---
title: "How to Enable YOLO Mode in Junie | AgentRQ Guidelines"
url: https://agentrq.com/guidelines/yolo-mode/junie
description: "Junie calls YOLO mode Brave mode. Start junie --brave, or cycle /brave or Ctrl+B through Off, Auto and On. The allowlist, sandbox and AgentRQ."
---

![](https://agentrq.com/assets/agent-icons/junie.png) Checked October 30, 2026 | [All YOLO Mode guides](https://agentrq.com/guidelines/yolo-mode/)

# How to Enable YOLO Mode in Junie

JetBrains' Junie calls its YOLO mode **Brave mode**. In the Junie CLI, start it with `junie --brave`, or press **Ctrl+B** (or type `/brave`) in a running session. In a JetBrains IDE, pick **Brave** in Junie's chat input. JetBrains itself does not recommend Brave mode, and its docs point you to the Action Allowlist instead.

This page is one of our [YOLO mode guides](https://agentrq.com/guidelines/yolo-mode/), and part of our guide to [YOLO mode in every coding agent](https://agentrq.com/blog/what-is-yolo-mode-and-how-to-turn-it-on-in-every-coding-agent). Everything below was checked against the Junie CLI docs at junie.jetbrains.com, the JetBrains AI Assistant 2026.2 help, and Junie release 3893.6 in the ACP registry 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](https://agentrq.com/assets/sketches/yolo-mode.svg)

## What Brave Mode Turns Off in Junie

Without Brave mode, Junie asks before potentially sensitive actions, such as most terminal commands, editing files outside the project and invoking MCP tools. Brave mode runs all of them without asking.

It does not turn off the sandbox, which is a separate switch (see below).

## How to Enable Brave Mode in Junie

In the CLI, Brave mode has three levels, and `/brave` or **Ctrl+B** cycles through them:

| Level | What happens |
| --- | --- |
| Off | Asks for every sensitive action not on the Action Allowlist |
| Auto | A safety check approves terminal commands it considers safe, and asks about the rest |
| On | Runs every sensitive action without asking |

bash

```bash
junie --brave
```

`--brave` starts the CLI with Brave mode on and works in interactive mode only. In a JetBrains IDE the same three choices are called **Safe**, **Auto** and **Brave**.

For unattended runs, `--act-as-interactive` runs a task with the interactive tools but never asks the user anything. Junie's docs also say non-interactive runs treat the project as trusted, so only run them in projects you trust.

### The Halfway Option: the Action Allowlist

When Junie asks, answer **Always allow** to add that command to the **Action Allowlist**, and it runs without asking in later sessions. The list lives in `~/.junie/allowlist.json`. It has `rules` for five kinds of action (`executables`, `fileEditing`, `mcpTools`, `readOutsideProject`, `readSecretFile`), each rule a `prefix` or glob `pattern` with an `allow` or `ask` action, matched top to bottom. `"defaultBehavior": "ask"` and `"allowReadonlyCommands": true` set the fallback.

**Auto** is the other middle ground: safe-looking commands run, the rest still ask.

## Junie's Sandbox

Junie CLI has a sandbox mode on macOS and Linux (not Windows). Start it with `junie --sandbox`, or toggle it with `/sandbox` for the current session. It wraps the agent's terminal commands and limits where its edit tools can write. Network access is open by default, and JetBrains says it is not hardened isolation like a container or VM. ACP clients get `/sandbox` and a **Sandbox** session option too.

## How to Enable YOLO Mode in Junie Through AgentRQ

Brave mode belongs to one terminal or IDE window. AgentRQ lets you make the decision per task, and answer from somewhere else.

### Approve From the AgentRQ Task Instead of the Terminal

Connect Junie to an AgentRQ workspace through the [ACP Gateway](https://agentrq.com/docs/connect-acp-agent) ([Junie setup guide](https://agentrq.com/docs/agents/junie)):

bash

```bash
npx @agentrq/acp-gateway@latest --agent junie
```

The gateway starts `junie --acp=true` without `--brave`. Leave Brave mode off and keep the allowlist short, or Junie approves actions before AgentRQ sees them.

Junie's ACP server is closed source, so we could not read exactly which actions it sends to the client for approval. Where it does ask, the request shows up in the AgentRQ task on the web, on your phone or in Slack, together with the command it is about. Answer **Allow Once**, **Always Allow** or **Deny** from wherever you are, and Junie 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](https://agentrq.com/features/yolo-mode). Every permission request in it is approved automatically and Junie never waits, while every other task in the workspace still asks. [Scheduled tasks](https://agentrq.com/features/task-scheduling), [event triggers](https://agentrq.com/features/events) and [workflow](https://agentrq.com/features/workflows) 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](https://agentrq.com/assets/guidelines/yolo-mode-task-toggle.gif)

### 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](https://agentrq.com/assets/guidelines/yolo-mode-workspace-settings.gif)

### A Safe YOLO Setup for Junie

- → **Allow the boring tools, not everything.** **Always Allow** adds the tool to the workspace's auto-approved list, so the routine calls stop asking and the risky ones still do. Prune that list in workspace settings now and then.
- → **Leave the workspace-wide switch off.** Turn YOLO on per task instead, so it never outlives the job you trusted.
- → **Turn on the sandbox.** Junie's sandbox mode is lighter than a container, but it keeps writes in bounds. For real isolation, run YOLO tasks in a container 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](https://agentrq.com/features/tool-call-history) lists every call the task made, including the ones that were auto-approved.

## FAQ

**Does Junie have a YOLO mode?** Yes, it is called Brave mode. Start the CLI with junie --brave, or press Ctrl+B or type /brave in a session.

**What are Junie's Off, Auto and On levels?** Off asks for every sensitive action not on the allowlist. Auto approves terminal commands a safety check considers safe. On runs everything without asking.

**Where is Junie's allowlist?** In ~/.junie/allowlist.json. Answering Always allow at a prompt adds the command to it.

**Does Junie have a sandbox?** Yes, on macOS and Linux. Start it with junie --sandbox or toggle /sandbox. It is not a container or VM.

**How do I approve Junie actions remotely?** Connect Junie to [AgentRQ](https://agentrq.com) through the ACP Gateway. Its permission 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](https://agentrq.com/blog/what-is-yolo-mode-and-how-to-turn-it-on-in-every-coding-agent).