Human-in-the-Loop Task Manager for AI Agents
Checked October 30, 2026 | All YOLO Mode guides

How to Enable YOLO Mode in OpenHands

To run the OpenHands CLI in YOLO mode, start it with openhands --yolo, the short name for --always-approve. OpenHands then runs every action without asking. If you want something in between, --llm-approve lets an LLM security analyzer wave through the low-risk actions and only asks about the risky ones.

This page is one of our YOLO mode guides, and part of our guide to YOLO mode in every coding agent. Everything below was checked against the OpenHands CLI source and README (OpenHands/OpenHands-CLI, version 1.16.0, commit 283c6ac) on October 30, 2026.

Animated sketch of YOLO mode in AgentRQ: claude waits to run go test, YOLO is flipped on for the task, and every later edit and test run lands auto-allowed in the Trajectory view

What YOLO Mode Turns Off in OpenHands

OpenHands calls its approval setting a confirmation mode. There are three:

Mode Flag What it does
Always ask none, the default asks before every action
LLM approve --llm-approve an LLM rates each action, and only high-risk ones ask
Always approve --always-approve or --yolo never asks

YOLO turns the confirmation prompt off and nothing else. The CLI runs actions in your working directory on your own machine, so there is no local sandbox for YOLO to drop. The isolated sandboxes OpenHands mentions belong to OpenHands Cloud.

How to Enable YOLO Mode in OpenHands

bash 
openhands --yolo

--yolo and --always-approve are the same flag. Two other ways get you there too:

  • → In a session. Type /confirm to open the confirmation settings and pick Always approve actions (no confirmation).
  • → At a prompt. Answer Always when OpenHands asks about an action. It approves that action and switches the rest of the session to always approve. Auto LOW/MED switches it to LLM approve instead.

Headless runs (openhands --headless -t "...") always approve every action. The help text says so, and there is no way to make a headless run ask, because nobody is there to answer.

The Halfway Option

--llm-approve is OpenHands' middle ground. Its security analyzer rates each action, low- and medium-risk ones run on their own, and you only see the high-risk ones. Remember that the rating comes from a model, not from a fixed list, so read what it lets through.

How to Enable YOLO Mode in OpenHands Through AgentRQ

OpenHands' own YOLO switch covers a whole session. AgentRQ lets you make the decision per task, and answer from somewhere other than the terminal.

Approve From the AgentRQ Task Instead of the Terminal

Connect OpenHands to an AgentRQ workspace through the ACP Gateway (OpenHands setup guide):

bash 
npx @agentrq/acp-gateway@latest -- openhands acp

openhands acp starts in Always Ask mode unless you add --always-approve or --llm-approve, so leave those off. Over ACP the three confirmation modes show up as session modes: always-ask, always-approve and llm-approve. Only always-ask sends every action to you.

Each permission request now shows up in the AgentRQ task on the web, on your phone or in Slack. OpenHands asks about a batch of pending actions at once, under the title Confirm Agent Actions, with each action listed. Answer Allow Once, Always Allow or Deny from wherever you are, and OpenHands carries on. If nobody answers within 30 minutes, the gateway cancels the turn instead of guessing. Change the limit with --permission-timeout.

Turn On YOLO for One Task

Flip the YOLO toggle on a task, or when you create it, to put just that task in YOLO mode. Every permission request in it is approved automatically and OpenHands never waits, while every other task in the workspace still asks. Scheduled tasks, event triggers and workflow steps have the same switch, so an unattended job can run in YOLO while your interactive work stays supervised.

The YOLO toggle on a task in AgentRQ being switched on, then off again

Turn YOLO On or Off in Workspace Settings

To make YOLO the default for a whole workspace, open the workspace, go to Settings, choose the Automations tab and flip YOLO Mode (Execute All). Click Update Workspace to save. Switch it off the same way. The switch is off by default, and every permission request in the workspace is approved automatically while it is on.

Workspace Settings in AgentRQ: the YOLO Mode (Execute All) switch turned on and saved, then off and saved

A Safe YOLO Setup for OpenHands

  • → Treat Always Allow as YOLO. Every OpenHands request arrives under the same title, Confirm Agent Actions, so Always Allow on one of them is close to approving everything that follows. Use Allow Once unless you mean it.
  • → Leave the workspace-wide switch off. Turn YOLO on per task instead, so it never outlives the job you trusted.
  • → Bring your own sandbox. The CLI runs on your machine, so run YOLO tasks in a container, a VM or a throwaway clone.
  • → Commit first. Start every YOLO task from a clean git tree, so any change is one git reset away.
  • → Read the record. The tool call history lists every call the task made, including the ones that were auto-approved.

FAQ

How do I enable YOLO mode in OpenHands? Start the CLI with openhands --yolo, or openhands --always-approve. They are the same flag.

How do I turn on YOLO in a running OpenHands session? Type /confirm and choose always approve, or answer Always at the next confirmation prompt.

What does openhands --llm-approve do? It lets an LLM security analyzer approve low- and medium-risk actions and asks you only about high-risk ones.

Does OpenHands headless mode ask for approval? No. openhands --headless approves every action automatically.

Does the OpenHands CLI have a sandbox? No local one. It runs actions in your working directory. Use a container or a throwaway clone for YOLO runs.

How do I approve OpenHands actions remotely? Connect openhands acp to AgentRQ through the ACP Gateway. Its confirmation requests show up in the task on the web, your phone or Slack.

For every other agent, see what YOLO mode is and how to turn it on in every coding agent.

Start Free