Open
- Confidential work
- No distinction, or European providers under DPA and ZDR. Your choice.
- Everything else
- The best model per skill, through OpenRouter or European providers.
- On your side
- Nothing to install.
Open · Hybrid · Local
Every request goes to the open model with the best score for the task. Confidential work stays where you decided.
An equivalent score at 3.5% of the price of Fable 5.
TMB benchmark, 32 tests. Scoreboard of 27 September 2026. The TMB scoreboard →
/01 · Skills
A closed model is a generalist, billed for everything. CoeOS classifies each request on one of 18 measured skills and sends it, whole, to the model with the best score there.
Every answer names the model that wrote it.
/02 · Levels
The same client, the same router. What changes: where confidential work goes, and what stays in the cloud.
Everything is a setting: providers, contracts, what runs at home.
/03 · Confidentiality
Nothing retained, nothing used to train a model, no leak.
Because the confidential path leads nowhere else.
Every conversation carries a class. Confidential is the starting point; a conversation is opened on purpose, never by accident.
A conversation that went confidential never returns to an open model. If the confidential target is down, the turn fails instead of leaking.
The client knows no provider address and no key. Everything goes through the router, which only sends confidential work to models you marked safe.
What was said in confidence is stored apart. An open conversation never reads it, and a test checks that continuously.
/04 · Open models
Yes, when you know who hosts it.
Open weights are numbers (safetensors), not code. A model sends nothing anywhere; only the software around it can, and in CoeOS that is the router.
The same model runs at a European host under a DPA, or on your own machines. You choose, provider by provider.
Every model goes through The Monocle Bear's TMB benchmark: 32 tests, 17 axes, public results.
/05 · Desktop
Chat, work on documents, review agents, team memory and company knowledge. Nothing to install, for the whole organisation.
BrowserGuarded multi-agent
An agent with the whole machine: your files, your shell. It plans, delegates to sub-agents in parallel, and asks for your approval on every command, or no longer does if you decide so. Your Claude Code skills work as they are.
macOS, Windows, LinuxFull machine access
/06 · Local
The Local level runs on OdyssAI-X, our inference engine for Apple Silicon. Three models, three jobs.
Planning, calculation, writing: when a mistake costs more than a second.
Everyday work: summaries, writing, tool calls.
Fully local agentic flows and large teams.
Aggregate throughput: 96 concurrent requests on three Mac Studio M3 Ultra with 256 GB.
The OdyssAI-X engine →/07 · Professions
Law, HR, health: agents tuned to a profession, on a dedicated server per client. The agent proposes, you decide.
The contract is read against the firm's Golden Rules, versioned and auditable. The output: a conformity table rule by rule, with the clause quoted, the page, a severity and a recommendation.
An HR policy checked against the applicable collective agreement. Same table, same evidence, plus alerts when a clause drifts out of bounds.
/08 · Demo
A demonstration on your documents, at the level that fits you. Pricing on request.
Request a demo hello@odyssai.eu