Quickstart (5 minutes)

From zero to a verified artifact: install, point the runtime at a provider, run one goal, read the evidence.

Overview#

From zero to a verified artifact: install, point the runtime at a provider, run one goal, read the evidence.

1 · Install

npm install @mlola/browser-runtime
npx @mlola/browser-cli browser doctor      # every line should be green

2 · Providers — pick one

mlola browser config init                  # writes mlola.config.json

# { "providers": {
#     "decision":  { "provider": "typesafe", "model": "jev-latest" },
#     "reasoning": { "provider": "openrouter", "model": "openai/gpt-5.6-luna" } } }

# or stay with environment variables:
export TYPESAFE_API_KEY=...                # TypeSafe is the default fast path
export OPENROUTER_API_KEY=...              # one key also runs everything: --fast openrouter

3 · Run a goal

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

4 · Read the evidence

# the run prints status, verification and the artifact
npx @mlola/browser-cli browser trace show <runId>   # every decision, action and recovery
mlola browser config show                            # which routes resolved, credentials redacted