supermemory

Supermemory provides memory and continual-learning tools for AI agents through an API, plugins, and an MCP interface.

supermemory.ai
supermemory homepage screenshot

About supermemory

Supermemory provides memory infrastructure for AI agents, accessed through an API, plugins, and an MCP interface. It is described as working with different models and agent harnesses, with memory stored separately from model providers.

Its learner-1 component processes files, chats, URLs and raw data, updating, merging, inferring and forgetting stored context in a vector-graph database and injecting relevant tokens into agent context in real time. Advanced PDF extraction with OCR and descriptions of figures and diagrams is listed for Scale and Enterprise plans, while Free, Pro and Max use standard extraction. Deployment options include customer data centers, VPCs, laptops, and air-gapped environments.

Key features

  • Memory access through API, plugins, and MCP interface
  • Compatible with different models and agent harnesses
  • Vector-graph storage of learnings with time understanding
  • Real-time injection of stored context into agent context
  • Advanced PDF extraction with OCR on Scale and Enterprise
  • Deployment in data center, VPC, laptop, or air-gapped
Best for: Developers and teams building AI agents that need persistent memory across models and harnesses.
Good for
  • Memory stored outside model providers for use across models and harnesses
  • Publishes production recall latency and token volume figures
  • Can be deployed where data lives, including air-gapped environments
Watch out for
  • Advanced PDF extraction with OCR is limited to Scale and Enterprise plans

supermemory at a glance

Type
Online tool
Pricing
Not confirmed. Check the site
Platforms
Web
Open source
Not stated
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026

supermemory alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Infrastructure & MLOps

Well-known listings from the same topic.

All 341

supermemory FAQ

How do agents receive stored memory?
Learner-1 stores context in a vector-graph database and injects relevant tokens into the agent's context in real time.
How can developers access supermemory?
Through its API, plugins, and MCP interface.
What is the difference in PDF extraction between plans?
Scale and Enterprise include advanced extraction with OCR and descriptions of figures and diagrams; Free, Pro and Max use standard PDF extraction.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing