Promptor for macOS: Turn your entire codebase into a single LLM prompt

Key Concepts:

• Prompter: A lightweight Swift UI application for macOS.
• LLM-ready prompt: A prompt formatted for use with Large Language Models.
• Token counting: Estimating the number of tokens in a prompt.
• Open-source codebase: Source code available for public use and modification.

Functionality of Prompter

Prompter is a Swift UI application designed for macOS that simplifies the process of creating prompts for Large Language Models (LLMs) from open-source codebases. Its primary function is to convert an entire project folder into a single, well-formatted prompt suitable for input into an LLM.

Key Features and Benefits

• Codebase Transformation: Prompter takes a project folder as input and transforms its contents into an LLM-ready prompt.
• Binary and Build Clutter Exclusion: The application intelligently skips binaries and build-related files, ensuring that only relevant source code is included in the prompt. This reduces noise and improves the quality of the prompt.
• Local Processing: All processing is done locally on the user's machine, ensuring privacy and security. No data is sent to external servers.
• Live Token Estimation: Prompter provides a live token estimate as files are added to the prompt. This allows users to monitor the prompt size and avoid exceeding the token limits of their chosen LLM.
• Elimination of Copy-Paste: Prompter eliminates the need for manual copy-pasting of code files, streamlining the prompt creation process.

Workflow

The workflow involves dragging and dropping a project folder into the Prompter application. The application then processes the folder, excludes irrelevant files, formats the code, and provides a token count. The resulting prompt can then be used with any LLM.

Problem Solved

Prompter addresses the challenge of preparing large codebases for use with LLMs. Manually creating prompts from code can be time-consuming and error-prone. Prompter automates this process, making it easier for developers to leverage LLMs for code analysis, generation, and other tasks.

Conclusion

Prompter is a useful tool for developers working with open-source codebases and LLMs. It simplifies the process of creating prompts, ensures that only relevant code is included, and provides a live token estimate. This can save time and improve the quality of prompts, making it easier to leverage LLMs for various coding-related tasks.