The orchestrator, in three layers.
We show you the concept, not the blueprint. The architecture stays under the hood, because what matters is what comes out of it.
The capability map
Soriku doesn't trust marketing benchmarks. When you add a model it runs a short evaluation locally, across the categories that matter: code generation, reasoning, summarisation, translation, code review, security review, and more. The output is a scorecard per model, per category, on your hardware.
Smart routing
Every prompt gets classified in under five milliseconds. Soriku looks at the capability map and routes to the model that scores highest for that category, subject to your constraints like local-only, a cost ceiling, a latency budget, or a preferred provider. You always see who answered.
Multi-model orchestration
For high-stakes prompts, Soriku can run two or three models in parallel and verify their answers against each other. The Conductor picks the strongest response or merges them. You get one answer back, with the provenance attached.
Local and remote, one pool
Soriku doesn't know, and doesn't care, whether a model runs on your laptop or in a datacenter. The capability map treats them equally. Routing picks on score, cost, and your policy. Switch off the internet and Soriku keeps working with whatever's local.
What you get access to
The Agent Persona API, the routing daemon, the benchmark runner, they all ship in the build you download. The docs cover every endpoint if you want to build on top, and you can use the whole thing without ever opening them.
Run it on your own machine
Download the macOS build and benchmark your models today. Windows and Linux follow.