Directory
Published directory entries matching your search.
KoNLPy (pronounced "ko en el PIE") is a Python package for natural language processing of the Korean language. It is open source software released under GPL v3 or above, and users are asked to acknowledge its use with a citation.
Kycnotme is the official source repository for the kycnot.me website, built with Astro, TypeScript, Python and PostgreSQL. The README describes setup using nvm, docker and just, database initialization and a local development server. Content is limited to development and installation instructions.
Label Studio is an open source data labeling and annotation platform for multi-modal data, including text, images, audio and time series. It lists uses such as LLM and agent evaluation, computer vision, NLP and document tasks, and audio transcription. It offers API, Python SDK and webhooks, and is available via pip, Homebrew, Git and Docker.
Integrate with providers using LangChain Python.
A Python framework for building LLM-powered applications through a multi-agent paradigm. Developers set up agents, equip them with optional components such as LLMs, vector stores and tools, assign tasks, and have them exchange messages to solve problems. It works with practically any LLM and does not use LangChain.
LaTeX-OCR converts an image containing a formula to corresponding LaTeX code. It includes a user interface written with PyQt5 and is installed through a Python environment with PyTorch. A standalone version is planned, and an AppImage for Linux is in development.
Analyzes structured data and helps produce queries, insights or visualizations.
A personal collection of solutions to LeetCode problems written in C++23, Java, Python, MySQL, and TypeScript. The site aims to provide readable code with consistent style. Solutions can be found by searching by number or title. The repository does not accept pull requests, though forking is allowed.
Leon is an open-source personal assistant that can run on a user's server. It is built on Node.js, Python and artificial intelligence concepts, and responds to requests. It uses a modular architecture for creating or using skills, and supports several cloud and offline text-to-speech and speech-to-text solutions.
LIBSVM is an integrated software library for support vector classification, regression and distribution estimation. It provides a simple interface for linking with other programs and includes multi-class classification, cross-validation and probability estimates. Interfaces exist for Python, R, MATLAB and other languages.
Lifelines is a complete survival analysis library, written in pure Python.
LightFM is a Python implementation of recommendation algorithms for implicit and explicit feedback. It allows item and user metadata to be incorporated into matrix factorization algorithms, representing users and items as sums of latent feature representations. Installation is available from PyPI, and a Docker setup is provided for running examples and tests.
LightlySSL is a Python computer vision framework for self-supervised learning on images, written in a PyTorch-like style. It exposes low-level building blocks such as loss functions and model heads, supports custom backbone models for self-supervised pre-training, and supports distributed training using PyTorch Lightning. Sample code covers models including MoCo, SimCLR, BYOL and DINO.
Lightwood is an AutoML framework that generates and customizes machine learning pipelines using a declarative JSON-AI syntax. It handles data types such as numbers, dates, categories, tags, text, arrays and multimedia formats, and includes a time-series mode. Users can override defaults or replace pipeline steps, and the framework generates Python code for the pipeline.
Linked COVID-19 Data transforms data from the JHU, ECDC and RKI interfaces into RDF. Dashboards query a prototypical demo SPARQL endpoint using Highcharts. The official data and Python script are available on Zenodo.
Linux.org is a friendly Linux forum where members register and post in discussion threads. The site also hosts articles and how-to series covering topics such as a Python series, Proxmox VE, the Arduino Uno Q and the PocketBeagle 2.
LiteLLM is an open-source library that provides a single, unified interface to call over 100 LLMs using the OpenAI format. It includes a Python SDK whose completion() function uses the same arguments across providers and returns responses in the OpenAI Chat Completions format, plus a self-hosted gateway with virtual keys, cost tracking and an admin UI.
Little Ball of Fur is a graph sampling extension library for Python and a graph sampling extension library for NetworKit and NetworkX. It consists of methods that can sample from graph structured data, covering vertex, edge, and exploration sampling techniques with a unified application public interface.
Liveweave is a browser-based workspace for HTML, CSS, and JavaScript with a live preview and an AI coding assistant. It also offers a Python playground, an SVG graphics editor, and a color explorer. The site hosts a showcase of user-created experiments, such as templates and a 3D bowling game.
A self-hosted proxy providing OpenAI and Anthropic compatible API endpoints for multiple LLM providers, so existing applications can use any supported provider through a single API key. It includes a FastAPI proxy application and a reusable Python resilience library for API key management, rotation, and failover.
LLMFlows is a Python framework for building LLM applications such as chatbots, question-answering systems and agents. It provides abstractions for using LLMs and vector stores, with explicit classes that avoid hidden prompts or LLM calls, aiming to make monitoring, maintenance and debugging easier.
Lobe is a free tool for Mac and PC that helps users train machine learning models and ship them to any platform. The GitHub organization hosts starter projects for iOS and web, a Python toolset for working with Lobe models, and tools for creating image-based datasets. The team states the Lobe desktop application is no longer under development.
LocalGPT is an on-premise document intelligence platform that lets users chat with their documents on their local device using GPT models. It supports PDF, DOCX, HTML, Markdown, and TXT files and combines dense vector search with LanceDB full-text search and a cross-encoder reranker. It runs with a plain Python RAG core and offers generation models via Ollama.
Lucas Chess is an open source chess program developed with Python and PySide2 for training, playing and competing on a PC. It includes 57 prepared engines with levels from 0 to 3600 elo, and other UCI engines can be added. The program offers trainings, tournaments and PGN database tools.
