Kilo CLI integration guide

Developer toolCLI toolUpdated: 2026-04-17

Introduction

Kilo CLI is an open-source terminal AI coding tool that helps you write, debug and refactor code conversationally from the command line. Point it at the SeaWhale AI API and you can use Claude, GPT-5, Qwen and other powerful models.

Key capabilities

💻 Code generation — generate code from a natural language description
🐛 Debugging — locate and fix bugs quickly
♻️ Refactoring — improve code structure and performance
🧪 Test generation — generate test cases for your functions
🔍 Code explanation — make sense of complex logic
🚀 Many languages — Python, JavaScript, Java, Go and more

Why SeaWhale AI?

Advantage	Description
🌐 Direct access	Reachable directly, stable connectivity
💰 Flexible billing	Pay as you go, no subscription required
⚡ High performance	Low latency, fast responses
🔒 Data security	Code is not stored, protecting your privacy
🤖 Many models	Claude, GPT-5, Qwen and more
🆓 New user credit	New accounts receive free credit

Supported models

SeaWhale AI supports many leading models, and you can switch between them freely in Kilo CLI:

Family	Recommended model	Strengths	Best for
Claude Sonnet	`claude-sonnet-4-6`	Strong at code, accurate reasoning, 200K context	Complex projects, refactoring
Claude Opus	`claude-opus-4-7`	Highest capability, deep reasoning	Architecture, complex algorithms
Claude Haiku	`claude-haiku-4-5-20251001`	Great value, low latency	Everyday work, code completion
GPT-5	`gpt-5.4`	Strong multimodal, well balanced	Everyday work, varied tasks
DeepSeek	`deepseek-v3`	Flagship open model, excellent at code	Coding tasks
Qwen	`qwen-max`	Strong in Chinese, fast responses	Chinese-language projects

Choosing a model

Deep engineering and architecture: claude-opus-4-7 or claude-sonnet-4-6, for complex algorithms and system design
Everyday coding assistance: claude-sonnet-4-6 or deepseek-v3, for good value
Lightweight tasks: claude-haiku-4-5-20251001, for fast, inexpensive responses

Before you begin

1. Get a SeaWhale AI API key

Open the SeaWhale AI console
Sign up and log in
Generate an API key on the API management page
Make sure your account has enough balance or free credit

New user credit

New SeaWhale AI accounts receive free starter credit, usable across all model inference services.

2. System requirements

Item	Requirement
Operating system	macOS 10.15+, Windows 10+, Linux
Node.js	v18.0 or later
npm	v7.0+
Terminal	A modern terminal with color support

Checking your Node.js version

bash

node -v

Version v18.x.x or later meets the requirement. If Node.js is missing, download it from the Node.js website.

Installing Kilo CLI

Global install

bash

npm install -g @kilocode/cli

Verify the installation

bash

kilo --version

A version number means the install succeeded.

Installation notes

If installation fails, check that Node.js is version 18 or later
To speed up npm, you can switch registries: npm config set registry https://registry.npmmirror.com
On macOS/Linux, permission errors can be resolved with sudo npm install -g @kilocode/cli

Configuring SeaWhale AI

Kilo CLI connects to model services through the ~/.config/kilo/config.json file.

Step 1: open the config file

macOS/LinuxWindows

bash

vim ~/.config/kilo/config.json

powershell

notepad %APPDATA%\kilo\config.json

Step 2: add the SeaWhale AI configuration

Paste the following into the config file, replacing sk-xxxxxxxxxxxxxxxx with your SeaWhale AI API key:

Basic (Claude)Multiple models

json

{
  "$schema": "https://kilo.ai/config.json",
  "provider": {
    "seawhale": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "SeaWhale AI",
      "options": {
        "baseURL": "https://api.atalk-ai.com/v1",
        "apiKey": "sk-xxxxxxxxxxxxxxxx"
      },
      "models": {
        "claude-sonnet-4-6": {
          "name": "claude-sonnet-4-6"
        },
        "claude-opus-4-7": {
          "name": "claude-opus-4-7"
        },
        "claude-haiku-4-5-20251001": {
          "name": "claude-haiku-4-5-20251001"
        }
      }
    }
  }
}

json

{
  "$schema": "https://kilo.ai/config.json",
  "provider": {
    "seawhale": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "SeaWhale AI",
      "options": {
        "baseURL": "https://api.atalk-ai.com/v1",
        "apiKey": "sk-xxxxxxxxxxxxxxxx"
      },
      "models": {
        "claude-sonnet-4-6": {
          "name": "claude-sonnet-4-6"
        },
        "claude-opus-4-7": {
          "name": "claude-opus-4-7"
        },
        "claude-haiku-4-5-20251001": {
          "name": "claude-haiku-4-5-20251001"
        },
        "gpt-5.4": {
          "name": "gpt-5.4"
        },
        "deepseek-v3": {
          "name": "deepseek-v3"
        }
      }
    }
  }
}

Notes

Replace sk-xxxxxxxxxxxxxxxx with your real SeaWhale AI API key
Restart Kilo CLI after saving for the changes to take effect
Keep your API key safe and never commit it to a repository
Add more models under models as needed — see the model list for everything available

Step 3: start and select a model

Save the config, restart Kilo CLI, type /models, search for SeaWhale AI and pick the model you want.

Kilo CLI model selection

Getting started

Starting Kilo CLI

bash

cd your-project    # Change into your project
kilo               # Start Kilo CLI

Kilo CLI chat interface

TIP

Kilo CLI uses the current directory as project context, so start it in the right place.

