Skip to content

About

⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks

Resources

Code of conduct

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

 
 

Latest commit

 

History

15,275 Commits

Folders and files

Repository files navigation

Continue logo

Continue

Continue enables developers to create, share, and use custom AI code assistants with our open-source VS Code and JetBrains extensions and hub of models, rules, prompts, docs, and other building blocks

Agent

Agent enables you to make more substantial changes to your codebase

agent

Chat

Chat makes it easy to ask for help from an LLM without needing to leave the IDE

chat

Autocomplete

Autocomplete provides inline code suggestions as you type

autocomplete

Edit

Edit is a convenient way to modify code without leaving your current file

edit

Getting Started

Learn about how to install and use Continue in the docs here

Contributing

Read the contributing guide, and join #contribute on Discord.

Web-dev Usage

  1. If GUI is modified only, run this in GUI folder
    npm run build
    
  2. Then, in extensions/vscode foler
    npm run prepackage
    npm run package
    

Features

Fundamental Knowledge Support

  1. In Markdown documents:
    • Select a piece of text and press Ctrl+E to get an explanation.
    • Select a piece of text and press Ctrl+Shift+Q to initiate a quick conversation.
  2. In the mind map:
    • Left-click on a node to start a quick chat.
    • Right-click on a node to ask the agent to update the task or requirements, such as requesting the agent to break down a task.
    Feature Screenshot 1 Feature Screenshot 2
  3. In the task panel:
    • Select a specific section of a task to inquire about knowledge. The inquiry results are saved in the corresponding task. Feature Screenshot
  4. In the chat flow:
    • Support simple knowledge viewing between lines.
    • Select a piece of text to perform predefined inquiries. Feature Screenshot Feature Screenshot

Working Flow

  1. During the initialization phase, the agent clarifies requirements through questions and generates requirements.md.
  2. After generating the requirements, the agent further clarifies and produces task.md and re-plan.md. The re-plan.md is visualized in the mind map.
  3. The agent guides the project step by step. After completing a task or checkpoint, the agent updates the corresponding documents (e.g., logs of related files for each task are updated in real-time), which are reflected in the task panel. Feature Screenshot

Explainability

  1. Full codebase structure analysis

    Feature Screenshot

  2. File Explanation Feature Screenshot

  3. Prompts: Rules for guiding full-stack beginners.

License

Apache 2.0 © 2023-2024 Continue Dev, Inc.

About

⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks

Resources

Code of conduct

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages