MiMo Code Install Guide

Install or Verify Node.js

MiMo Code requires Node.js 18 or later.

brew install node@20
node --version  # should be v20 or higher

# In WSL terminal:
sudo apt update && sudo apt install nodejs npm -y
node --version  # should be v20 or higher

curl -fsSL https://deb.nodesource.com/setup_20.x | sudo -E bash -
sudo apt install -y nodejs
node --version  # should be v20 or higher

Install MiMo Code CLI

Two methods — pick one.

Method A: npm (recommended)

npm install -g @mimo-ai/cli

Method B: curl install script

curl -fsSL https://mimo.xiaomi.com/install.sh | bash

⚠️ Security tip: Always review install scripts before piping to bash. The official script is at GitHub.

Verify Installation

mimo --version

Expected output: @mimo-ai/cli v0.1.0 or similar.

Set Up Your Model Provider

Choose a provider and set environment variables:

Option A: OpenRouter (flexible, multi-model)

export MIMOCODE_PROVIDER=openai_compatible
export MIMOCODE_API_BASE=https://openrouter.ai/api/v1
export MIMOCODE_API_KEY=your-openrouter-key
export MIMOCODE_MODEL=anthropic/claude-sonnet-4-20250514

Option B: DeepSeek (affordable)

export MIMOCODE_PROVIDER=openai_compatible
export MIMOCODE_API_BASE=https://api.deepseek.com
export MIMOCODE_API_KEY=your-deepseek-key
export MIMOCODE_MODEL=deepseek-chat

Option C: Local (private, free)

# Start Ollama first: ollama serve
# Then pull a model: ollama pull qwen2.5-coder:14b

export MIMOCODE_PROVIDER=openai_compatible
export MIMOCODE_API_BASE=http://localhost:11434/v1
export MIMOCODE_API_KEY=ollama
export MIMOCODE_MODEL=qwen2.5-coder:14b

Launch MiMo Code in Your Project

cd /path/to/your/project
mimo

On first run, MiMo Code will initialize its configuration. Run /init to set up the project context.

Optional: Security Hardening

Disable telemetry if you prefer privacy:

export MIMOCODE_ENABLE_ANALYSIS=false

Add environment variables to your shell profile (~/.zshrc, ~/.bashrc) for persistence.