Fast path: Jev API key

Routine decisions are made by the fast path — TypeSafe Jev — which needs an API key.

Overview#

Routine decisions are made by the fast path — TypeSafe Jev — which needs an API key. Without a key you can still run everything with the offline baseline (--provider keyword), but that is a deterministic demo baseline, not the decision model.

Create a key at https://typesafe.ai (TypeSafe account → API keys).
Store it in the environment — pick one of the options below.
Verify with doctor until the "Jev fast path" line is green.

Option 1 — export in your shell (persists per session)

export TYPESAFE_API_KEY="tsk_..."
mlola browser doctor

Option 2 — make it permanent (zsh)

echo 'export TYPESAFE_API_KEY="tsk_..."' >> ~/.zshrc
source ~/.zshrc

Option 3 — inline for a single run (CI friendly)

TYPESAFE_API_KEY="tsk_..." npx @mlola/browser-cli browser run \
  --goal "Download my latest invoice" \
  --url https://billing.example.com/invoices

Option 4 — .env file (your runner must load it)

# .env
echo 'TYPESAFE_API_KEY=tsk_...' > .env
node --env-file=.env ./node_modules/.bin/mlola browser run --goal "..."

Option 5 — config file (recommended, nothing to export)

mlola browser config init          # writes mlola.config.json
mlola browser config show          # what the file says + what actually resolved

# and if you only have an OpenRouter key, the fast path runs on it too:
export OPENROUTER_API_KEY=...
mlola browser run --fast openrouter --goal "Download my latest invoice" --url https://...

Overriding the endpoint or model#

Variable	Default	Purpose
TYPESAFE_API_KEY	—	Jev credential (required for the fast path)
MLOLA_JEV_BASE_URL	https://api.typesafe.ai	API base URL
MLOLA_JEV_MODEL	jev-latest	Model id sent in the request
MLOLA_JEV_TIMEOUT_MS	20000	Per-request timeout

Choosing the decision provider#

Provider selection

mlola browser run --provider typesafe …   # fast path (needs a key)
mlola browser run --provider keyword  …   # offline baseline, no key required