In development · Personal use first
Instead of asking one big AI model to do everything, Nanana runs a set of small focused models — each doing one job well — on top of a shared layer that handles memory, routing, and logging. The whole thing runs on your own hardware. No cloud. No subscription.
One big model handles everything — memory, reasoning, tool use, personality — all crammed into a single context window. When something goes wrong, it is hard to tell why.
Build the infrastructure first — memory, routing, logging — then drop in small focused models as tenants. Each one does one job. When something breaks, you can see exactly where and why.
The key finding from early testing: a failure that looked like the AI reasoning badly turned out to be a small retrieval component returning the wrong input. Every model was behaving correctly — the problem was visible and fixable because the pieces were separate.
That is what transparency buys you. Not just for debugging — but for trusting what your local AI is actually doing.
Sits alongside your AI and logs every interaction — what went in, what came out, any tools used in between. Stored as plain text files you can read yourself. Useful for understanding what your AI is doing, auditing past sessions, and carrying memory across different models without losing anything in translation.
Drop it alongside whatever you are already running. Logs input, output, and tool usage as an outside observer.
Inside the SoS infrastructure, it sees everything — context assembly, routing decisions, each specialist's input and output.
Nanana is a personal research project that is still being built.
It runs on consumer hardware and has produced findings worth sharing —
the paper is published — but it is not production ready and is not
being presented as a finished product.
The goal right now is to stabilise the infrastructure and release
components one at a time as they become useful to others.
Context Tracer is first.