ViteHub is still experimental. Expect bugs and breaking changes.

ViteHub docs

Add server APIs or portable Agents to a Vite application.

ViteHub adds a server layer to Vite. Use Server Primitives directly from application code, or combine them with models and tools in an Agent.

Server Primitives work without an Agent. When you build an Agent, Capabilities control which operations it can use.

Server primitives
Add auth, storage, queues, schedules, sandboxes, and other server APIs.
Agents
Define an Agent, select its Capabilities and Workspace, then run and inspect it.
Get started
Install ViteHub and run one Server Primitive or Agent.
Concepts
Learn how definitions, integrations, Workspaces, Sources, and Capabilities fit together.

Find what you need

You are buildingStart with
A new installationGet started
Auth, storage, background work, schedules, sandboxes, or environment valuesServer primitives
Model-backed actors, Agent Invocations, triggers, chat history, evals, or CLI inspectionAgents
Tools and product operations that an Agent can useCapabilities
The difference between definitions, server APIs, Workspaces, Sources, and CapabilitiesConcepts
Host support, generated output, or deployment supportRuntime and host support

How ViteHub connects your code to a host

Most features use this path:

  1. Start with Installation.
  2. Register vitehub() in the Vite configuration.
  3. Add a definition when the feature needs a name, schema, or reusable configuration.
  4. Call the documented server API from application code.
  5. Attach a Capability if an Agent needs to call that operation.

The Vite integration discovers definitions and prepares the provider-specific files for the selected host. Application code keeps using ViteHub imports.

Check host support

Not every Server Primitive runs on every host. Check the runtime and host support matrix before you choose a deployment target.

Open Installation for a runnable path, or read Concepts when you need the runtime model.