01Public preview
Hub and registry
Accounts and organizations, model repositories under a stable namespace, versioned files, model cards, search with decision-native facets, and lineage. Free during the preview.
Loading…
ABOUT
System One is a registry and developer platform for decision models — models that return a typed decision with calibrated confidence instead of generated text.
System One Models began as an open-source environment for fine-tuning System One decision models.
Psychologists describe two modes of thinking. System 2 is slow and deliberate: it reasons, weighs, explains. System 1 is fast and automatic: it sees the situation and acts. Large language models are the System 2 of AI, and the tools around them (chat playgrounds, token counts, prompt templates) were built for models whose output is prose.
System One models are the other half. A routing model picks a queue. A game agent picks its next move. A fraud model returns a score. The output is a typed decision with a probability attached, produced in milliseconds, often on a CPU or a phone. What matters about such a model is not how well it writes but how often it is right, whether its confidence can be trusted, and whether it is fast enough to sit in a request path.
The developers who train and ship these models, and have been making do: people building game AI and reinforcement-learning agents, robotics controllers, ticket and request routers, risk and fraud scorers, rankers, and small classifiers that run on the device.
It is early, and it is being shaped in the open. The manifest is a draft that changes with real architectures, and what gets built next is decided by what the people publishing here need.
Everything a model needs, versioned. A repository holds the manifest, the model card, the evaluation numbers, the lineage and the files themselves. Weights go straight from your machine to object storage and are stored once by content.
Accounts and organizations, model repositories under a stable namespace, versioned files, model cards, search with decision-native facets, and lineage. Free during the preview.
Browser login, search, pull with a content-addressed cache, create and push, and manifest validation before publication.
What comes next is shaped by the people publishing here.
System One Models is a project of the founding team of Gilver.ai, operated for now by Gilver.ai, Inc., a Delaware company. See the legal notice.
For now, System One Models is a free public preview. There are no paid plans and no service-level guarantees, and features may change as the platform takes shape. Hosted models from other providers are offered and billed by those providers, not by us.
Questions: Biplov Gautam, founder, [email protected] · Siraj Dahal, co-founder, [email protected]
System One Studio is an open-source fine-tuning environment for System One decision models, created by Biplov Gautam. It trains locally, evaluates calibration alongside accuracy, and emits a manifest you can publish straight to this registry. Studio is a separate project with its own licence and address.