Best local llm AI tools

PersonaXYZ is a private, on-device AI chat tool that allows users to create and interact with custom AI characters. It emphasizes privacy by running entirely in your browser without cloud servers or data sharing. Users can define unique personalities, voices, and memory settings for their AI companions, offering a truly personal and secure conversational experience.

Vectra is an open-source, production-grade SDK for Node.js and Python, designed to build, manage, and query advanced Retrieval-Augmented Generation (RAG) pipelines. It offers a comprehensive toolkit for developing context-aware AI applications, optimized for low latency, high precision, and scalability.

Apprendre is an AI-powered French learning workbench for macOS. It operates entirely on-device, ensuring 100% privacy with no subscriptions. It offers tools for sentence analysis, pronunciation, vocabulary management, and AI-generated lesson plans, all through a one-time "Pay What You Want" model.

Offeline is a powerful, privacy-first AI chat application that runs open-source Large Language Models (LLMs) locally on your hardware. It supports both browser and native desktop use, ensuring your data never leaves your machine. Enjoy offline capabilities, web search integration, document analysis, and voice support.

Sidian is an AI-powered code editor designed for modern developers. It features a sophisticated context engine that rapidly understands complex codebases, integrates with major AI providers like OpenAI and Google, and supports local models for enhanced privacy and flexibility.

Privacy AI is a native application for iPhone, iPad, and Mac that allows you to run powerful open-source large language models (LLMs) entirely offline. It ensures absolute privacy by processing all data on your device, with no data collection or internet connection required. Access models like LLaMA, Mistral, and Phi3 securely, with advanced customization options for a tailored AI experience.

Ollama is a powerful open-source framework for running large language models (LLMs) like Llama 3, Mistral, and Gemma locally on your own hardware. Available for macOS, Windows, and Linux, it simplifies the setup and management of open-source models, enabling private, offline, and cost-effective AI development and usage.

RAGDrive is a free, open-source, and no-code tool that allows you to chat with your documents privately and offline. Using RAG technology, it turns your files into an interactive knowledge base, accessible across Windows, Mac, iOS, and Android.

MinimalChat was a popular open-source, self-hostable AI chat platform known for its lightweight, minimalist design. It supported various GPT models, file uploads, and voice interactions, offering a private and flexible alternative to commercial services. Note: The project has ceased operations.

Socrates is an advanced AI tool for deep document analysis. It allows users to upload long documents like PDFs and DOCX to get complete, accurate answers. Its unique 'Deep Dive' feature provides thorough analysis, while features like Table AI and Local LLM support cater to researchers, legal professionals, and students seeking detailed insights with enhanced data privacy.

Protocraft AI is a versatile AI production studio for software development, data analysis, and creative tasks. It operates on a 'Bring Your Own Key' (BYOK) model, integrating with major LLMs like OpenAI, Anthropic, and Google, as well as local models. Available as both a web and desktop app, it allows users to interact directly with their local files, generate and edit code, create images, and automate prompts, all while maintaining full control over their data and privacy.

RecurseChat is a powerful, privacy-focused AI client for macOS. It operates local-first, allowing you to chat with local LLMs, ChatGPT, and Claude, even offline. Interact with your PDFs and documents securely on your device using RAG technology. It features multi-modal input, full-text search, and extensive customization without requiring a subscription.

Jan is an open-source, offline-first AI chat application that functions as a powerful alternative to ChatGPT. It allows you to run large language models (LLMs) like Llama 3 and Mistral directly on your computer, ensuring 100% privacy and data control. Jan also offers the flexibility to connect to cloud-based AI services and provides a local API server for developers.

EnConvo is a powerful AI agent launcher for macOS designed to automate tasks and boost productivity. It integrates seamlessly into your workflow with a Spotlight-like interface, offering over 150 tools, custom workflows, context awareness, and support for local LLMs, transforming how you interact with your Mac.

Socrates is an advanced AI tool for deep document analysis. Upload PDFs, DOCX, and more to get complete, accurate answers instantly. Features like Deep Dive, Table AI, and local LLM support provide unparalleled insights while ensuring data privacy. Ideal for researchers, professionals, and anyone needing to understand long documents quickly.

Chorus is a fast, lightweight desktop app for Mac that lets you chat with multiple cutting-edge AI models simultaneously. It unifies access to models like GPT, Claude, Gemini, and local open-source AIs in a single interface, complete with features for comparing responses, synthesizing answers, and integrating with your workflow through file uploads and screen context.

FridayGPT is an AI copilot for Mac that integrates ChatGPT, Claude, and local LLMs directly into your workflow. It offers instant access to AI, advanced voice-to-text transcription in over 100 languages, and one-click actions like grammar correction and text rewriting. Boost your productivity by using AI anywhere on your Mac without switching contexts.

ncurator is a browser extension that transforms your documents, webpages, and bookmarks into a personal, AI-powered knowledge base. Ask questions in natural language and get summarized answers directly from your own data, with a strong focus on local processing and data privacy.

Omnibot is a private, native AI assistant that runs large language models (LLMs) directly in your browser using WebGPU. It offers a completely offline and secure chat experience, ensuring your data never leaves your computer. Customize it with your own instructions for personalized responses.

GrammarBot is a privacy-focused AI grammar and spelling checker for macOS. It operates entirely offline using a local Large Language Model (LLM), ensuring your text never leaves your computer. With a simple hotkey integration, it works across all your applications. It's available for a one-time purchase, offering a lifetime license without any subscriptions.

MindMac is a powerful, native macOS client that provides a unified interface for interacting with a vast range of AI models, including OpenAI's GPT, Google Gemini, Claude, and local LLMs. It enhances productivity with features like an inline mode for use in any app, a rich prompt library, and extensive customization. It prioritizes privacy and security by storing API keys locally and communicating directly with AI providers.

LM Studio is a desktop application for Windows, macOS, and Linux that allows you to discover, download, and run open-source Large Language Models (LLMs) entirely on your local machine. It offers a user-friendly interface, an OpenAI-compatible local server, and robust privacy features, making it ideal for developers, researchers, and anyone seeking a private AI experience.

Msty is a user-friendly desktop application that simplifies running both local and online AI models. It offers a one-click setup, an offline-first approach for ultimate privacy, and powerful features like split-screen model comparison, advanced RAG via Knowledge Stacks, and full conversation control without needing technical expertise.

LM Studio is a user-friendly desktop application for discovering, downloading, and running open-source Large Language Models (LLMs) locally on your computer. It offers a simple chat interface and a local inference server, ensuring privacy and offline access.