Build AI agents on DeepSeek in YAML

DeepSeek changed the cost calculus for agent setups in late 2025. V3 handles general coordination tasks credibly at a fraction of frontier pricing, and R1 ships strong reasoning. For exploration agents, fact-checkers, classifiers, anything that produces text the user does not directly read, DeepSeek is often the right default.

Models worth knowing about

Drop into your app.yaml

1brain:2  provider: deepseek3  model: deepseek-chat4  backend: openai_compat5  credential:6    ref: deepseek_main7    scope: per_user8    provider: deepseek9  config:10    api_key: "{{env.DEEPSEEK_API_KEY}}"   # dev fallback11    base_url: "https://api.deepseek.com/v1"12  temperature: 0.2

Register your DeepSeek 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 deepseek \
  --label deepseek_main \
  --scope per_user \
  -f api_key=...

Install Digitorn and chat with your DeepSeek agent

# 1. install the runtime
curl -sSL https://digitorn.ai/install | sh

# 2. register your DeepSeek credential in the vault
digitorn credentials create --provider deepseek --label deepseek_main -f api_key=...

# 3. install a starter agent and chat
digitorn install hub://digitorn/digitorn-code
digitorn chat digitorn-code