GitPedia

RunOnce

Run LLM-generated one-off scripts via the "Run Code Here" option in the Windows 11 context menu.

From Water-Run·Updated June 6, 2026·View on GitHub·

Right-click, "Run Here" for tens to hundreds of lines of code generated by large language models as "one-time" programs. The project is written primarily in C#, distributed under the GNU General Public License v3.0 license, first published in 2026. Key topics include: code-runner, context-menu, csharp, desktop-app, developer-tools.

RunOnce

中文

Example Image

Right-click, "Run Here" for tens to hundreds of lines of code generated by large language models as "one-time" programs.

Installation

After installation, the program will automatically register a Windows 11 context menu item: Run Code Here.

Language Support

Supports the following languages:

  • bat
  • powershell
  • python
  • lua
  • nim
  • go

UTF-8 Runtime Environment

On Chinese systems, the default runtime environment for some languages (such as lua) may cause encoding issues.
Switch to the UTF-8 runtime environment in settings to resolve these problems.

Mode Selection: Ensure Compatibility and Ensure Cleanup

These two modes control the generation path of temporary files. For general scripts, the Ensure Cleanup mode is sufficient.
However, if your script contains statements like os.path.abspath(__file__) that retrieve the actual script path, you'll need to use Ensure Compatibility mode.
Note that in Ensure Compatibility mode, temporary files may remain in the directory if not properly cleaned up due to abnormal terminal closure or other reasons.

Built-in Large Language Model Integration (contributed by @Tritium0041)

RunOnce supports built-in large language model integration. Scripts generated by the model will be automatically pasted into the editor.
Configure the API KEY in Settings → LLM Settings. OpenAI-compatible API calls are supported.

Contributors

Showing top 2 contributors by commit count.

View all contributors on GitHub →

This article is auto-generated from Water-Run/RunOnce via the GitHub API.Last fetched: 6/18/2026