The path to useful AI is to scale in-context continuous learning that works with any model, any harness, and for all the varieties of use cases. As open-source model adoption grows and the world becomes even more multi-model, learning and memory should be separated from the model providers and be highly interoperable (hence in-context!).
Intelligence is no longer a constraint.
Pre-training and post-training, scaling on data and compute, will continue to push models’ intelligence, but will not enable them to learn and improve in real time.
We build all the hard infrastructure parts of a scalable memory system, with dense, interconnected, growing learnings, and an understanding of time.
Our model learner-1 helps any model continuously improve by extracting and dreaming on the context of any user, task, or tenant, and putting it on our vector-graph database. This is then brought to the model by injecting tokens into its context in real time.
We’re a small team based in San Francisco.
Today, supermemory already serves the memory and context for 100k+ organizations, with tens of millions of end users, processing hundreds of billions of tokens every day. It is accessible via an API, with integrations for multiple harnesses available for use.
