Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Software
Data sources: ZENODO
addClaim

dtr-kalfer/frompt: frompt v1.0.0

Authors: Ferdinand Tumulak;

dtr-kalfer/frompt: frompt v1.0.0

Abstract

As Generative Artificial Intelligence (AI) and Large Language Models (LLMs) become deeply integrated into software engineering research and academic workflows, providing models with accurate repository context remains a critical bottleneck. Standard directory mapping utilities frequently rely on heavy, non-portable host dependencies or generate outputs that break UTF-8 formatting when transferred across isolated network boundaries (e.g., Docker containers, remote SSH sessions). This paper introduces frompt (Folder Prompt Tree), a native, zero-dependency PHP Command Line Interface (CLI) utility optimized explicitly for LLM context ingestion. frompt automatically handles terminal-agnostic clipboard synchronizations (including OSC 52 fallbacks) and standardizes code block encapsulation to maximize prompt structural integrity while minimizing token consumption.

Powered by OpenAIRE graph
Found an issue? Give us feedback