communication
- Pricing
- Contract fairness
Pricing measures whether the price looks fair for the value delivered, including packaging and renewal friction that show up in real buying cycles.
Score Composition
| Input | Weight | What it covers |
|---|---|---|
| Reviews | 40% | A proprietary read of what practitioners say about likes, complaints, and day-to-day use, including public review sites, forums, and private chat rooms. Paid reviews and pay-for-play sites such as Clutch are out of scope. |
| Product | 35% | Hands-on look at screens and workflows. |
| Pricing | 15% | Whether the price looks fair for what you get. |
| Docs & training | 10% | Docs, tutorials, and training material. |
How we balanced the evidence
The Overall Score is the simple average of the eight criteria. Recommendation language follows that score and the fit pattern described above.
Scope
Supermemory is graded here as AI agent memory. Criteria scores can move as more review volume and product checks are added.