import useDocusaurusContext from '@docusaurus/useDocusaurusContext';
import { DISCORD_URL } from '@site/src/constants.ts'
This page answers some common questions about Kilo Code.
Kilo Code is an open-source AI agent extension for Visual Studio Code. It helps you write code more efficiently by generating code, automating tasks, and providing suggestions.
Kilo Code uses large language models (LLMs) to understand your requests and translate them into actions. It can:
You interact with Kilo Code through a chat interface, where you provide instructions and review/approve its proposed actions, or you can use the inline autocomplete feature which helps you as you type.
Kilo Code can help with a variety of coding tasks, including:
The Kilo Code extension itself is free and open-source. In order for Kilo Code to be useful, you need an AI model to respond to your queries. Models are hosted by providers and most charge for access.
There are some models available for free. The set of free models if constantly changing based on provider pricing decisions.
You can also use Kilo Code with a local model or "Bring Your Own API Key" for another model provider (like Anthropic, OpenAI, OpenRouter, Requesty, etc.).
If you choose to pay for models via Kilo Code, you do so by buying Kilo Credits. You can purchase Kilo Credits and receive bonus credits. We do not charge a markup on Kilo Credits. $1 you give us is $1 in Kilo Credits.
Model usage is metered by the providers in terms of different kinds of tokens. When you use a model, we debit your Kilo credits by the amount the provider charges us -- with no markup.
You can use any models you like as long as you have credits in your account. When you run out of credits, you can add more. It's that simple!
If you're looking to earn some credits, you could join our Discord where we sometimes have promotional offers!
Kilo Code is a powerful tool, and it's important to use it responsibly. Here are some things to keep in mind:
See the Installation Guide for detailed instructions.
Kilo Code supports a wide range of API providers, including:
Each API provider has its own process for obtaining an API key. See the Setting Up Your First AI Provider for links to the relevant documentation for each provider.
Yes, Kilo Code supports running models locally using Ollama and LM Studio. See Using Local Models for instructions.
Open the Kilo Code panel () and type your task in the chat box. Be clear and specific about what you want Kilo Code to do. See The Chat Interface for best practices.
Use chat when you need to:
Use autocomplete when you need to:
In general, autocomplete is best for quick, in-flow coding assistance, while chat is better for larger tasks that require more context and interaction.
Modes are different personas that Kilo Code can adopt, each with a specific focus and set of capabilities. The built-in modes are:
Use the dropdown menu in the chat input area to select a different mode, or use the / command to switch to a specific mode.
Tools are how Kilo Code interacts with your system. Kilo Code automatically selects and uses the appropriate tools to complete your tasks. You don't need to call tools directly. You will be prompted to approve or reject each tool use.
Context mentions are a way to provide Kilo Code with specific information about your project, such as files, folders, or problems. Use the "@" symbol followed by the item you want to mention (e.g., @/src/file.ts, @problems).
Yes, if you are using a provider with a model that support web browsing. Be mindful of the security implications of allowing this.
Yes, Kilo Code can execute commands in your VS Code terminal. You will be prompted to approve each command before it's executed, unless you've enabled auto-approval for commands. Be extremely cautious about auto-approving commands. If you're experiencing issues with terminal commands, see the Shell Integration Guide for troubleshooting.
You can provide feedback by approving or rejecting Kilo Code's proposed actions. You can provide additional feedback by using the feedback field.
Yes, you can customize Kilo Code in several ways:
.clinerules Files: Create .clinerules files in your project to provide additional guidelines.Yes, Kilo Code has a few settings that when enabled will automatically approve actions. Find out more here.
Yes, if you use a local model.
MCP is a protocol that allows Kilo Code to communicate with external servers, extending its capabilities with custom tools and resources.
Yes, you can create your own MCP servers to add custom functionality to Kilo Code. See the MCP documentation for details. Yes, you can create your own MCP servers to add custom functionality to Kilo Code. See the MCP documentation for details.
The error message should provide some information about the problem. If you're unsure how to resolve it, seek help in the community forums.
Kilo Code uses VS Code's built-in file editing capabilities. You can use the standard "Undo" command (Ctrl/Cmd + Z) to revert changes. Also, if experimental checkpoints are enabled, Kilo can revert changes made to a file.
Please report bugs or suggest features on the Kilo Code Issues page and Feature Requests page.