<div align="center"><img src="https://storage.googleapis.com/sourcegraph-assets/docs/images/cody/cody-logomark-default.svg" height="20"/></div> logo

<div align="center"><img src="https://storage.googleapis.com/sourcegraph-assets/docs/images/cody/cody-logomark-default.svg" height="20"/></div>

Free

[Sourcegraph Cody](https://sourcegraph.com/cody)

FreeFree tier
Inputs: code, textOutputs: code, text
Type
Open Source

About <div align="center"><img src="https://storage.googleapis.com/sourcegraph-assets/docs/images/cody/cody-logomark-default.svg" height="20"/></div>

Cody is an AI coding assistant developed by Sourcegraph that leverages large language models (LLMs) and deep codebase context to help developers understand, write, and fix code faster. It integrates with popular IDEs such as VS Code, JetBrains, and Visual Studio, as well as the Sourcegraph web app and CLI. Cody uses Sourcegraph's advanced Search API to pull context from both local and remote codebases, enabling accurate answers and code suggestions based on actual APIs, symbols, and usage patterns. Key capabilities include chat-based code assistance, automatic code edits, customizable prompts, debugging support, and context filters. Cody is available as a free tier and also offers an Enterprise plan with additional features and support.

Key Features

Chat with AI about your code using context from open files, repositories, and remote codebases
Auto-edit: suggests code changes by analyzing cursor movements and recent edits
Prompts: automate key tasks with premade and customizable prompts that can be shared with your team
Context from Sourcegraph's advanced Search API for accurate answers across local and remote code
Debug code: optimized to identify and fix errors, accelerating debugging
Context Filters: ignore selected repositories from chat and autocomplete results

Pros & Cons

Pros
  • Free to use with a generous free tier
  • Open source and community-driven
  • Integrates directly into multiple popular IDEs (VS Code, JetBrains, Visual Studio)
  • Leverages Sourcegraph's code search for accurate context across entire codebase
  • Supports both local and remote codebases
  • Privacy-conscious: no use of data to train models
Cons
  • Full context capabilities require connecting to a Sourcegraph instance
  • Some advanced features and support require the paid Enterprise plan
  • Primarily designed for codebases already indexed by Sourcegraph
  • Dependency on internet connectivity for LLM-powered features

Best For

Understanding and navigating unfamiliar codebasesGenerating and editing code with contextual suggestionsDebugging and fixing errors in codeAutomating repetitive coding tasks with promptsCode review and refactoring using deep codebase context

FAQ

What data does Cody collect?
Cody collects prompts and responses to provide the service, as well as usage data and feedback to improve user experience. Sourcegraph does not use any user data to train models.
Which IDEs are supported?
Cody supports VS Code, JetBrains IDEs, and Visual Studio (experimental). It can also be used via the Sourcegraph web app and CLI.
Is Cody free?
Yes, Cody offers a free tier. There is also an Enterprise plan with additional features, support, and scalability starting at $16K.