Local AI 44

AI memory assistant for Mac that writes with context in your tone. Goldfish is an AI memory assistant for Mac that privately remembers what you have been working on across your device. It allows users to write better from any application with full context and in their own tone, eliminating the need to copy, paste, or re-explain background information.

Omnibot is an in-browser AI platform that runs LLMs natively and privately. Omnibot is an innovative AI platform that leverages WebGPU to run large language models (LLMs) natively in your browser, ensuring your data is processed securely on your device without any server-side interference. With offline functionality, Omnibot brings you an in-browser and offline AI experience. It allows you to use selected LLMs offline once the initial download of a model is processed. All AI models run locally (client side) on your hardware, ensuring that your data is processed only on your PC. You can also add custom instructions/memory to allow the AI to provide better and more personalized responses.

Open-source, self-hosted personal AI infrastructure for autonomous task execution and privacy. clawbot is an open-source, self-hosted personal AI assistant and infrastructure that operates entirely on the user's own hardware. Designed for privacy and autonomy, clawbot moves beyond reactive chatbots (Generation 1 & 2) to become a proactive system capable of executing real tasks, integrating deeply with digital environments, and maintaining conversation continuity across over 15 messaging platforms. It features a model-agnostic architecture, allowing users to choose between models like GPT, Claude, or local models via Ollama.

On-device voice assistant for conversational AI coding SKI is an on-device voice assistant for AI coding agents such as Claude Code, Cursor, Codex, Gemini CLI, Windsurf, and OpenClaw. It lets developers speak naturally to their coding agent, have the agent build and manage code, and hear its responses aloud. Unlike dictation tools, SKI provides a full two-way voice conversation with local speech-to-text, neural voice synthesis, full-duplex interruption, agent status updates, multi-project support, and optional meeting participation. Voice data, transcripts, and local meeting recordings remain on the user's computer and are not uploaded.

Offline AI app for iPhone, iPad, and Mac, ensuring total privacy and customizable AI models. Privacy AI is a mobile and desktop application that allows users to run advanced AI models offline, ensuring complete data privacy. It features models like LLaMA, Mistral, Phi3, StableLM, and Gemma2, with customizable settings for fine-tuning interactions. The app is available for iPhone, iPad, and Mac, offering both free and premium options, including a one-time purchase model.

AI-powered Photoshop plugin for enhanced photo-bashing using stable diffusion. Bashful.ai enhances photo-bashing techniques for artists by integrating stable diffusion and Photoshop. It allows users to generate single or multiple layers using AI with multiple prompts and settings. However, as of June 22, 2023, Cloud Generation and Creative Cloud support are no longer available. Local AI Image Generation is still supported.

Personal AI app for offline, private chats with local AI models and documents. RecurseChat is a personal AI app designed for chatting with local AI offline and privately. It allows users to use local AI as their daily driver, enabling them to chat with local documents, images, import ChatGPT history, perform full-text searches, and more. It's a powerful, fast, and local-first AI client for local LLMs, ChatGPT, and Claude.

Klee is a local and secure AI-powered note and knowledge base application. Klee is a note and knowledge base application with client-side AI models, offering local and secure AI on your desktop. It supports DeepSeek, Llama, Qwen, and Gemma, ensuring data security and privacy with on-device processing.

Offline-first macOS screenshot organizer using local AI for private, searchable digital memory. ScreenSorts is an offline-first screenshot organizer specifically designed for macOS that functions as a 'second brain' for your digital memory. It uses local AI and on-device vision models to make every pixel of your screenshots searchable. The utility features semantic search, OCR (Optical Character Recognition), automatic tagging, and URL detection, all while ensuring total privacy by processing data entirely on the Apple Neural Engine without cloud or API dependencies.

No-code, on-device AI with voice and RAG for local document interaction. RAGDrive.com is a No-Code On-Device AI with Voice & RAG. It is a user-friendly local AI inferencing solution. It allows users to 'talk' to their documents using Retrieval Augmented Generation (RAG) technology. Users can choose to operate completely offline and private or leverage inference providers when they need more computing power.

Secure AI copilot alternative for enterprises, ensuring data protection and compliance. Opilot is a secure copilot alternative designed to help enterprises use AI securely with full compliance and data protection. It allows users to run their copilot locally, ensuring sensitive data is never shared. Opilot offers features like summarizing, explaining, and translating text within any web app, enhancing productivity while maintaining privacy and security.