Common commands

Command	What it does
`/models`	Browse and switch models
`/clear`	Clear conversation history
`/help`	Show help

Worked examples

Example 1: code generation

👤 User:
Write a TypeScript function that deduplicates an array and sorts it ascending

🤖 Kilo CLI:
function deduplicateAndSort(arr: number[]): number[] {
  return [...new Set(arr)].sort((a, b) => a - b);
}

// Example
console.log(deduplicateAndSort([3, 1, 4, 1, 5, 9, 2, 6, 5]));
// Prints: [1, 2, 3, 4, 5, 6, 9]

Example 2: debugging

👤 User:
Why is the Promise result always undefined here?
async function fetchData() {
  fetch('https://api.example.com/data').then(res => res.json());
}

🤖 Kilo CLI:
The async function never returns the result of fetch(). Here is the fix:
async function fetchData() {
  return fetch('https://api.example.com/data').then(res => res.json());
}
// Or with await:
async function fetchData() {
  const res = await fetch('https://api.example.com/data');
  return res.json();
}

Example 3: generating unit tests

👤 User:
Generate unit tests for this function:
function add(a: number, b: number): number {
  return a + b;
}

Kilo CLI generates complete Jest or Vitest test cases covering normal values, boundary values, negative numbers and similar cases.

FAQ

Q1: I get an error or no response after connecting

Possible causes and fixes:

Wrong API key — sign in to the SeaWhale AI console, regenerate the key and copy it again
Wrong baseURL — confirm it is https://api.atalk-ai.com/v1 (note the trailing /v1)
Wrong model name — check the model ID against the model list
Insufficient balance — check your balance in the console and top up

Q2: How do I switch models?

Type /models, search by name (for example claude or gpt-5) and select the model you want.

If the model is missing, add it under models in the config file and restart Kilo CLI.

Q3: How do I add more models?

Add entries under models in the config file:

json

"models": {
  "claude-sonnet-4-6": {
    "name": "claude-sonnet-4-6"
  },
  "gpt-5-mini": {
    "name": "gpt-5-mini"
  }
}

Save and restart Kilo CLI, and the new models appear under /models.

Q4: How do I update Kilo CLI?

bash

npm install -g @kilocode/cli@latest

Q5: Which programming languages are supported?

Kilo CLI supports all mainstream programming languages:

Supported languages

Web development: JavaScript, TypeScript, HTML, CSS, Vue, React

Backend development: Python, Java, Go, Rust, C/C++, C#, PHP, Ruby

Mobile development: Swift, Kotlin, Dart (Flutter)

Data science: Python (NumPy/Pandas), R, SQL

Other: Shell, YAML, JSON, Markdown

Error codes

HTTP status	Meaning	How to fix
401	API key auth failed	Check the API key; confirm baseURL is `https://api.atalk-ai.com/v1`
403	Insufficient permission	Check API key permissions and model access
429	Rate limited	Wait a moment and retry, or increase your account quota
500	Server error	Retry later, or contact support

📚 Quick start — SeaWhale AI API basics
🎯 Model list — every available model
🔧 API reference — the complete API documentation

Other AI coding tools

Tool	Platform	Characteristics
Kilo CLI	CLI	Open source, flexible configuration, terminal-based
Claude Code	CLI	Official Anthropic tool, deep code understanding
OpenCode	CLI	Lightweight, open source, easy to pick up
Cline	VSCode	IDE extension, plans and runs multi-step tasks

Support

Channel	Response time	Best for
📖 Documentation	Immediate	Common questions
💬 Live support	Weekdays 9:00–18:00	Real-time technical questions
📧 Email support	Within 24 hours	Detailed reports and feedback

🏠 Back to home
🔑 Get an API key

Last updated 2026-04-17

Kilo CLI integration guide ​

Introduction ​

Key capabilities ​

Why SeaWhale AI? ​

Supported models ​

Before you begin ​

1. Get a SeaWhale AI API key ​

2. System requirements ​

Installing Kilo CLI ​

Global install ​

Verify the installation ​

Configuring SeaWhale AI ​

Step 1: open the config file ​

Step 2: add the SeaWhale AI configuration ​

Step 3: start and select a model ​

Getting started ​

Starting Kilo CLI ​

Common commands ​

Worked examples ​

Example 1: code generation ​

Example 2: debugging ​

Example 3: generating unit tests ​

FAQ ​

Q1: I get an error or no response after connecting ​

Q2: How do I switch models? ​

Q3: How do I add more models? ​

Q4: How do I update Kilo CLI? ​

Q5: Which programming languages are supported? ​

Error codes ​

Related resources ​

Other AI coding tools ​

Support ​

Kilo CLI integration guide

Introduction

Key capabilities

Why SeaWhale AI?

Supported models

Before you begin

1. Get a SeaWhale AI API key

2. System requirements

Installing Kilo CLI

Global install

Verify the installation

Configuring SeaWhale AI

Step 1: open the config file

Step 2: add the SeaWhale AI configuration

Step 3: start and select a model

Getting started

Starting Kilo CLI

Common commands

Worked examples

Example 1: code generation

Example 2: debugging

Example 3: generating unit tests

FAQ

Q1: I get an error or no response after connecting

Q2: How do I switch models?

Q3: How do I add more models?

Q4: How do I update Kilo CLI?

Q5: Which programming languages are supported?

Error codes

Related resources

Other AI coding tools

Support