Supermemory
used in
0
stacks
Closed-source universal memory API that adds long-term, personalized memory to AI agents and apps.
Supermemory is a commercial memory API and routing layer that stores, recalls, and personalizes data for LLM applications and agents. It provides fact extraction, user-profile building, contradiction resolution, and selective forgetting through a single API, and deduplicates ingested content at the byte level to reduce cost. It offers an MCP server and integrations for coding-agent workflows. It is proprietary infrastructure billed via usage credits across subscription tiers, with a free tier available.
Strengths
- Single API covering extraction, profiles, contradiction resolution, and forgetting
- Byte-level deduplication lowers cost on repeated agent-loop content
- MCP server and integrations for coding-agent memory workflows
- Free tier with usage-credit billing across paid tiers
Tradeoffs
- Closed-source proprietary service with no self-hosting
- Usage-based pricing can be hard to predict at scale
- Benchmark leadership claims are largely self-reported