### macOS/Linux Setup Script Example

Source: https://kilo.ai/docs/automate/agent-manager

This script installs npm dependencies and conditionally copies a local environment file. It utilizes WORKTREE_PATH and REPO_PATH environment variables.

```shell
#!/bin/sh
set -e

cd "$WORKTREE_PATH"
npm install

# Copy a nested env file that Kilo does not auto-copy.
if [ -f "$REPO_PATH/apps/web/.env.local" ] && [ ! -f "$WORKTREE_PATH/apps/web/.env.local" ]; then
  cp "$REPO_PATH/apps/web/.env.local" "$WORKTREE_PATH/apps/web/.env.local"
fi

```

--------------------------------

### Quick Local Qdrant Setup with Docker

Source: https://kilo.ai/docs/customize/context/codebase-indexing

Use this Docker command for a quick local setup of a Qdrant server. Ensure Docker is installed and running on your system.

```bash
docker run -p 6333:6333 qdrant/qdrant

```

--------------------------------

### macOS/Linux Run Script Example

Source: https://kilo.ai/docs/automate/agent-manager

A basic script to start a development server using npm. This script is executed from the Agent Manager toolbar.

```shell
#!/bin/sh
npm run dev

```

--------------------------------

### Start Ollama Server

Source: https://kilo.ai/docs/ai-providers/ollama

Run this command in your terminal to start the Ollama server. Ensure Ollama is installed and running before proceeding.

```bash
ollama serve

```

--------------------------------

### Install Dependencies

Source: https://kilo.ai/docs/gateway/quickstart

Install the required AI SDK and OpenAI provider packages.

```bash
npm install ai @ai-sdk/openai dotenv
```

--------------------------------

### Install AgentCard CLI and Sign Up

Source: https://kilo.ai/docs/kiloclaw/tools/agentcard

Use this command to install the AgentCard CLI and create a new account.

```bash
agent-cards signup
```

--------------------------------

### Start Local Backend

Source: https://kilo.ai/docs/contributing/development-environment

Start the local backend for API validation. Use the root TESTING.md guide for detailed instructions on validating behavior with `curl` requests.

```bash
bun dev serve

```

--------------------------------

### Install Kilo CLI

Source: https://kilo.ai/docs

Install the Kilo CLI globally using npm.

```bash
# Or install via CLI
$ npm install -g @kilocode/cli
```

--------------------------------

### Install OpenAI SDK (Python)

Source: https://kilo.ai/docs/gateway/sdks-and-frameworks

Install the OpenAI SDK using pip. This is a prerequisite for using the SDK.

```bash
pip install openai

```

--------------------------------

### Install Project Dependencies

Source: https://kilo.ai/docs/contributing/development-environment

Install all necessary dependencies for the project's workspace packages using Bun.

```bash
bun install
```

--------------------------------

### Install OpenAI SDK (TypeScript/JavaScript)

Source: https://kilo.ai/docs/gateway/sdks-and-frameworks

Install the OpenAI SDK using npm. This is a prerequisite for using the SDK.

```bash
npm install openai

```

--------------------------------

### Install Dependencies and Run Repo-Level Checks

Source: https://kilo.ai/docs/contributing/development-environment

Install project dependencies and run linting and type checking from the repo root.

```bash
bun install
bun run lint
bun run typecheck

```

--------------------------------

### Example: Download qwen3-coder:30b Model

Source: https://kilo.ai/docs/ai-providers/ollama

This is an example of downloading the recommended 'qwen3-coder:30b' model using the `ollama pull` command. Ensure the Ollama server is running.

```bash
ollama pull qwen3-coder:30b

```

--------------------------------

### Install Additional Tools at Runtime

Source: https://kilo.ai/docs/kiloclaw/pre-installed-software

Agents can install additional tools at runtime using language-specific package managers.

```bash
go install github.com/example/tool@latest
```

```bash
npm install -g <package>
```

```bash
pip install <package>
```

--------------------------------

### Install Git on macOS using Xcode Command Line Tools

Source: https://kilo.ai/docs/code-with-ai/features/checkpoints

Installs Git on macOS by installing the Xcode Command Line Tools. This is an alternative method to Homebrew.

```bash
xcode-select --install
```

--------------------------------

### Install Git on Fedora

Source: https://kilo.ai/docs/code-with-ai/features/checkpoints

Installs Git on Fedora Linux using the dnf package manager.

```bash
sudo dnf install git
```

--------------------------------

### Install a Plugin Globally

Source: https://kilo.ai/docs/automate/extending/plugins

Installs a plugin into the global configuration. This makes the plugin available across all projects.

```bash
kilo plugin my-plugin --global
```

--------------------------------

### Install Git on Arch Linux

Source: https://kilo.ai/docs/code-with-ai/features/checkpoints

Installs Git on Arch Linux using the pacman package manager.

```bash
sudo pacman -S git
```

