Cody

AI-Powered Developer Chat

Cody's chat lets you ask questions about your code, generate code, and edit code directly. It automatically uses the context of your open file and repository, and you can use @ to add context on specific files, symbols, remote repositories, or other non-code artifacts.

Get accurate answers and code changes with full codebase context.

Contextual Code Edits

Cody's Auto-edit feature suggests code changes by analyzing your cursor movements and typing. After you've made at least one character edit, it begins proposing contextual modifications based on your cursor position and recent changes.

Speed up your editing workflow with real-time, context-aware suggestions.

Customizable Prompts

Cody lets you automate key tasks with premade and customizable prompts. Any common query or task can be built into a prompt to save and share with your team.

Streamline repetitive workflows and share best practices across your team.

Advanced Codebase Context

Cody uses Sourcegraph's advanced Search API to pull context from both local and remote codebases. This gives you access to APIs, symbols, and usage patterns from across your entire codebase.

Get the most accurate and relevant AI responses by leveraging your full codebase.

Optimized Debugging

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.

Resolve errors faster and boost your productivity.

Control Your Context

Cody can ignore selected repositories from chat and autocomplete results, helping you control and manage what context your codebase uses.

Keep your AI interactions focused and relevant by filtering out unwanted repositories.

• AI-powered code assistanceCody is an AI coding assistant that uses the latest LLMs and your development context to help you understand, write, and fix code faster. It leverages Sourcegraph's advanced Search API to pull context from local and remote codebases, enabling accurate answers about APIs, symbols, and usage patterns.
• Seamless IDE and codehost integrationCody connects with codehosts like GitHub and GitLab, and IDEs like VS Code, JetBrains, and Visual Studio. It is available on VS Code, JetBrains, Visual Studio (experimental), the Web app, and CLI, making it easy to integrate into your existing workflow.
• Rich feature set for developersCody includes chat for asking questions and generating code, auto-edit for contextual code changes, customizable prompts for automating tasks, and debugging capabilities. It also offers context filters to control which repositories are used for context.
• Privacy-conscious data handlingSourcegraph collects prompts and responses to provide the service, but does not use your data to train models. Usage data and feedback are collected to improve user experience, and you can read more about the privacy policy.

• Supported platforms and enterpriseCody is supported on Sourcegraph Enterprise and available on VS Code, JetBrains, Visual Studio, and the Web app. For enterprise use, you need to get in touch with the team to try Cody for Sourcegraph Enterprise.
• Data collection specificsCody collects prompts and responses, usage data, and feedback. For individuals using Cody via Sourcegraph.com, Sourcegraph may use prompts and responses to enhance user experience, but does not use data to train models. No other data usage is specified.
• Compatibility with other productsCody is compatible with other Sourcegraph products like Code Search. You can use Cody's chat to ask questions about your codebase after running a search query and opening a repository or file, where you'll find the Cody button.
• Getting started optionsYou can start using Cody by installing extensions for VS Code, JetBrains, or Visual Studio (experimental), using Cody in the Sourcegraph web app, running Cody CLI from the command line, or contacting the team for Cody Enterprise.

Codebase Q&A

Ask Cody questions about your code directly in chat. It uses Sourcegraph's advanced Search API to pull context from both local and remote codebases, so you can get accurate answers about APIs, symbols, and usage patterns across your entire project.

Code Completion & Edits

Cody provides code completions, code edits, and customizable prompts. Its Auto-edit feature suggests changes by analyzing your cursor movements and typing, proposing contextual modifications after you make at least one character edit.

Debugging Assistance

Cody is optimized to identify and fix errors in your code. Its debugging capability and autocomplete suggestions accelerate the debugging process, helping you resolve issues faster and boost developer productivity.

Context Filtering

Cody lets you ignore selected repositories from chat and autocomplete results with Context Filters. This helps you control and manage what context your codebase uses, ensuring more relevant and focused AI assistance.

Define the exact aI Coding Tools workflow Cody should support.

Compare it with closely related AI tools in the same category before committing.

Set review rules for accuracy, privacy, brand voice, compliance, and final approval.

Connect useful outputs to the wider stack instead of leaving them inside the AI tool.