Azure OpenAI runs the same models as OpenAI's API, deployed in Microsoft's cloud regions with the compliance posture enterprises expect. Useful when SOC 2, HIPAA, FedRAMP, or regional data residency are non-negotiable. The deployment model is named-deployment-per-model, which the YAML maps onto cleanly.
app.yaml1brain:2 provider: azure_openai3 model: my-gpt4o-deployment # your Azure deployment name4 credential:5 ref: azure_openai_main6 scope: per_user7 provider: azure_openai8 config:9 api_key: "{{env.AZURE_OPENAI_API_KEY}}" # dev fallback10 endpoint: "{{env.AZURE_OPENAI_ENDPOINT}}"11 api_version: "2024-08-01-preview"Register your Azure OpenAI key once in the encrypted credential vault, then reference it from any agent by name. The runtime resolves the secret at session start, never bakes it into the app bundle, and rotates without redeploys.
# one-time setup: register the credential
digitorn credentials create \
--provider azure_openai \
--label azure_openai_main \
--scope per_user \
-f api_key=...\
-f endpoint=...credential: block (shown above). The legacy {{env.X}} template still works as a development fallback.# 1. install the runtime
curl -sSL https://digitorn.ai/install | sh
# 2. register your Azure OpenAI credential in the vault
digitorn credentials create --provider azure_openai --label azure_openai_main -f api_key=...
# 3. install a starter agent and chat
digitorn install hub://digitorn/digitorn-code
digitorn chat digitorn-codeEngineering notes from the Digitorn team. No marketing, no launch announcements, no "10 prompts that will change your life". Just the things we write that we'd want to read.