hlvm serve exposes the local runtime host for GUI clients and local tools.
hlvm serve
Default host:
http://127.0.0.1:11435
| Method | Path | Purpose |
|---|---|---|
GET | /health | Runtime health check |
POST | /api/chat | Chat, eval, and agent submissions |
GET | /api/chat/messages | Current conversation messages |
GET | /api/chat/stream | Server-sent conversation events |
curl -X POST http://127.0.0.1:11435/api/chat \
-H "Content-Type: application/json" \
-d '{"mode":"eval","messages":[{"role":"user","content":"(+ 1 2)"}]}'
curl -X POST http://127.0.0.1:11435/api/chat \
-H "Content-Type: application/json" \
-d '{"mode":"chat","messages":[{"role":"user","content":"hello"}]}'
The runtime host is not the local LLM engine. HLVM's managed local AI endpoint
is 127.0.0.1:11439, and HLVM owns that path.