--------------------------------

### Install Vercel AI SDK and OpenAI integration

Source: https://kilo.ai/docs/gateway/sdks-and-frameworks

Install the necessary packages for using the Vercel AI SDK with OpenAI compatibility.

```bash
npm install ai @ai-sdk/openai

```

--------------------------------

### Install FFmpeg on Linux (Ubuntu/Debian)

Source: https://kilo.ai/docs/code-with-ai/features/speech-to-text

Use apt to install FFmpeg on Ubuntu/Debian-based Linux systems. This is required for audio capture and processing for voice input.

```bash
sudo apt update
sudo apt install ffmpeg
```

--------------------------------

### Install Kilo Code VS Code Extension

Source: https://kilo.ai/docs

Install the Kilo Code VS Code Extension using the 'code' command.

```bash
# Install Kilo Code VS Code Extension
$ code --install-extension kilocode.kilo-code
```

--------------------------------

### Install a Plugin Locally

Source: https://kilo.ai/docs/automate/extending/plugins

Installs a plugin into the current project's configuration. The command resolves the package and updates the local config file.

```bash
kilo plugin my-plugin
```

--------------------------------

### Install Kilo Code CLI via npm

Source: https://kilo.ai/docs/code-with-ai/platforms/cli

Install the Kilo Code CLI globally using npm. This command makes the 'kilo' executable available system-wide.

```bash
npm install -g @kilocode/cli
```

--------------------------------

### First-Time Setup with /connect

Source: https://kilo.ai/docs/code-with-ai/platforms/cli

Use the /connect command within the Kilo TUI to add your first provider credentials and configure API keys for model providers.

```bash
kilo
/connect
```

--------------------------------

### Initialize Project

Source: https://kilo.ai/docs/gateway/quickstart

Create a new directory and initialize a Node.js project.

```bash
mkdir my-ai-app
cd my-ai-app
npm init -y
```

--------------------------------

### Fly-Provider Topology Example Flowchart

Source: https://kilo.ai/docs/contributing/architecture/cloud-platform

Visualizes the topology of a Fly-provider setup for KiloClaw, showing the interaction between Cloudflare Workers, Fly proxy, Fly instances, and persistent storage. It highlights the flow of authentication and traffic routing.

```flowchart
flowchart TB
  subgraph worker ["Cloudflare Worker"]
    direction LR
    auth["JWT auth<br/>tied to Kilo user"]
    instanceDO["Per-instance Durable Object"]
    dbConnection["Kilo database connection"]
  end

  db["Kilo database<br/>Instances<br/>Short-lived access codes<br/>Image catalog<br/>Billing and user preferences"]
  proxy["Fly proxy<br/>Per-user Fly app<br/>Per-user encryption<br/>Routes to pinned instance"]

  subgraph flyInstance ["Fly instance: owner-scoped runtime"]
    direction TB
    subgraph container ["KiloClaw container"]
      direction TB
      controller["KiloClaw controller<br/>Supervises OpenClaw gateway<br/>Exposes control endpoints<br/>Proxies HTTP and WebSocket traffic"]
      openclaw["OpenClaw<br/>Gateway and Control UI"]
      tools["Pre-installed tools and skills"]
      controller --> openclaw
      tools --> openclaw
    end
    volume["Persistent Fly volume<br/>/root/.openclaw config<br/>/root/clawd workspace"]
    volume --> openclaw
  end

  dbConnection <--> db
  worker <--> proxy
  proxy <--> controller


```

--------------------------------

### Verify Kilo Code CLI Installation

Source: https://kilo.ai/docs/code-with-ai/platforms/cli

After installation, verify that the Kilo Code CLI is installed correctly by checking its version. This command should output the installed version number.

```bash
kilo --version
```

--------------------------------

### Install Debian Packages via APT

Source: https://kilo.ai/docs/kiloclaw/pre-installed-software

Use apt to install additional system packages. Note that these installations do not persist across redeploys.

```bash
apt update && apt install -y <package>
```

--------------------------------

### Build and Test Documentation Locally

Source: https://kilo.ai/docs/contributing

Commands to test, build, and develop the Kilo documentation site locally from the repository root. Ensure you have Bun installed.

```bash
bun run --filter @kilocode/kilo-docs test
bun run --filter @kilocode/kilo-docs build
bun run --filter @kilocode/kilo-docs dev

```

--------------------------------

### Initialize OpenAI Client with ZenMux

Source: https://kilo.ai/docs/ai-providers/zenmux

Use the standard OpenAI SDK by setting the `baseURL` to ZenMux's OpenAI compatible endpoint. Ensure your ZenMux API key is provided.

```javascript
import OpenAI from "openai"

const openai = new OpenAI({
  baseURL: "https://zenmux.ai/api/v1",
  apiKey: "<ZENMUX_API_KEY>",
})

async function main() {
  const completion = await openai.chat.completions.create({
    model: "openai/gpt-5",
    messages: [
      {
        role: "user",
        content: "What is the meaning of life?",
      },
    ],
  })

  console.log(completion.choices[0].message)
}

main()

