A high-performance Python library for optimizing LLM prompt inputs: token-efficient JSON flattening + deterministic TextRank-based text compression.
A new package that takes user-provided text input (such as event details, membership information, or coupon data) and uses an LLM to generate structured, formatted pass content for Apple Wallet. It en
A new package designed to streamline content management tasks within Textpattern CMS 4.9.0. It allows users to input text-based content or instructions related to their CMS, such as article drafts, fo
This package would process text input, such as a research paper title or abstract snippet, and generate a structured summary of the core idea or problem addressed. It uses an LLM to interpret the inpu
A new package that processes user-provided text inputs (such as headlines, descriptions, or extracted content from media) and returns structured, pattern-validated summaries using an LLM. It leverages
Push-to-talk speech-to-text input using OpenAI Whisper
A library for printing colored text, getting colored input, changing Qt5 controls' colors, adding watermarks to the video. 一个用来打印彩色文字、获取彩色的输入、更改Qt5控件的颜色、给视频添加水印的库。
Compare sentences from input document with all sentences from reference documents - find very similar ones.
Real-time voice channel plugin for Hermes Agent over Plivo Audio Streaming. Phone conversations with the agent, inbound and outbound, with barge-in and keypad input.
A new package would process user-provided text inputs, such as headlines or short descriptions, and generate structured summaries or categorizations using an LLM. It would be particularly useful for c
The new package transforms a user’s plain‑text search phrase into a structured, BM25‑ranked list of PostgreSQL search results. It takes the query text as input, forwards it to an LLM that rewrites the
A new package designed to enhance structured text processing by leveraging the capabilities of llmatch-messages. This package will take user-provided text as input and return a well-organized, structu
handles spaces, accents and other sneaky characters in ADB commands
This project implements a keyboard-controlled text user interface (TUI) for the terminal that allows users to navigate menus and nested subsections using simple key inputs (w, s, Enter, Esc). It provides a lightweight framework for building interactive CLI applications with features like menu navigation, subsections, progress bars, and confirmation prompts.
GTK textbuffer with undo functionality.
Easily create terminal user interface containing menus, text boxes and input fields for your projects
Generate ascii art from text input.
Force correct text direction (LTR/RTL) on Django admin and form input fields, regardless of site language.
This validator checks if the input is a single line of text.
Use strings to get what function your user wants to run.
test: input list is write for list_out("v=list",b=False,n=0,fh)function with text file./v=list variable, b(bool)= Do list indent?, n=number of tab./
Hands-free voice assistant + agent: dictate into any terminal, browse the web, run Claude Code/Codex, verify results — cross-platform
A Python library for computing the Mel-Cepstral Distance (also known as Mel-Cepstral Distortion, MCD) between two inputs. This implementation is based on the paper 'Mel-Cepstral Distance Measure for Objective Speech Quality Assessment' by Kubichek (1993).
About This filter changes a given text to Title Caps, and attempts to be clever about SMALL words like a/an/the in the input. The list of SMALL words which are not capped comes from the New York Times Manual of Style, plus some others like 'vs' and 'v'.
Convert text files based on input and output templates
Parse Input Text using One-or-More Ontology (OWL) files
Voice input and output toolkit — build voice-to-voice projects easily.
Visual output surface for agents: render and preview images and videos from text, image, or embedding inputs. Starts with a ComfyUI backend but is not locked to it — pluggable generation backends behind one agent-first CLI.
Dynamic and customizable Tkinter input dialogs with text fields, alternatives, and typed results
Cerbose is a simple, highly customisable, cross-platform Python logging library that allows for fancy terminal text output, log message tagging, file logging, and additional console-related features, such as cerbar, an ASCII progress bar generator, and more.
Django text and character fields that clean HTML input.
Streamlit multimodal chat input component with text, image, and voice support
A powerful Python library for terminal manipulation and text styling
Text cleaning, scoring and compression pipeline
A Streamlit chat input bar with text, audio, and photo upload/camera support.
Convert many medium into text, and the text format is specialized for prompt input
Streamlit component which include row(s) of text input field with DnD property
An interactive Windows CLI menu with support for toggles, numbers, and text input.
A Streamlit custom component that provides enhanced usage over standard streamlit.multiselect. Users can enter free form text which will appear as separate keyword chips.
Streamlit multimodal chat input component with text, image, and voice support
The equivalent of SDImg2ImgPipeline for DDPO: modifying DDPOTrainer to support image inputs in addition to text prompts
A simple way to print colored text in the terminal.
Havina is a Python library that can generate knowledge graphs triplets from an input text. Its implementation is based on the paper "Language models are open knowledge graphs" with some tweaks to improve performance. Havina can be used to evaluate the language comprehension of AI models or as a tool to extract triplets from text and build knowledge graphs.
multiline text input with resut and submit buttons