augmentationAI

Benchmarks

The number we quote, what it measures, and where it comes from. It was measured in our lab on the public LoCoMo long-conversation benchmark. It says how the system behaved on that test, not what your data or workload will do. Results vary with dataset, configuration and workload.

87.9%
fewer tokens than resending the conversation (LoCoMo)

Tokens: the harness

87.9% fewer tokens than resending the conversation, by token accounting on the LoCoMo benchmark: the tokens sent when only the recalled context is included, against the tokens needed to resend the whole conversation each time. It measures context size, not answer quality; we do not claim the answers are identical. Your savings depend on how long your conversations are and what you ask.

How this is measured

We list only numbers we can reproduce, and we say which benchmark each one comes from. If we find a flaw in a number, we withdraw it.

Memory

Our memory is proprietary and built in-house. It remembers your work and goes with you across harnesses, models and machines, cloud or local. It runs on our own servers, so the memory step does not send your text to a third-party AI service. Inference requests are different: they go to the Model Provider that serves them, as the Privacy Policy explains.

Take it with you

Export your store any time (/wiki/export.ndjson) and keep your own copy.