CLI reference
The commands of the mlola browser CLI and their flags.
Overview#
| Command | What it does |
|---|---|
| mlola browser run | Execute a goal (flags below) or a task JSON file |
| mlola prove <contract.json> | Prove a change against its approved contract and write a signed proof (exit 0 proven, 1 not proven, 3 not proven yet) |
| mlola contract check <file> | Validate a contract; print its digest and how much a machine can check |
| mlola browser verify --url|--cdp … | Judge browser work another agent, script or person did; no model, acts on nothing |
| mlola receipt check|show|keygen | Recheck a receipt or proof offline, print it as Markdown, or create a signing key |
| mlola browser doctor | Check Node, key, browser, runtime home and daemon |
| mlola browser sessions [list|show <id>] | List recent runs / inspect one run |
| mlola browser trace show <id> [--type T] | Print the event log (filterable) |
| mlola browser trace summary <id> | Metrics as JSON |
| mlola browser eval --suite core|matrix|security|regression|stress|all | Run the deterministic eval corpus |
| mlola browser daemon start|stop|status | Manage the local daemon |
| mlola browser extension status | Inspect the browser-extension bridge |
| mlola browser config init|show | Write or inspect mlola.config.json; shows resolved routes and where each credential came from |
| mlola browser profiles | List managed browser profiles |
run flags#
| Flag | Meaning |
|---|---|
| --goal "…" | The task, in plain language |
| --url <url> | Start page |
| --task <file.json> | Task specification file (see Task file & boundaries) |
| --provider typesafe|keyword | Decision provider |
| --llm openrouter|openai|custom|none | Stronger model for ESCALATE and planning |
| --llm-model <id> | Model id for that provider |
| --llm-api-key <key> | Credential for that provider, instead of exporting it |
| --fast typesafe|openrouter|keyword | Which fast path to use (default: typesafe) |
| --fast-model <id> / --fast-api-key <key> / --fast-base-url <url> | Override the fast path |
| --llm-base-url <url> | Custom endpoint (Azure, gateways, local servers) |
| --planner-model/-api-key/-base-url | Same, for the planner role |
| --model <id> | Override the fast-path model id |
| --browser chrome|chromium|msedge | Browser channel |
| --browser-extension | Drive your own Chrome through the loaded extension |
| --headless | Run without a visible window |
| --profile <dir> | Persistent browser profile |
| --cdp <url> | Attach to an existing Chrome (e.g. http://127.0.0.1:9222) |
| --policy <file.json> | Policy configuration file |
| --stop-before "…, …" | Stop at the requested boundary instead of doing it |
| --max-steps <n> | Step budget for this run |
| --screenshot off|on-failure|always | Screenshot policy (default on-failure) |
| --yes | Auto-approve approval-required actions |
| --no-human | Disable human help (unattended) |
| --json / --quiet | Machine-readable result / summary only |