Production polish: sub-300ms, SOC2/HIPAA, connectors, context fencing.
- Storage
- Cloud (self-host only on Scale tier+)
- Retrieval
- Managed semantic retrieval with 'context fencing' to keep tenants' memories from polluting each other.
- Self-host
- Managed only
- License
- OSS*
- Pricing
- Free ($5/mo incl.) → $19 → $100 → $399 → Enterprise · Freemium
- GitHub stars
- 27,830
- Last release
- 2026-06-13
- Last commit
- 2026-06-28
- First catalogued
- 2026-06-28
Strengths
- Anti-pollution context fencing
- Sub-300ms
- Multi-tenant
Watch out
- Self-host paywalled high ($399+); proprietary internals
Best for
- Polished managed memory API with SOC 2 / HIPAA compliance
- Coding-agent memory via MCP (Claude Code / OpenCode plugins)
- One API over mixed data (files, email, PDFs, chat)
Benchmark results
No sourced results yet.
Sources
- https://supermemory.ai/ (vendor)
- https://github.com/supermemoryai/supermemory (vendor)
- Supermemory — universal memory API; MCP plugins for coding agents (vendor)
Last verified 2026-06-28 · updated by refresh-framework-cards