Runtimes

Chat with a running runtime agent

Human-only. Proxies to the runtime container's OpenAI-compatible POST /v1/chat/completions (hermes / openclaw / openclaude / opencode chat bridge). Starts the runtime if stopped. Streams SSE when Accept: text/event-stream or stream: true. Conversation history is ephemeral (pass messages). Requires a public URL (shell access, Shroud sidecar, or HTTP hosting).

post/v1/runtimes/{runtimeId}/chat

Request

  • Base URL: https://api.1claw.co
  • URL: https://api.1claw.co/v1/runtimes/{runtimeId}/chat
  • Auth: HTTP bearer

Path parameters

runtimeIdstring uuid required

Request body

messagestring

Latest user message

messagesobject[]

OpenAI chat messages (optional history)

modelstring
providerstring
streamboolean

Request SSE streaming (default true when Accept is text/event-stream)

Response

Chat completion (JSON) or SSE stream

object required

Changes

No recorded changes to this operation across all 1 revision of this API.