---
title: "Getting Started with Mantis AI Controller"
description: "Install and configure Mantis AI Controller with live Claude hook routing, auto-updates, skills, and fail-closed checks."
---

# Getting Started with Mantis AI Controller

Install the Mantis controller for Claude Code with live hook routing, memory, skills, auto-updates, and fail-closed checks.

## Requirements

You need Claude Code (Anthropic's official CLI tool) and an Anthropic API key or subscription. The controller runs on Windows 10+ with WSL2 or native Linux. Docker Desktop is optional and only needed for cross-terminal coordination between multiple Claude sessions.

## Download

Private installs are generated from [https://erebora.org/mantis/](https://erebora.org/mantis/). The setup command installs the launcher, controller runtime, skills, update checks, and the Mantis Remote phone guide for Linux, macOS, or WSL.

## Installation

Installation is command-line based. The installer configures the `mantis` launcher, asks which backend to use, installs the bundled controller surface, and keeps itself ready for updates.

The live Claude side currently audits to 6 lifecycle events, 35 hook entries, 25 controller-owned entries, 20 registered handlers, 15 routed batches, and 37 explicit main-path checks.

## First Run

When the installer finishes, it asks whether you want to set up Mantis Remote, start Codex, start Claude, or skip remote setup for later.

- Android users get the native APK path first. It is the fastest phone-control option.
- iPhone and iPad users get the browser shortcut path. Open it in Safari, then use Share -> Add to Home Screen.
- Anyone can fall back to SSH/Tailscale and attach the same tmux session.

You can reopen the phone setup later:

```bash
mantis phone setup
```

Open any terminal and type `mantis`. The launcher asks whether you want Claude or Codex:

- Claude uses the live Claude controller surface.
- Codex uses the Mantis glue layer built for Codex.
- Startup checks for updates before launch.
- Skills and workflow instructions are installed with the runtime.

No phone setup is forced. Mantis does not silently enroll devices, change SSH rules, or open firewall access.

## The Workflow

This is how you work with Mantis AI Controller every day:

### 1. Describe Your Vision

Talk like an architect, not a bricklayer. Say what you want built, not how to build it. The system handles research, planning, and implementation details.

### 2. Answer Clarifying Questions

The AI asks focused multiple-choice questions, one at a time. These are generated by the Thinking Partner gate (97% confidence threshold) to ensure the AI understands your intent before writing code.

### 3. Review the Plan

Research happens automatically via specialist agents (scout, oracle). A structured plan is presented for your approval. No code is written until you explicitly approve.

### 4. Watch It Build

The system enters a TDD loop: write failing tests, implement minimum code, refactor. Sub-agents spawn in parallel for independent tasks. You see real-time progress.

### 5. Steer the Ship

Add features, change design direction, or pivot entirely while work is in progress. The gate system ensures every change follows the same research-plan-approve-build-test cycle.

## What to Expect

When you first use the controller, you will see messages that may be unfamiliar:

- **Gate messages** (teal or red text) that pause progress. These are safety checks, not errors. They ensure the AI has researched, planned, and received approval before editing your code.
- **Agent spawning messages** indicating specialist sub-agents are working on parts of your task in parallel.
- **Memory recall** showing relevant learnings from past sessions, ranked by TF-IDF relevance scoring.

## Related

- [Safety Gates](https://erebora.org/mantis/docs/safety-gates) -- How the live hook routing protects your code
- [Memory System](https://erebora.org/mantis/docs/memory-system) -- Cross-session learning and recall
- [Skills & Agents](https://erebora.org/mantis/docs/skills-and-agents) -- Skills, slash-command workflows, and agents
- [FAQ](https://erebora.org/mantis/docs/faq) -- Common questions answered
- [Live Documentation](https://erebora.org/mantis/) -- Full product page