Cody is an AI coding assistant built by Sourcegraph that combines deep codebase understanding with flexible AI model selection to provide context-aware code generation, explanations, and refactoring across entire repositories. Unlike assistants that only consider the current file, Cody leverages Sourcegraph's code intelligence platform to understand relationships between components, dependencies, and patterns across your entire codebase. This deep contextual awareness makes Cody particularly effective for large, complex codebases where understanding cross-file relationships is critical for accurate code assistance.
Cody provides autocomplete with both single-line and multi-line suggestions, a chat interface for asking questions and generating code, inline editing for quick code modifications with natural language, and automated unit test generation. A key differentiator is its ability to fetch context from external platforms through OpenCtx providers, pulling in information from Jira tickets, Linear issues, Notion pages, Google Docs, and Sourcegraph code search to enrich its understanding of your project. Users can select from multiple LLMs including Claude, Gemini Pro, and GPT models, choosing the best model for each task.
Cody is designed for developers and engineering teams working with large, complex codebases who need an AI assistant that truly understands their project architecture. It is available on VS Code, JetBrains IDEs, Visual Studio, and as a web application, connecting seamlessly with code hosting platforms like GitHub and GitLab. Cody is particularly valuable for onboarding new team members, navigating unfamiliar code, and maintaining consistency across large projects where manual code review and exploration would be time-consuming.