Convert Figma logo to code with AI

sourcegraph logocody

Type less, code more: Cody is an AI code assistant that uses advanced search and codebase context to help you write and fix code.

2,519
260
2,519
248
View on GitHub

Top Related Projects

codota's avatar

TabNine

10,552

AI Code Completions

Quick Overview

Cody is an AI-powered coding assistant developed by Sourcegraph. It integrates with popular IDEs and code editors to provide intelligent code suggestions, answer questions, and help developers write, understand, and fix code more efficiently.

Pros

  • Seamless integration with popular IDEs and code editors
  • Provides context-aware code suggestions and completions
  • Capable of answering natural language questions about codebases
  • Supports multiple programming languages and frameworks

Cons

  • May require a learning curve to fully utilize its capabilities
  • Depends on internet connectivity for AI-powered features
  • Potential privacy concerns when sharing code with an external service
  • May not always provide accurate suggestions for complex or domain-specific code

Getting Started

To get started with Cody, follow these steps:

  1. Install the Cody extension for your preferred IDE or code editor (e.g., VS Code, JetBrains IDEs).
  2. Sign up for a Sourcegraph account or connect to your existing account.
  3. Authenticate the extension with your Sourcegraph account.
  4. Start using Cody by typing /cody in your editor to access its features.

Example usage in VS Code:

1. Open a code file in VS Code.
2. Type `/cody` to bring up the Cody command palette.
3. Choose an action, such as "Ask a question" or "Explain code".
4. Enter your query or select the code you want explained.
5. Cody will provide an AI-generated response or explanation.

Note: Specific installation and usage instructions may vary depending on your chosen IDE or editor.

Competitor Comparisons

codota logo

TabNine

10,552

AI Code Completions

Pros of TabNine

  • Supports a wider range of programming languages and IDEs
  • Offers a local AI model option for enhanced privacy
  • Has a longer track record and more established user base

Cons of TabNine

  • May require more system resources for local AI model
  • Some advanced features are only available in paid plans
  • Can be less context-aware compared to Cody's repository-wide understanding

Code Comparison

TabNine:

def calculate_sum(numbers):
    return sum(numbers)

Cody:

def calculate_sum(numbers: List[int]) -> int:
    return sum(numbers)

Both tools provide code completion, but Cody tends to offer more detailed type hints and documentation suggestions.

Key Differences

  • Cody focuses on deep integration with Sourcegraph's code intelligence platform
  • TabNine offers broader language support and IDE compatibility
  • Cody emphasizes natural language understanding and repository-wide context
  • TabNine provides options for both cloud-based and local AI models

Use Cases

  • TabNine: Developers working across multiple languages and IDEs
  • Cody: Teams using Sourcegraph and prioritizing context-aware completions

Community and Support

  • TabNine has a larger community due to its longer presence in the market
  • Cody benefits from Sourcegraph's established enterprise support infrastructure

Both tools continue to evolve rapidly, with frequent updates and improvements to their AI-powered code assistance capabilities.

Convert Figma logo designs to code with AI

Visual Copilot

Introducing Visual Copilot: A new AI model to turn Figma designs to high quality code using your components.

Try Visual Copilot

README

Cody

Code AI with codebase context

Cody is an AI coding assistant that uses search and codebase context to help you understand, write, and fix code faster.

Docs • cody.dev

vscode extension License test Twitter Discord

Get started

⭐ Install Cody from the VS Code Marketplace or the JetBrains Marketplace, then check out the demos to see what you can do.

— or —

  • Build and run the VS Code extension locally: pnpm install && cd vscode && pnpm run dev
  • See all supported editors

What is Cody?

Cody is an open-source AI coding assistant that helps you understand, write, and fix code faster. It uses advanced search to pull context from both local and remote codebases so that you can use context about APIs, symbols, and usage patterns from across your codebase at any scale, all from within your IDE. Cody works with the newest and best large language models, including Claude 3.5 Sonnet and GPT-4o.

Cody is available for VS Code, JetBrains, and on the web.

See cody.dev for more info.

What can Cody do?

  • Chat: Ask Cody questions about your codebase. Cody will use semantic search to retrieve files from your codebase and use context from those files to answer your questions. You can @-mention files to target specific context, and you can also add remote repositories as context on Cody Enterprise.
  • Autocomplete: Cody makes single-line and multi-line suggestions as you type, speeding up your coding and shortcutting the need for you to hunt down function and variable names as you type.
  • Inline Edit: Ask Cody to fix or refactor code from anywhere in a file.
  • Commands: Cody has quick commands for common actions. Simply highlight a code snippet and run a command, like “Document code,” “Explain code,” or “Generate Unit Tests.”
  • Swappable LLMs: Support for Anthropic Claude 3.3 Sonnet, OpenAI GPT-4o, Mixtral, Gemini 1.5, and more.
    • Free LLM usage included Cody Free gives you access to Anthropic Claude 3.5 Sonnet and other models. It's available for individual devs on both personal and work code, subject to reasonable per-user rate limits (more info).

Demos

Autocomplete

Codebase-wide chat:

Contributing

All code in this repository is open source (Apache 2).

Quickstart: pnpm install && pnpm build && cd vscode && pnpm run dev to run a local build of the Cody VS Code extension.

See development docs for more.

Feedback

Cody is often magical and sometimes frustratingly wrong. Cody's goal is to be powerful and accurate. You can help:

Usage

Individual usage

Individual usage of Cody currently requires a (free) Sourcegraph.com account because we need to prevent abuse of the free Anthropic/OpenAI LLM usage. We're working on supporting more swappable LLM options (including using your own Anthropic/OpenAI account or a self-hosted LLM) to make it possible to use Cody without any required third-party dependencies.

Codying at work

You can use Cody Free or Cody Pro when Codying on your work code. If that doesn't meet your needs (because you need higher rate limits, a dedicated/single-tenant instance, audit logs, etc.), upgrade to Cody Enterprise.

Existing Sourcegraph customers

The Cody editor extensions work with:

  • Sourcegraph Cloud
  • Sourcegraph Enterprise Server (self-hosted) instances on version 5.1 or later