VLCode | AI CodeGen in your IDE

Meet VLCode, your AI assistant that seamlessly integrates ValkyrAI and ThorAPI into your IDE workflow, enhancing your coding experience.

Here are some practical examples to get you started:

1. Task Management: Enter your task and attach images to convert mockups into functional apps or fix bugs with screenshots.
2. Code Analysis: VLCode analyzes your file structure and source code ASTs, running regex searches to understand existing projects without overwhelming the context window.
3. File Management: Create and edit files while monitoring linter/compiler errors, allowing VLCode to proactively fix issues like missing imports and syntax errors.
4. Command Execution: Execute terminal commands directly, enabling VLCode to react to development server issues after editing files.
5. Web Development: Launch your site in a headless browser, allowing VLCode to interact with it, capturing screenshots and console logs to fix runtime errors and visual bugs.
6. Result Presentation: Once a task is completed, VLCode presents the result with a terminal command like open -a "Google Chrome" index.html, which you can run with a click.

[!TIP] Use the CMD/CTRL + Shift + P shortcut to open the command palette and type "VLCode: Open In New Tab" to open the extension as a tab in your editor. This lets you use VLCode side-by-side with your file explorer, and see how they changes your workspace more clearly.

Use any API and Model

VLCode supports API providers like OpenRouter, Anthropic, OpenAI, Google Gemini, AWS Bedrock, Azure, and GCP Vertex. You can also configure any OpenAI compatible API, or use a local model through LM Studio/Ollama. If you're using OpenRouter, the extension fetches their latest model list, allowing you to use the newest models as soon as they're available.

The extension also keeps track of total tokens and API usage cost for the entire task loop and individual requests, keeping you informed of spend every step of the way.

Run Commands in Terminal

Thanks to the new shell integration updates in VSCode v1.93, VLCode can execute commands directly in your terminal and receive the output. This allows him to perform a wide range of tasks, from installing packages and running build scripts to deploying applications, managing databases, and executing tests, all while adapting to your dev environment & toolchain to get the job done right.

For long running processes like dev servers, use the "Proceed While Running" button to let VLCode continue in the task while the command runs in the background. As VLCode works he’ll be notified of any new terminal output along the way, letting him react to issues that may come up, such as compile-time errors when editing files.

Create and Edit Files

VLCode can create and edit files directly in your editor, presenting you a diff view of the changes. You can edit or revert VLCode's changes directly in the diff view editor, or provide feedback in chat until you're satisfied with the result. VLCode also monitors linter/compiler errors (missing imports, syntax errors, etc.) so they can fix issues that come up along the way on his own.

All changes made by VLCode are recorded in your file's Timeline, providing an easy way to track and revert modifications if needed.

Use the Browser

With Claude 3.5 Sonnet's new Computer Use capability, VLCode can launch a browser, click elements, type text, and scroll, capturing screenshots and console logs at each step. This allows for interactive debugging, end-to-end testing, and even general web use! This gives him autonomy to fixing visual bugs and runtime issues without you needing to handhold and copy-pasting error logs yourself.

Try asking VLCode to "test the app", and watch as they runs a command like npm run dev, launches your locally running dev server in a browser, and performs a series of tests to confirm that everything works. See a demo here.

"add a tool that..."

Thanks to the Model Context Protocol, VLCode can extend his capabilities through custom tools. While you can use community-made servers, VLCode can instead create and install tools tailored to your specific workflow. Just ask VLCode to "add a tool" and they will handle everything, from creating a new MCP server to installing it into the extension. These custom tools then become part of VLCode's toolkit, ready to use in future tasks.

• "add a tool that fetches Jira tickets": Retrieve ticket ACs and put VLCode to work
• "add a tool that manages AWS EC2s": Check server metrics and scale instances up or down
• "add a tool that pulls the latest PagerDuty incidents": Fetch details and ask VLCode to fix bugs

Add Context

@url: Paste in a URL for the extension to fetch and convert to markdown, useful when you want to give VLCode the latest docs

@problems: Add workspace errors and warnings ('Problems' panel) for VLCode to fix

@file: Adds a file's contents so you don't have to waste API requests approving read file (+ type to search files)

@folder: Adds folder's files all at once to speed up your workflow even more

Checkpoints: Compare and Restore

As VLCode works through a task, the extension takes a snapshot of your workspace at each step. You can use the 'Compare' button to see a diff between the snapshot and your current workspace, and the 'Restore' button to roll back to that point.

For example, when working with a local web server, you can use 'Restore Workspace Only' to quickly test different versions of your app, then use 'Restore Task and Workspace' when you find the version you want to continue building from. This lets you safely explore different approaches without losing progress.

License

Valkyr Labs EULA 2.0 © 2025 Valkyr Labs Inc