serve-api
serve-api¶
Run an agent as an OpenAI-compatible completions API server.
This creates an OpenAI-compatible API server backed by a single agent. Model listing uses the agent's model discovery.
config¶
--host¶
Default: localhost Host to bind server to
--port¶
Default: 8000 Port to listen on
--cors¶
Default: True Flag Enable CORS
--agent¶
Name of specific agent to use (defaults to pool's default)
--show-messages¶
Flag Show message activity
--help¶
Flag Show this message and exit.