Question 1

What is Kilo Code?

Accepted Answer

Kilo Code is an open source AI coding agent that runs inside VS Code, JetBrains IDEs, and your terminal. It writes, debugs, refactors, and reviews code, automates multi-step tasks across your repo, and gives you direct access to 500+ AI models — including Claude, GPT, Gemini, DeepSeek, and local models via Ollama or LM Studio. Unlike closed alternatives, every prompt is visible, the source is Apache-2.0 licensed, and you can bring your own API keys at provider rates with no markup.

Question 2

Is Kilo Code free?

Accepted Answer

Yes. The VS Code extension, JetBrains plugin, and CLI are free to install and open source under the Apache-2.0 license. You can use Kilo with free models, bring your own API keys at zero markup, or top up pay-as-you-go credits that work across every surface — IDE, CLI, Cloud Agents, and App Builder. There is no mandatory subscription and no fixed seat price for individual developers.

Question 3

How do I install Kilo Code?

Accepted Answer

Install the Kilo extension from the VS Code Marketplace, the JetBrains Marketplace, or install the CLI with a single command. Sign in once with your Kilo account to sync settings and credits across every surface. You can also start from kilo.ai/get-started, which walks you through picking your editor and the first run.

Question 4

What IDEs and platforms does Kilo support?

Accepted Answer

Kilo Code runs in VS Code and every VS Code-based editor (including Cursor forks and Windsurf), in all JetBrains IDEs (IntelliJ IDEA, PyCharm, WebStorm, GoLand, Rider, RubyMine, CLion, and more), and as a standalone CLI in any terminal. It also powers Cloud Agents and App Builder in the browser, and ships a native Slack integration for team workflows.

Question 5

Which AI models does Kilo Code support?

Accepted Answer

Kilo gives you access to 500+ AI models through one unified interface, including Claude Sonnet 5, Claude Opus 4.8, GPT-5.5, Gemini 3.1 Pro Preview, DeepSeek, Mistral, xAI Grok, Qwen, Llama, and more via Kilo Gateway. You can also bring your own API keys for any provider, or run fully local models through Ollama or LM Studio when you need to keep code on your machine.

Question 6

How does pricing work and can I bring my own API key?

Accepted Answer

Kilo Code charges zero markup on AI token usage. You can bring your own API keys for OpenAI, Anthropic, Google, Groq, and any OpenAI-compatible provider, and pay those providers directly at list prices. If you prefer a single bill, top up the Kilo gateway balance pay-as-you-go and pay the same provider rate. Kilo Pass subscribers get bonus credits on top of what they pay.

Question 7

How does Kilo handle code privacy and data?

Accepted Answer

Kilo doesn't collect telemetry by default and never trains on your code. Prompts and completions are passed directly to the model provider you pick, never stored for training. You can run 100% local models through Ollama or LM Studio to keep code on your machine, and teams get enterprise controls including SSO, audit logs, SOC 2 Type II certification, and data-residency controls.

Question 8

What agent modes does Kilo Code have?

Accepted Answer

Kilo ships with five specialized modes: Code (writes and edits production code), Architect (plans features and designs systems before touching code), Debug (traces errors and proposes fixes), Ask (answers questions about your codebase), and Orchestrator (coordinates multi-step tasks across other modes). You can also define custom modes with your own system prompts, tool permissions, and model choice.

Question 9

How do Cloud Agents work?

Accepted Answer

Cloud Agents run Kilo inside isolated cloud containers connected to your GitHub or GitLab repo, so long-running tasks like migrations, refactors, or autonomous PR creation keep working even when your laptop is closed. You can kick them off from the IDE, CLI, Slack, or a web dashboard, review their output as pull requests, and resume the exact same session locally with full context preserved.

Question 10

Does Kilo understand my entire codebase?

Accepted Answer

Yes. Kilo automatically indexes your repository, pulls in the most relevant files and symbols for every prompt, and uses ripgrep-powered search, AST-aware tooling, and persistent memory to stay grounded in your actual code. You can also add explicit context with @file, @folder, or @url mentions, connect MCP servers for live tool access, and pull in documentation via Context7 to avoid hallucinated APIs.

Question 11

What programming languages does Kilo support?

Accepted Answer

Kilo Code works with every language your chosen model knows, including TypeScript, JavaScript, Python, Go, Rust, Java, Kotlin, Swift, C#, C/C++, Ruby, PHP, Scala, Elixir, Dart, SQL, HTML/CSS, Terraform, and Bash. Tree-sitter parsers keep code edits AST-aware across the most common languages, and the JetBrains plugin uses the IDE's own language services for deeper integration.

Question 12

Why switch from Cursor to Kilo Code?

Accepted Answer

Kilo is open source, supports 500+ models with bring-your-own API keys, and runs inside standard VS Code and JetBrains — no editor fork required. You get stronger privacy options (local models, no training on your code), visibility into every prompt the agent sends, pay-as-you-go pricing instead of a locked subscription, and team features like SSO and audit logs without moving off your existing editor.

Question 13

How does Kilo Code compare to GitHub Copilot?

Accepted Answer

GitHub Copilot is a closed autocomplete and chat product locked to OpenAI models with a fixed monthly price. Kilo Code is an open source agent that does multi-step work — refactors, debugging, reviews, deployments — across 500+ models from every major provider, supports local inference, and charges zero markup. Teams that need audit logs, shared credentials, and custom modes typically find Kilo more flexible and cheaper at scale.

Question 14

Does Kilo support MCP (Model Context Protocol)?

Accepted Answer

Yes. Kilo is a first-class MCP client: you can connect any MCP server to expose custom tools, APIs, docs, or internal services to the agent. There is a built-in MCP marketplace for one-click installs (GitHub, Linear, Jira, Postgres, Context7, Browserbase, and more), and teams can publish private MCP servers to their organization.

Question 15

Can I use Kilo Code on a team or in an enterprise?

Accepted Answer

Yes. Kilo Teams adds centralized billing, shared credit balance, usage analytics, role-based access, and team-wide rules or skills. Enterprise plans add SSO/SAML, SCIM provisioning, audit logs, SOC 2 Type II, data-residency controls, a dedicated proxy gateway, and priority support with SLAs. Teams and enterprises get centralized administration without markup on AI token usage.

Question 16

Is Kilo Code really open source?

Accepted Answer

Yes. Kilo Code is open source under the Apache-2.0 license, including the VS Code extension, JetBrains plugin, and CLI. You can read the source, self-build, submit pull requests, and run Kilo with your own API keys. Hosted services such as Kilo Gateway, Cloud Agents, and team administration add managed infrastructure and enterprise controls.

Code with AI
without breaking the bank

Trusted by developers at the world's most innovative companies

Built differently, on purpose

One portal for every agent

Models at cost. No markup. No lock-in.

No black boxes. Inspect everything.

Use Kilo Everywhere

Built for agentic engineering

Hosted OpenClaw

Stop choosing models. Start shipping.

Efficient

Frontier

Balanced

Free

Recent posts

Introducing Kilo Memory: Project-Scoped Memory for Your Agents

Kimi K3 Just Took the #1 Spot for Frontend. We Put It Against Claude Fable 5 on 10 UIs

Laguna S 2.1 is live on Kilo

Why we won’t see another DeepSeek moment anytime soon

Inside Kilo Speed: We Taught Kilo to Test Itself

One agent per model: control which skills load in Kilo

Frequently asked questions

Ready to get started?

Code with AIwithout breaking the bank