Roo Code gives you a whole dev team of AI agents in your code editor.

Saoud Rizwan 011d4ffbc9 Fix scrolling to bottom; update system prompt to not unnecessarily read files before editing; add gif to README 1 tahun lalu
.vscode 08effc4799 Make react build task; add react-textarea-autosize; add settings button; add settings page; get basic chat interface working 1 tahun lalu
src 011d4ffbc9 Fix scrolling to bottom; update system prompt to not unnecessarily read files before editing; add gif to README 1 tahun lalu
webview-ui 011d4ffbc9 Fix scrolling to bottom; update system prompt to not unnecessarily read files before editing; add gif to README 1 tahun lalu
.eslintrc.json 56bafe9f59 Fix warnings 1 tahun lalu
.gitignore 9f169b7e4b Initial commit 1 tahun lalu
.nvmrc fafdfe30a4 Add .nvmrc, .prettierignore, icon; Remove vsc quickstart guide 1 tahun lalu
.prettierignore fafdfe30a4 Add .nvmrc, .prettierignore, icon; Remove vsc quickstart guide 1 tahun lalu
.prettierrc.json 0ede211d4f Add vscode-webview-ui-toolkit and follow tutorial to get started 1 tahun lalu
.vscode-test.mjs 9f169b7e4b Initial commit 1 tahun lalu
.vscodeignore 1c6e838681 Fix missing icons in production build bug 1 tahun lalu
CHANGELOG.md fafdfe30a4 Add .nvmrc, .prettierignore, icon; Remove vsc quickstart guide 1 tahun lalu
LICENSE 691d4d6d59 Create LICENSE 1 tahun lalu
README.md 011d4ffbc9 Fix scrolling to bottom; update system prompt to not unnecessarily read files before editing; add gif to README 1 tahun lalu
esbuild.js 303da320aa Add analyze_project tool 1 tahun lalu
icon.png fafdfe30a4 Add .nvmrc, .prettierignore, icon; Remove vsc quickstart guide 1 tahun lalu
package-lock.json 303da320aa Add analyze_project tool 1 tahun lalu
package.json 9fa611cb3d Update README, Announcement, Settings; update version 1 tahun lalu
tsconfig.json cd8bbc5c7f Update extension to use react app 1 tahun lalu

README.md

Claude Dev

Download VSCode Extension       Tutorials (coming soon)       Make Contribution

Thanks to Claude 3.5 Sonnet's agentic coding capabilities Claude Dev can handle complex software development tasks step-by-step. With tools that let him read & write files, analyze project source code, and execute terminal commands (after you grant permission), he can assist you in ways that go beyond simple code completion or tech support. From building software projects to running system operations, Claude Dev is only limited by your imagination.

While autonomous AI scripts traditionally run in sandboxed environments, Claude Dev offers a human-in-the-loop GUI to supervise every file change and command executed, providing a safe and accessible way to explore the potential of agentic AI.

  • View syntax highlighted file previews and diffs for every change Claude makes
  • Streams command execution output into the chat, so you never have to open a terminal yourself
  • Presents permission buttons (i.e. 'Approve CLI command') before tool use or sending information to the API
  • Keep track of total tokens and API usage cost for the entire task loop and individual requests
  • Set a maximum # of API requests allowed for a task before being prompted for permission to proceed
  • When a task is completed, Claude Dev determines if he can present the result to you with a CLI command like open -a "Google Chrome" index.html, which you run with a click of a button

How it works

Claude Dev uses an agentic loop style implementation with chain-of-thought prompting and access to powerful tools that give him the ability to accomplish nearly any task. Start by providing a task and the agentic loop fires off, where it might use certain tools (with your permission) to accomplish each step in its thought process.

Tools

Claude Dev has access to the following capabilities:

  1. execute_command: Execute CLI commands on the system
  2. analyze_project: Analyze the project's source code and file structure
  3. list_files: List all file paths at the top level of the specified directory
  4. read_file: Read the contents of a file at the specified path
  5. write_to_file: Write content to a file at the specified path
  6. ask_followup_question: Ask the user a question to gather additional information needed to complete a task
  7. attempt_completion: Present the result to the user after completing a task, potentially with a CLI command to kickoff a demonstration

Only With Your Permission

Claude always asks for your permission first before any tools are executed or information is sent back to the API. This puts you in control of this agentic loop, every step of the way.

image

Contribution

Feel free to contribute to this project by submitting issues and pull requests. Contributions are welcome and appreciated! To build Claude Dev locally, follow these steps:

  1. Clone the repository:

    git clone https://github.com/saoudrizwan/claude-dev.git
    
  2. Open the project in VSCode:

    code claude-dev
    
  3. Install the necessary dependencies for the extension and webview-gui:

    npm run install:all
    
  4. Launch by pressing F5 to open a new VSCode window with the extension loaded

Reviews

License

This project is licensed under the MIT License. See the LICENSE file for details.

Questions?

Contact me on twitter @sdrzn. Please create an issue if you come across a bug or would like a feature to be added.

Acknowledgments

Special thanks to Anthropic for providing the API that powers this extension.