Ollama and Dome

1. 01

   Add the connection

   Use the provider id openai_compatible and Ollama's /v1 URL. Ollama ignores API keys, so set no credential.

   $ dome models add gpt-oss-ollama \
     --provider openai_compatible \
     --endpoint http://ollama.internal.example.com:11434/v1 \
     --model gpt-oss:20b \
     --auth-method none --credential-type none \
     --attributes '{"env":"dev"}' \
     --gateway dev-gateway

2. 02

   Expose it to the Gateway

   Dome's hosted gateway can't see localhost or a private network. Ollama needs an address it can reach.

3. 03

   Pool it and call the Gateway

   Ollama goes first and vLLM second. Your client calls gpt-oss-20b with the agent's Dome key.

   $ dome models pool create gpt-oss-20b \
     --failover-max all --gateway dev-gateway
    
   $ dome models pool member add gpt-oss-20b gpt-oss-ollama --priority 0
   $ dome models pool member add gpt-oss-20b gpt-oss-vllm --priority 1

Commands and rules tested against a Dome workspace on October 1, 2026. For anything about Ollama itself, see Ollama's documentation.

forbid (principal, action == Dome::Action::"llm:invoke", resource is Dome::LLMModel)
when { resource has env && resource.env == "dev" };