×

What does it do?

  • Code Autocomplete
  • Code Generation
  • Code Explanation
  • Debugging Assistance
  • IDE Integration

How is it used?

  • Plugin for IDEs providing AI-assisted code autocomplete.
  • 1. Install plugin w/ IDE 2. Use autocomplete & Cody Chat 3. Integrate w/ code hosts 4. Leverage LLMs for AI 5. Ideal for all devs

Who is it good for?

  • Data Scientists
  • IT Professionals
  • Software Developers
  • Computer Science Students
  • DevOps Engineers

Details & Features

  • Made By

    Sourcegraph
  • Released On

    2013-07-10

Cody is an AI coding assistant developed by Sourcegraph that enhances the coding experience by providing advanced search capabilities, codebase context understanding, and generative AI features to help developers understand, write, and fix code more efficiently.

Key features:
- AI-assisted autocomplete for single lines or entire functions across any programming language
- AI-powered chat to assist developers in navigating projects, understanding code, and solving complex problems
- Code understanding and generation, including explaining code blocks or repositories, generating unit tests, and describing code smells for optimization
- Support for custom commands tailored to the developer's workflow

Integrations:
- IDEs: Visual Studio Code, JetBrains IDEs, and NeoVim
- Code Hosts: GitHub, Bitbucket, GitLab, Gerrit, Perforce, and Golang

Use of AI:
Cody leverages generative AI through the use of advanced Large Language Models (LLMs) such as Claude 3, GPT-4 Turbo, and Mixtral-8x7B. It also allows users to bring their own LLM keys from Amazon Bedrock and Azure OpenAI, providing flexibility and avoiding lock-in to a specific model.

How to access:
Cody is available as a plugin for various IDEs, making it easily accessible for developers working in supported coding environments. There is also a Cody Enterprise version offering additional features like enhanced security, scalability, and control for organizations.

  • Supported ecosystems
    GitHub, GitHub, Amazon, Google, Microsoft
  • What does it do?
    Code Autocomplete, Code Generation, Code Explanation, Debugging Assistance, IDE Integration
  • Who is it good for?
    Data Scientists, IT Professionals, Software Developers, Computer Science Students, DevOps Engineers

Alternatives

CodeQL is a semantic code analysis engine that helps developers find and fix vulnerabilities in their codebase.
GitHub Copilot generates code suggestions in real-time to enhance developer productivity.
Augment is an AI-powered coding assistant that enhances software development efficiency and quality.
Amazon Q Developer is an AI-powered coding assistant that enhances software development and infrastructure management for AWS developers.
StarCoder is a Large Language Model for Code (Code LLM) that has been developed using permissively licensed data from GitHub, with a model trained on 1 trillion tokens and fine-tuned for 35 billion Python tokens, and it performs better than existing open Code LLMs on popular programming benchmarks.
Gemini Code Assist is an AI coding assistant that boosts developer productivity with code completions and generation.
PolyCoder generates code snippets and assists with code understanding across 12 programming languages.
CodeT5 and CodeT5+ are open-source language models that automate coding tasks for developers.
Bloop converts legacy COBOL code into modern, readable Java code with identical behavior using AI.
CodeLlama-34b-Instruct-hf is an AI model for code synthesis and understanding, ideal for developers and researchers.