OD
toolODS
Turns local hardware into a private AI stack with llama-server inference, chat, voice, RAG, automation, and operations tools.
What it provides
Connect an HTTPS inference API. Model weights stay on CPU/GPU infrastructure and are never installed inside the 4 GB bot.
Connection requirements
An ODS llama-server endpoint exposed through authenticated HTTPS
- Protocol
- OpenAI-compatible REST
- Endpoint
https://ods.example.com- Authentication
- Choose the mode required by your service
Example calls
Open official setup guide ↗get /v1/modelspost /v1/chat/completions {"model":"MODEL_ID","messages":[{"role":"user","content":"Hello"}]}Where to add it
Open Dashboard Tools, select a running OpenClaw or Hermes instance, then use the card’s Install or Connect action. External services may require an HTTPS endpoint and credentials; the dashboard shows those fields before anything is saved.