Directory
Published directory entries matching your search.
LocalAI is described as an open source AI engine that runs models, including LLMs, vision, voice, image and video, on any hardware without a GPU. It presents itself as a drop-in replacement for most upstream APIs and includes a built-in agent platform powered by LocalAGI, whose agents can reason, use tools and maintain memory. Image generation with Stable diffusion on CPU is also supported.
A tool that provides a Model Context Protocol server for any web application with an OpenAPI specification. It can connect Claude Desktop and other apps to external tools and data services, similar to ChatGPT plugins.
Open-source project that provides machine-learning models, research, training resources, or evaluation tools.
MALLET is a Java-based package for statistical natural language processing, document classification, clustering, topic modeling, information extraction, and other machine learning applications to text. It includes tools for converting text to features, classifiers such as Naïve Bayes, Maximum Entropy and Decision Trees, sequence tagging with Hidden Markov Models and Conditional Random Fields, and sampling-based topic model implementations.
Mastra is a TypeScript AI framework for building agents and AI applications. It includes built-in memory, tool support, MCP compatibility, and observability features to support development from prototype to production. The framework also offers workflow tools, agent factory functionality, cloud deployment servers, and an agent builder for evaluation and iteration.
MaxVideoAI is a pay-as-you-go AI video generator that lets users compare models such as Seedance, Kling, Veo, LTX, Wan and Pika before generating, with pricing shown upfront. An MCP integration connects compatible assistants and automation tools to the models, credits and private media library of a MaxVideoAI account for quotes, approvals and results.
Metorial is an agentic infrastructure platform for AI-native companies. It provides a single unified platform for employees, AI agents, and AI clients to connect tools and skills, with built-in governance, access control, and tracing capabilities. The platform supports development of customer-facing agents, internal assistants, and scalable AI workforces.
Model-agnostic SDK for building, orchestrating and deploying AI agents and multi-agent systems, with built-in support for OpenAI, Azure OpenAI, Hugging Face and Nvidia. It offers tools/plugins, memory, planning, vector database integrations and a process framework. Microsoft states that Semantic Kernel is now Microsoft Agent Framework.
Mirascope is a project labeled the LLM Anti-Framework that provides one unified interface for using frontier LLMs. Its examples show calling LLMs with a decorator, getting structured output via Pydantic models, and building an agent with tools. It is organized as a monorepo with Python and TypeScript implementations plus documentation.
Machine Learning Visualized is a book of Jupyter Notebooks that implement and mathematically derive machine learning algorithms from first principles. Each notebook's output is a visualization of the algorithm during training, converging at its optimal weights. Chapters cover optimization, clustering and reduction, linear models and activation functions, and neural networks.
MLflow is an open source AI engineering platform for agents, LLMs, and ML models. It provides tools for debugging, evaluating, monitoring, and optimizing AI applications, including tracing, evaluation metrics, prompt management, an AI gateway, and an agent server. The project is released under the Apache 2.0 license.
mlsysbook supports machine learning models, deployment, inspection, datasets, or AI development workflows.
Open-source project that provides machine-learning models, research, training resources, or evaluation tools.
ModelScope supports machine learning models, deployment, inspection, datasets, or AI development workflows.
ModelScope Finetuning supports machine learning models, deployment, inspection, datasets, or AI development workflows.
ModelViewer is a web component for displaying interactive 3D models on the web and in AR. It offers documentation, examples, API reference and addons, plus an editor for testing models and downloading a starter website. It supports the last two major versions of evergreen desktop and mobile browsers and the last two versions of Safari.
NCNN is a neural network inference framework optimized for mobile, embedded, and desktop deployment. It has no third-party runtime dependencies and runs across CPU and Vulkan GPU backends. Tools such as pnnx convert PyTorch and ONNX models to ncnn, allowing deployment to phones, PCs, browsers, and edge devices. The project is used in several Tencent applications.
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.
neuml/txtai is an all-in-one AI framework for semantic search, LLM orchestration, and language model workflows. It is open source and hosted on GitHub. The framework provides tools for building applications that understand and generate text.
new.space is a private AI tool that lets users control their Mac from their iOS device, Mac, or web browser. It supports running frontier AI models, local models, and Ollama on a Mac, and integrates the user's calendar, files, reminders and conversations in one interface. It offers local model deployment, bring-your-own API key options, and a no-logging proxy, and states that user data is never used for AI model training.
Nilearn provides statistical and machine-learning tools for analyses of brain volumes and surfaces, with documentation and a community. It supports general linear model based analysis and uses the scikit-learn toolbox for multivariate statistics, with applications such as predictive modeling, classification, decoding and connectivity analysis. It is written in Python and installable with pip.
Platform and SDK for AI Engineers providing tools for LLM evaluation, observability, and a version-controlled enhanced prompt playground.
PhotoGPT creates ecommerce images, product ads and marketing visuals with AI, generating lifestyle shots, AI models and listing assets. Tools include AI product photography, ad clone, product detail pages and virtual try on. The Starter plan is listed at $10 per month billed annually at $96 per year with 500 credits per month.
Pipcook is a JavaScript application framework for machine learning and its engineering, aimed at Web developers. It provides subprojects including a machine learning pipeline framework, management tools and a JavaScript runtime for machine learning. A Pipcook Pipeline composes scripts and outputs an NPM package containing the trained model and JavaScript functions. The documentation describes a workflow of install, train, test and deploy using the Pipcook command-line tool.
