runtime

CopilotKit Runtime

@copilotkit/runtime is the server half of CopilotKit: it accepts AG-UI protocol requests, dispatches them to an AbstractAgent (built-in or external), runs the stream through an AgentRunner, and responds as Server-Sent Events.

This SKILL.md is the index. Read the reference under references/ that matches your task — do not try to absorb the whole package from this file.

Mental Model — the three dictionaries you hand to CopilotRuntime

new CopilotRuntime({
  agents, // Record<string, AbstractAgent>     — see wiring-external-agents or built-in-agent
  runner, // AgentRunner (optional)            — see agent-runners
  intelligence, // CopilotKitIntelligence (optional) — see intelligence-mode (auto-wires runner)
  mcpApps, // McpAppsConfig (optional)          — see wiring-mcp-apps-middleware
  a2ui, // A2UIConfig (optional)             — see packages/a2ui-renderer skill
  hooks, // { onRequest, onBeforeHandler }    — see middleware
  beforeRequestMiddleware,
  afterRequestMiddleware, // legacy — see middleware
  transcription, // TranscriptionService (optional)  — see transcription
});

You then mount it:

import { createCopilotRuntimeHandler } from "@copilotkit/runtime/v2";
const handler = createCopilotRuntimeHandler({
  runtime,
  basePath: "/api/copilotkit",
});
export default { fetch: handler };

When to load which reference

Invariants and gotchas (load-once, before any reference)

• createCopilotRuntimeHandler is the canonical primitive. createCopilotExpressHandler / createCopilotHonoHandler exist but are avoid at all costs — delegate from Express/Hono routes to the fetch primitive instead.
• publicLicenseKey is the canonical provider-side field. publicApiKey is a deprecated alias — expect to see it in legacy code, emit the canonical name in new code.
• Intelligence mode auto-wires IntelligenceAgentRunner. Passing both runner and intelligence to CopilotRuntime is rejected at construction.
• Intelligence mode targets the managed CopilotKit Intelligence service (api.cloud.copilotkit.ai) and is not self-hostable.
• hooks.onRequest runs before beforeRequestMiddleware (hook-based middleware wins for Response short-circuits). beforeRequestMiddleware runs after hooks.onRequest (see fetch-handler.ts:136-147).
• identifyUser (Intelligence) does not forward thrown Response objects — convert to 500. Gate auth rejection in hooks.onRequest, which does forward Responses.
• agents__unsafe_dev_only and selfManagedAgents are dev-only aliases of each other; do not reach for them in production. Either signals that the SPA is in dev mode.

Reading order for a first-time reader

1. setup-endpoint — the primitive.
2. built-in-agent or pick one from wiring-external-agents — the agent.
3. agent-runners — production persistence choice.
4. Optional: middleware, intelligence-mode, server-side-tools, transcription.