Run the AI where you want — cloud, local, or your own servers

The Deputy and Posse are provider-agnostic — the SAME features run wherever you point them. The heavy compute lives wherever the model runs, so your workstation only needs a big spec when the model runs ON it.

1) CLOUD (bring your own key) — Anthropic / OpenAI / Gemini. Workstation stays minimal; secrets are redacted before anything is sent. Fastest to start, top model quality.

2) LOCAL (Ollama on this workstation) — fully private, works offline, but this box needs ~32 GB + a GPU (see 'What SubnetSlinger needs').

3) YOUR OWN INFERENCE SERVER (private) — point the Deputy at a server on your network and every workstation you point at it runs at the minimum spec:

• Ollama: set the Ollama Host to your server, e.g. http://ollama.lan:11434 (server: OLLAMA_HOST=0.0.0.0:11434).
• Any OpenAI-compatible endpoint: pick the OpenAI-compatible provider and set the Base URL to your endpoint —

self-hosted vLLM / LM Studio, Azure OpenAI, or an enterprise model-serving platform (e.g. a Databricks

serving endpoint). Set base URL + key + model.

4) YOUR DATA (MCP) — connect the Deputy to your systems of record over MCP so it reasons over YOUR network data: ServiceNow, Cisco DNAC, NetBox, a CMDB, or a SQL source. Today this is a generic MCP server you configure in the Deputy's MCP panel; a one-click connector catalog is planned.

PRIVACY & REDACTION: secrets (passwords, SNMP/TACACS+/RADIUS keys) are ALWAYS masked in the copy sent to the model — every backend is treated the same, cloud or local Ollama. You still see the real values in the transcript; only the model's copy is scrubbed, so nothing sensitive leaks into what the model sees or into a saved transcript, Incident, or export.

SPEC NOTE: cloud AI and any inference you host elsewhere keep the workstation at the MINIMUM spec — only a model running locally on the box needs the 32 GB + GPU. Put ONE GPU server on your network and keep every workstation you point at it at the minimum spec.