Universal document converter with 250+ format combinations. Multi-page PDF to image conversion with page selection. OCR-powered image to Markdown for high-accuracy text extraction. Enhanced image support with PNG/JPEG/JPG/HEIC cross-conversions and PDF↔image conversions. Features PowerPoint to Obsidian Markdown with image extraction, format preservation, and navigation links. Supports PDF, DOCX, PPTX, MD, TEX, CSV, XLSX, TXT, HEIC, JPG, PNG, HTML, RTF, ODT.
scikit-learn hyperparameter search with multi-fidelity data growth and scatter-search multi-start: a from-scratch Bayesian (GP + Expected Improvement) search, BayesHalvingSearchCV, plus a Hooke-Jeeves pattern search, PatternSearchCV
Deterministic governance adapter for AG2 (AutoGen fork) — policy enforcement, PII detection, cost tracking, per-agent kill switch, governed speaker selection, and structured audit evidence. No LLM in the governance path.
DECANT prioritizes biological heterogeneity over batch effects during feature selection for single-cell multi-omics data.
Intelligent AutoML Framework with comprehensive multi-metric evaluation and AI-driven optimization
Scale-safe multi-axis score fusion and auditable top-K selection under set constraints. Pure Rust, deterministic, no models, no network.
Multi-backend Physics-Informed Neural Network (PINN) framework for solving, animating, and cross-validating ODEs/PDEs, with 50+ built-in equations, SDF-based geometry/CSG, and automatic architecture selection
A toolkit for use with pytorch. Self-contained imperative programming, highly customizable, comes with its own instruction controller oriented to complex processes (partly multithreaded parallel, partly sequential serial, and able to be nested). Has built-in features to instantly visualize the training process (highly customizable), generate logs, auto-save, pause and resume training, automatic device selection, etc., and thanks to the use of multi-threading, it has no impact on the training speed at all.
A multi-agent AI framework for collaborative scientific research, implementing tournament-based hypothesis evolution and peer review systems
Select individually the product template visibility on each company
A multi-select button group
Diversity-aware sample subsetting and kNN-based extrapolation from one data matrix/layer to another across complete datasets.
using multi template on one view_config
A fast, keyboard-driven terminal UI for exploring AWX/Ansible logs with multi-select filtering, error navigation, and collapsible sections.
Select individually the partner visibility on each company
Select individually the partner visibility on each company
Allows setting multiple VAT numbers on any partner and select the right one depending on the fiscal position and delivery address of the invoice.
Knowledge-driven multi-agent orchestration with LLM-powered query analysis and intelligent agent selection
Streamlit component that allows you to render a menu widget with multiple columns but with only one globally selected value. It is possible to use photos for background inside the menu buttons.
A lightweight Python library that automatically discovers, evaluates, and tunes parameters of multi-provider LLM pipelines to balance quality, cost, and latency.
MSDA - An open source, low-code time-series multi-sensor data analysis, unsupervised feature selection, deep unsupervised anomaly detection & explainable time-series predictor library in Python.
A free multi-source GenAI orchestration library for automatic model selection and routing
Learning-to-rank for post-Pareto selection of consensus gene regulatory networks
Multi-LLM Response Validation & Selection Framework with RAG metrics evaluation
Streamlit component that allows you to choose multi selection but not extend your widget
Selective re-verification of safety/compliance constraints across multi-step AI processes
Allows setting multiple VAT numbers on any partner and select the right one depending on the fiscal position and delivery address of the invoice.
Interactive polygon annotation component for Gradio with multi-selection, hover effects, and customizable appearance
Open-source multi-agent orchestration CLI — spin up a 5-role AI team with automatic topology selection, model freedom, and white-box observability
Sparse Linear Multi-Task Regression
MOOSE-FS: Multi-Objective Optimized Ensemble Feature Selection
Scikit-learn compatible feature selection for binary and multi-class classification using the Kolmogorov-Smirnov (K-S) test, with pairwise / one-vs-rest comparison and Fisher / min / max p-value aggregation.
Thermodynamic routing of multi-reference quantum chemistry: C/T skeleton pre-screening and MGE-based active-space selection for CASSCF
Select individually the partner visibility on each company
Tags multiple selection
A Streamlit custom component for image selection with single and multi-selection support
Tags multiple selection
Select individually the partner visibility on each company
Underlying-agnostic day-by-day backtesting engine for NSE F&O options strategies (pluggable strike selection, delta-drift rebalancing, multi-cycle profit-target/stop-loss exits), backed by a DuckDB cache over the Nubra API. Built to sit behind the options-backtest Claude Code skill.
Train a Double DQN router that selects an optimal subset of agents for any multi-agent system.
A multi-objective particle swarm optimization framework for feature selection in bioinformatics.
Feature Selection Module for Data Sciences in Python
Select individually the partner visibility on each company
This python package simplifies the manipulation with the lists of multi-dimensional dictionaries as select, filter or join.
A module for selecting an item from a list of multi-field data in terminal
Select individually the product template visibility on each company
Feature Selection using Metaheuristics Made Easy: Open Source MAFESE Library in Python
Select individually the product visibility on each company