Sourcegraph Cody: Code help grounded in your whole codebase
Sourcegraph Cody is an AI coding assistant that uses large language models and development context to help developers understand, write, and fix code.
What is Sourcegraph Cody?
Sourcegraph Cody is an AI coding assistant that draws on development context to help developers understand, write, and fix code. It uses Sourcegraph's Search API to gather context from local and remote codebases, so answers can reference APIs, symbols, and usage patterns from across a codebase rather than only the open file. It is available as extensions for VS Code, JetBrains, and Visual Studio (experimental), in the Sourcegraph web app, and as a CLI. Core capabilities include chat for asking about code, generating code, and editing code, with @ used to add context on specific files, symbols, remote repositories, or non-code artifacts. Auto-edit proposes changes based on cursor position and recent edits, prompts automate common tasks and can be shared with a team, and context filters let selected repositories be excluded from chat and autocomplete results. Cody is documented as supported on Sourcegraph Enterprise, and the docs describe data collection for prompts, responses, usage data, and feedback.
Focus areas: Refactoring.
Who is Sourcegraph Cody for?
- Developers working in VS Code, JetBrains, or Visual Studio
- Engineering teams on Sourcegraph Enterprise
- Teams that need context from large or multi-repository codebases
Is Sourcegraph Cody worth it?
A codebase-aware coding assistant for teams already working in Sourcegraph-supported editors and code hosts
Where Sourcegraph Cody is strong
- Pulls context from local and remote codebases through Sourcegraph's Search API
- Available across VS Code, JetBrains, Visual Studio, the web app, and a CLI
- Includes chat, auto-edit, prompts, and context filters for repository control
Where it falls short
- Pricing and plan details are not published on the pages reviewed
- The docs list Cody as supported on Sourcegraph Enterprise, so availability may depend on that
How do you get started with Sourcegraph Cody?
- 01Install the Cody extension for VS Code, JetBrains, or Visual Studio, or open Cody in the Sourcegraph web app
- 02Connect a code host such as GitHub or GitLab so Cody can use repository context
- 03Use chat with @ to add context on files, symbols, or remote repositories, and save prompts for recurring tasks
Sourcegraph Cody: frequently asked questions
Which editors and environments does Cody support?
The docs list Cody for VS Code, JetBrains, and Visual Studio (experimental), plus Cody for Web in the Sourcegraph web app and a Cody CLI.
How does Cody get context about my code?
It uses Sourcegraph's Search API to pull context from local and remote codebases, and you can add context on specific files, symbols, remote repositories, or non-code artifacts with @.
Does Cody use my code to train models?
The docs state that Sourcegraph collects prompts and responses to provide the service, and that it does not use your data to train models.
How much does Cody cost?
The pages reviewed do not publish pricing. The docs say Cody is supported on Sourcegraph Enterprise and direct you to contact the team to try it.
Sourcegraph Cody alternatives
The closest tools in our directory, matched on category, focus areas and audience.
Developers wanting model choice and step-by-step agent control in their IDE
Engineering teams giving AI coding agents trusted, permission-aware context
| Tool | Best for | Free plan | Starting price | Focus areas |
|---|---|---|---|---|
| Sourcegraph Cody | Developers who want code answers grounded in repository context | No | — | Refactoring |
| CodeGPT by Judini | Developers wanting model choice and step-by-step agent control in their IDE | Yes | $10/mo | Refactoring |
| Cosine | Teams shipping production code in complex or regulated environments | No | $19/mo | — |
| Circuit Mind | Hardware engineering teams | No | — | — |
| Factory | Engineering teams delegating full tasks to agents | Yes | $20/mo | — |
| Unblocked | Engineering teams giving AI coding agents trusted, permission-aware context | Yes | $29/mo | — |
| GitStart | Teams needing extra PR delivery capacity with agent and human review | Unknown | — | — |
| Kiro | AI IDE for structured, spec-driven coding from prototype to production. | Yes | — | — |
| Augment Code | AI platform for understanding codebases, accelerating coding, and improving team collaboration. | Unknown | — | — |
| Kolosal | Train and run LLMs on your device | Unknown | — | — |
| Overcut.ai | Build your autonomous team with continuous AI. | Unknown | — | — |
