Cody

Cody is an AI coding assistant that uses all the latest LLMs and your development context to help you understand, write, and fix code faster. It uses the powerful Sourcegraph's advanced Search API to pull context from both local and remote codebases so that you can use context about APIs, symbols, and usage patterns from across your entire codebase.

Cody connects seamlessly with codehosts like GitHub, GitLab and IDEs like VS Code, JetBrains, Visual Studio, and Eclipse. Once connected, Cody acts as your personal AI coding assistant, equipped with the following capabilities:

Developer chat with the most powerful models and context
Code completions, code edits, and customizable prompts
Extensive context to deliver the most accurate results

Getting started

You can start using Cody with one of the following options:

Cody for VS Code

Install Cody's free extension for VS Code.

Cody for JetBrains

Install Cody's free extension for JetBrains.

Cody for Visual Studio (Experimental)

Install Cody's free extension for Visual Studio.

Cody for Eclipse (Experimental)

Install Cody's free extension for Eclipse.

Cody for Web

Use Cody in the Sourcegraph web app.

Cody CLI

Run Cody from the command line.

Cody Enterprise

Get in touch with our team to try Cody for Sourcegraph Enterprise.

Main features

Cody's main features include:

Feature	Description
Chat	Chat directly with AI to ask questions about your code, generate code, and edit code. Cody has the context of your open file and repository by default, and you can use `@` to add context on specific files, symbols, remote repositories, or other non-code artifacts.
Autocomplete	Cody predicts what you're trying to write before you type it. It makes single-line and multi-line suggestions as you type, using the context of the code around your cursor to make accurate suggestions.
Prompts	Automate key tasks in your workflow with premade and customizable prompts. Any common query or task can be built into a prompt to save and share with your team.
Context	Cody provides the best LLM models and context to power chat. It uses the powerful Sourcegraph's advanced Search API to pull context from both local and remote codebases.
Debug code	Cody is optimized to identify and fix errors in your code. Its debugging capability and autocomplete suggestions can significantly accelerate your debugging process, increasing developer productivity.
Context Filters	Cody can ignore selected repositories from chat and autocomplete results, which helps you control and manage what context your codebase uses.

What data is collected, and how is it used?

Cody collects and uses data in the following ways:

Prompts and responses: When you use Cody, Sourcegraph collects your prompts and responses to provide the service. For individuals using Cody via Sourcegraph.com, Sourcegraph may use your prompts and responses to enhance the user experience, but Sourcegraph does not use any of your data to train models.
Usage data and feedback: Sourcegraph also collects usage data and feedback to improve the user experience.

Compatible with Sourcegraph products

Cody is compatible with other Sourcegraph products, like Code Search. You can use Cody's chat to ask questions about your codebase. When you run any search query and open a repository or file, you’ll find the Cody button that takes you to Cody’s chat interface, which you can use to ask questions about the codebase.

Join our community

If you have any questions regarding Cody, you can always ask our community, Discord, or create a post on X.