```

--------------------------------

### Run Documentation Site Commands

Source: https://kilo.ai/docs/contributing/development-environment

Execute these commands from the repo root to build, test, or run the documentation site locally. These are useful for development and previewing changes.

```bash
bun run --filter @kilocode/kilo-docs test
bun run --filter @kilocode/kilo-docs build
bun run --filter @kilocode/kilo-docs dev
```

--------------------------------

### Plugin Directory Structure Example

Source: https://kilo.ai/docs/automate/extending/plugins

Place TypeScript or JavaScript plugin files directly into a `plugin/` or `plugins/` folder within your Kilo configuration directories. These files are automatically registered at startup.

```tree
my-project/
├── kilo.json
└── .kilo/
    └── plugin/
        ├── env-guard.ts
        └── notifications.ts
```

--------------------------------

### Example Fix Commit Message

Source: https://kilo.ai/docs/code-with-ai/features/git-commit-generation

An example of a generated commit message for a bug fix, detailing the resolution.

```gitcommit
fix(api): resolve race condition in user data fetching

Add proper error handling and retry logic to prevent
concurrent requests from causing data inconsistency

```

--------------------------------

### Initialize Google GenAI Client with ZenMux

Source: https://kilo.ai/docs/ai-providers/zenmux

Set up the Google GenAI client for use with ZenMux by providing your API key, setting `vertexai: true`, and configuring the `httpOptions` with the ZenMux Vertex AI base URL and API version.

```javascript
const genai = require("@google/genai")

const client = new genai.GoogleGenAI({
  apiKey: "$ZENMUX_API_KEY",
  vertexai: true,
  httpOptions: {
    baseUrl: "https://zenmux.ai/api/vertex-ai",
    apiVersion: "v1",
  },
})

const response = await client.models.generateContent({
  model: "google/gemini-2.5-pro",
  contents: "How does AI work?",
})
console.log(response)

```

--------------------------------

### Cron Expression Examples

Source: https://kilo.ai/docs/kiloclaw/triggers/scheduled

Illustrative examples of cron expressions and their corresponding meanings, demonstrating various scheduling patterns.

```text
*/15 * * * * | Every 15 minutes
```

```text
0 9 * * 1-5 | 9:00 AM on weekdays
```

```text
0 0 1 * * | Midnight on the first of each month
```

```text
30 14 * * 3 | 2:30 PM every Wednesday
```

--------------------------------

### MCP Server Configuration with Environment Variable

Source: https://kilo.ai/docs/automate/mcp/using-in-cli

Example demonstrating how to use environment variables within MCP server configurations, such as for API keys in headers.

```json
{
  "mcp": {
    "my-server": {
      "type": "remote",
      "url": "https://mcp.example.com/mcp",
      "headers": {
        "Authorization": "Bearer {env:MY_API_KEY}"
      }
    }
  }
}
```

--------------------------------

### Example Docs Commit Message

Source: https://kilo.ai/docs/code-with-ai/features/git-commit-generation

An example of a generated commit message for documentation updates, specifying the changes made.

```gitcommit
docs(readme): update installation instructions

Add missing dependency requirements and clarify
setup steps for new contributors

```

--------------------------------

### Custom LSP Server Configuration

Source: https://kilo.ai/docs/code-with-ai/platforms/cli

Example of configuring a custom Language Server Protocol (LSP) server. This includes the command to run the server and an 'extensions' array specifying file types it should handle, unless disabling a built-in server.

```json
{
  "lsp": {
    "my-language-server": {
      "command": ["my-lsp", "--stdio"],
      "extensions": [".foo"],
    },
  },
}

```

--------------------------------

### Get Kilo CLI Help

Source: https://kilo.ai/docs/code-with-ai/platforms/cli

Opens the help documentation for the Kilo CLI, listing available commands and options.

```bash
kilo --help
```

--------------------------------

### Install Git on Debian/Ubuntu

Source: https://kilo.ai/docs/code-with-ai/features/checkpoints

Installs Git on Debian-based Linux distributions like Ubuntu using the apt package manager.

```bash
sudo apt update
sudo apt install git
```

--------------------------------

### Local Qdrant Setup with Docker Compose

Source: https://kilo.ai/docs/customize/context/codebase-indexing

Configure a local Qdrant server using Docker Compose. This method allows for more configuration options and persistent storage for the Qdrant data.

```yaml
version: "3.8"
services:
  qdrant:
    image: qdrant/qdrant
    ports:
      - "6333:6333"
    volumes:
      - qdrant_storage:/qdrant/storage
volumes:
  qdrant_storage:


```

--------------------------------

### Install Git on macOS using Homebrew

Source: https://kilo.ai/docs/code-with-ai/features/checkpoints

Installs Git on macOS using the Homebrew package manager. This is the recommended method.

```bash
brew install git
```

--------------------------------

### Install FFmpeg on macOS

Source: https://kilo.ai/docs/code-with-ai/features/speech-to-text

Use Homebrew to install FFmpeg on macOS. This is required for audio capture and processing for voice input.

```bash
brew install ffmpeg
```