Directory
Published directory entries matching your search.
Elicit is an artificial intelligence tool built for research and decision-making use cases. Its core functions include synthesizing evidence, analyzing research landscapes, designing programs and experiments, drafting proposals, and assessing tradeoffs. The tool is intended to support researchers and related professional workflows.
FastChat is an open platform for training, serving, and evaluating large language model based chatbots. Its core features include training and evaluation code for models such as Vicuna and MT-Bench, and a distributed multi-model serving system with a web UI and OpenAI-compatible RESTful APIs.
Featureform is an open-source virtual feature store hosted on GitHub under the featureform organization. It is designed to turn users' existing data infrastructure into a feature store, with supporting resources including a public website, documentation, community forum, and explanatory material on its core abstraction and unique value proposition.
Friday is a developer agent that helps create applications with AI assistance. It provides a core prompt for the application foundation and allows adding unlimited sections, each a prompt representing a specific part of the app.
Future AGI is an open-source, self-hostable platform for evaluating, observing, and improving LLM and AI agent applications. It combines tracing, evals, simulations, datasets, a gateway and guardrails on one platform with a feedback loop. The Apache 2.0 core can be self-hosted, and a managed Cloud option is offered.
GeneticSharp is a C# genetic algorithm library described as fast, extensible, multi-platform and multithreading, intended to simplify development of applications using genetic algorithms. The source states it can be used in .NET 6, .NET Standard and .NET Framework apps, including ASP.NET MVC, ASP.NET Core, Blazor, Web Forms, UWP, Windows Forms, GTK#, Xamarin, MAUI and Unity3D games.
Turi Create is a toolkit that simplifies the development of custom machine learning models, offered as an archived repository. It supports tasks such as recommendations, object detection, image classification, image similarity and activity classification, and can export models to Core ML. The repository was archived by its owner on December 21, 2023, and is now read-only.
High Charts is a JavaScript charting library designed for use in web applications, dashboards, grids and frameworks including React. It offers products for core charting, stock data, maps, Gantt charts, grids and dashboards, and is used by a large number of global enterprises. The library provides built-in adaptive functionality and extensive customization options for interactive data visualizations.
Katonic AI is a full-stack enterprise platform for building, deploying, and governing AI agents on customer-owned infrastructure, including on-premise, private cloud, and air-gapped environments. It incorporates NVIDIA NeMo guardrails, enforces zero data egress, and provides three core surfaces (Studio, Workroom, Control Room) alongside more than 80 pre-built agents and over 240 governed MCP tool servers.
LangMagic is an adaptive language learning platform that provides reading, listening, and grammar practice tools for approximately 30 languages, covering A1 to C2 proficiency levels. It offers two core products: the Endless Book, an adaptive reader that adjusts difficulty and provides word definitions and audio, and a content portal with a library of adaptive learning materials for learners and educators. The platform adjusts to each user's pace and chosen content genres.
A guide that introduces data processing and cleaning in JavaScript, teaching how to load, modify and transform data using JavaScript libraries. It covers tasks geared around preparing data for further analysis and visualization, demonstrated with core JavaScript API, d3.js and lodash. It assumes some basic knowledge of JavaScript.
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.
An interactive educational game built for the Google Gemma 3n Impact Challenge. It uses Gemma 3n via Ollama for on-device, structured educational conversations about sustainable farming and botany, and runs locally with no internet required for core features.
Meitu Inc. is an AI-driven technology company centered on the core ideal of beauty. It develops imaging products to simplify image, video, and design creation, with a product portfolio including BeautyCam, Portrait Photography Pro, Wink, Designkit, Kaipai, and others. The company also operates an AI open platform and publishes sustainability and investor-related information.
MITIE is a set of tools for information extraction built on dlib. It provides named entity extraction and binary relation detection, along with tools for training custom extractors and relation detectors. Pre-trained models support English, Spanish and German. The core is written in C++, with bindings for Python, R, Java, C and MATLAB.
MMDeploy is documented at version 1.3.1 and covers getting started, converting, running, evaluating and quantizing models, building from source or Docker image, and SDK usage. Its backend support pages describe ncnn, ONNX Runtime, OpenVINO, PPLNN, SNPE, TensorRT, TorchScript, RKNN, TVM and Core ML, and its codebase support covers several OpenMMLab projects.
Netron is a viewer for neural network, deep learning and machine learning models. It supports formats including ONNX, TensorFlow Lite, PyTorch, TensorFlow, Core ML, OpenVINO, Keras, Caffe, Darknet, Safetensors and NumPy. It is available as a browser version and installers for macOS, Linux and Windows, plus a Python package. Experimental support exists for MLIR, JAX, GGUF and other formats.
Neural Networks and Deep Learning is a free online book by Michael Nielsen. It teaches core concepts of neural networks and deep learning, covering handwriting recognition, backpropagation, and improving how neural networks learn. The work is licensed for copying and sharing but not for selling.
NumPy is a Python library providing a multidimensional array object and routines for fast operations on arrays, including mathematical, logical, sorting, Fourier transforms, linear algebra and random simulation. It is open source under a BSD license and is described as the fundamental package for scientific computing in Python, with core code written in optimized C.
Open RAG Eval is an open-source Python evaluation toolkit for Retrieval-Augmented Generation pipelines. It provides TREC-RAG evaluation metrics and a modular design for custom metrics and connectors, with core metrics that do not require golden chunks or golden answers.
This GitHub repository contains an open solution for the Kaggle Toxic Comment Classification Challenge. It includes starter code for the challenge, documents the project's core idea, notes ensemble prediction capabilities, includes a disclaimer, and accepts community contributions.
Apache OpenNLP is a machine learning based toolkit for the processing of natural language text. It supports tasks such as sentence segmentation, tokenization, lemmatization, part-of-speech tagging, named entity extraction, chunking, parsing, language detection and coreference resolution. The project is developed by volunteers and welcomes contributions, from small documentation fixes to new components.
pgvecto.rs is an open-source tool that provides scalable, low-latency, hybrid-enabled vector search for PostgreSQL. It is designed to enhance vector search capabilities without modifying the core database system, per its official GitHub repository.
A general-purpose network embedding framework: pair-wise representations optimization Network Edit.
