OpenAI's family covers the full range from cheap general-purpose models to premium reasoning. GPT-4o is the workhorse for most agent tasks, with native vision when you need it. The o1 family ships chain-of-thought reasoning that helps for math-heavy or multi-step planning tasks where you want the model to think before acting.
app.yaml1brain:2 provider: openai3 model: gpt-4o4 credential:5 ref: openai_main6 scope: per_user7 provider: openai8 config:9 api_key: "{{env.OPENAI_API_KEY}}" # dev fallback10 temperature: 0.211 max_tokens: 4096Register your 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 openai \
--label openai_main \
--scope per_user \
-f api_key=...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 OpenAI credential in the vault
digitorn credentials create --provider openai --label 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.