ViteHub is still experimental. Expect bugs and breaking changes.

Official capabilities

Use the official Capability catalog by agent ability, not by package boundary.

Official Capabilities are public factories exported from @vite-hub/agent/capabilities. Use them when the Agent needs a named ability that ViteHub owns end to end, including requirements, runtime behavior, driver contributions, and inspection metadata.

server/agents/support.ts
import {
  access,
  blob,
  chat,
  chatSummary,
  chatTitle,
  db,
  entry,
  fetch,
  git,
  inputCommands,
  kv,
  llmGate,
  llmRoute,
  mcp,
  memory,
  rateLimit,
  repositoryHost,
  sandbox,
  schedule,
  skills,
  subagents,
  transcribe,
  usageTelemetry,
  webSearch,
  workspaceShell,
} from '@vite-hub/agent/capabilities'

Catalog

AbilityCapabilityUse it when
Invocation accessaccess()Trusted invocation identity should narrow chat admission or Workspace Scope before later Capabilities run.
Chat behaviorchat()A chat surface should start Agent Invocations and manage Chat History behavior.
App-owned entryentry()A product event needs a named Agent Trigger without a full product-specific Capability.
Input commandsinputCommands()Explicit user commands should transform or enrich input before the Agent runs.
Subagentssubagents()A model-backed Agent should delegate bounded work to named Agent Definitions through model-facing tools.
Workspace filesworkspaceShell()The Agent should inspect or edit Workspace files through constrained Workspace tools.
Git source historygit()The Agent needs bounded Git source-history inspection or local Workspace Session git state selection.
Repository hostrepositoryHost()The Agent needs provider-hosted repository, Change Request, issue, comment, check, or status data through a configured Repository Host client.
Skills fileskills()The Agent requires a Workspace skill file at invocation time.
KV storagekv()The Agent needs scoped key-value read or edit tools.
Blob storageblob()The Agent needs scoped object read or edit tools.
Databasedb()The Agent needs guarded SQL query, schema, or mutation tools.
Sandbox executionsandbox()The Agent may run an allowlisted executable in an isolated runtime.
Schedulesschedule()The Agent declares scheduled invocations or manages Runtime Schedules through tools.
MCP serversmcp()External MCP server tools should become model-facing Agent tools.
Web searchwebSearch()The Agent needs model web search or normalized web search/read tools.
Fetch toolsfetch()The Agent needs named HTTP tools for developer-approved endpoints.
Transcriptiontranscribe()Audio input parts should become text before model execution.
Durable memorymemory()The Agent needs scoped durable records across invocations.
LLM routingllmRoute()A pre-invocation model decision should choose one developer-defined route.
LLM gatellmGate()A pre-invocation model decision should allow or reject the request.
Rate limitrateLimit()A trusted invocation budget should be checked or consumed before the Agent runs.
Chat titlechatTitle()Chat streams and finish extensions should include a generated conversation title.
Chat summarychatSummary()A summary command should replace explicit input with a conversation summary.
Usage telemetryusageTelemetry()Agent Usage Records should be normalized, emitted, or attached to output.

Read capability pages first

Each capability page starts with installation and configuration, then shows runtime behavior, requirements, driver support, options, inspection path, and related reference links. Avoid copying option shapes between Capabilities unless the public factory exposes the same type.

Copyright © 2026