AI that uses your codebase as context

Sourcegraph’s AI code assistant goes beyond individual dev productivity, helping you achieve consistency and quality at scale with AI. Sourcegraph accelerates the entire workflow for developers by providing them a more natural and intuitive way to work. Searching code, chatting with AI, invoking prompts, and using agents can now all be performed in one place with the best models available.

Agentic Chat

Designed to simplify and accelerate developer workflows, Sourcegraph uses intent detection and a combination of search, AI chat, and prompts in a single interface to streamline how you explore, understand, and generate code.

Prompts

Streamline your development process by using prompts to understand, improve, fix, document, and generate unit tests for your code. You can also create your own prompts and save them in the Prompt Library to tailor Sourcegraph to your workflow.

Auto-edit

Autocompletes single lines, or whole functions, in any programming language, configuration file, or documentation. It’s powered by the latest instant LLM models, for accuracy and performance.

Works with your favorite IDEs

Sourcegraph is available on the IDEs you use today. Get AI chat, autocomplete, and inline edit without changing your workflow.

The best context

When tools focus solely on individual productivity, teams face inconsistent and poor-quality results. Sourcegraph focuses on team productivity using whole codebase context and shared prompts to ensure quality and consistency across your enterprise.

The best models

Sourcegraph users can select the LLM they want to use for chat and experiment to choose the best model for the job. Choose from multiple options including Claude Sonnet 4, Gemini 1.5 Pro, and Mixtral 8x7B. Cody Pro users can also select Claude 3 Opus and GPT-4o. See the full list of model options here.

Chat

Answer questions about your entire codebase, specific files and symbols, or general programming topics.

For example, you can ask Cody:

• "How is our app's secret storage implemented on Linux?"
• "Where is the CI config for the web integration tests?"
• "Write a new GraphQL resolver for the AuditLog"
• "Why is the UserConnectionResolver giving an "unknown user" error, and how do I fix it?"
• "Add helpful debug log statements"
• "Make this work" (seriously, it often works—try it!)

Prompt Library

You can also create your own prompts and save them in the Prompt Library to tailor Cody to your workflow.

Choose Your LLM

Cody users can select the LLM they want to use for chat and experiment to choose the best model for the job. Choose from multiple options including Claude Sonnet 4, Gemini 1.5 Pro, and Mixtral 8x7B. Cody Pro users can also select Claude 3 Opus and GPT-4o. See the full list of model options here.

Administrators for Sourcegraph Enterprise instances can configure which model options to let team members choose from.

Engineered for the enterprise

Sourcegraph is built to support the needs of the largest enterprises, with flexible deployment and support for enterprise security and compliance.

Usage

This extension works for all Cody plans, including Cody Free, Cody Pro, and Cody Enterprise.

You can find detailed information about Cody's available plans on our website.

Programming Languages

Cody works for any programming language because it uses LLMs trained on broad data. Cody works great with Python, Go, JavaScript, and TypeScript code.

Feedback

• File an issue
• Discord
• Twitter (@sourcegraph)

More Information

See https://cody.dev/ for demos, information and more.