System-wide local AI autocomplete assistant for macOS apps. Typeahead is a system-wide AI autocomplete writing assistant for macOS. It finishes sentences across every application on your Mac, such as Slack, Notion, and email clients. It runs locally on an onboard AI model, meaning it works entirely offline without requiring cloud processing or sending your data to external servers. It learns your writing style over a few days to provide tailored inline suggestions that adapt to your personal voice.

Open-weights uncensored AI video generator based on LTX 2.3 for local GPU use. Sulphur 2 is an uncensored, open-weights AI video generator fine-tuned on Lightricks LTX 2.3. It is a community-released model designed to run locally on consumer GPUs. The release includes base weights, distilled LoRAs for faster generation, and specialized ComfyUI workflows. It focuses on high-fidelity realism by training on approximately 125,000 video clips while intentionally excluding 2D animation. As a derivative of the LTX 2.3 DiT-based foundation model, it supports both text-to-video and image-to-video tasks and includes a local prompt enhancer based on Qwen 3.5 to maintain a fully on-device creative pipeline.

Tool to find and run private local AI models on your laptop. Suverenum is a simple online tool designed to help users find and run the perfect local AI model for their laptop. It detects the user's hardware specifications and prescribes a suitable AI from over 10,000+ options, eliminating jargon and confusion. The platform emphasizes enabling private and offline AI usage, claiming local AI can match cloud performance for everyday tasks without sacrificing quality or requiring a computer science degree.

Znote is a private, local AI-powered note-taking and automation tool for coding and data visualization. Znote is an application that allows the development and instant code execution to learn and prototype your ideas faster. It works with JavaScript and Markdown, providing various templates and AI integration. It's a private, AI-powered note-taking and automation tool that operates 100% locally. It allows users to take private notes, transcribe meetings, generate reports, and run code snippets with local AI. It is a powerful Jupyter alternative for JavaScript, ideal for coding, automation, and data visualization.

Offline AI voice generator and unlimited voice cloning app for Mac. VocoSpeech is a native macOS application designed for high-quality, offline AI voice generation and instant voice cloning. It serves as a local alternative to cloud-based services like ElevenLabs, running 100% on Apple Silicon to ensure that sensitive audio data remains private and secure. The app allows users to create natural-sounding text-to-speech (TTS) for various content types, including videos, podcasts, and tutorials, while providing granular controls over emotions, sound tags, and speaking styles.

Native desktop app for controlling secure, local AI agents without terminal commands. EasyClaw is the native OpenClaw application for Mac and Windows, providing a graphical interface to control AI agents without using the terminal. It is built on the OpenClaw framework and focuses on a 'privacy-first' approach, where everything runs locally on the user's computer within a secure sandbox. The app allows AI agents to interact with system-level UI and web applications natively. It also features a 'Global Relay' system, enabling users to control their desktop workstations remotely via popular messaging apps like WhatsApp, Telegram, and Slack.

Local AI solution for Mac and Windows with focus on accessibility and privacy. HyperMink AI is a local AI solution for Mac and Windows that offers fast, local, long-form conversations, local PDF and CSV inference, vision capabilities, and the ability to read web pages. It requires no complex installations, subscriptions, or GPU. HyperMink System 1 is a personal AI assistant accessible via a simple USB plug-in. The platform emphasizes accessibility and privacy, aiming to demystify AI for everyday users.

Open-source tool for building document question-answering systems with local AI models. RLAMA (Retrieval-Augmented Local Assistant Model Agent) is an open-source AI solution that integrates with local AI models to create, manage, and interact with Retrieval-Augmented Generation (RAG) systems. It allows users to build powerful document question-answering systems with multiple document formats, advanced semantic chunking, and local storage and processing.

Local, private macOS meeting transcription tool with Whisper-powered offline processing and Claude integration. trnscrb is a local meeting transcription tool for macOS that lives in the menu bar and automatically detects meetings on platforms like Zoom, Google Meet, Microsoft Teams, Slack, and FaceTime. It utilizes OpenAI's Whisper model to perform on-device transcription via Apple Silicon Metal acceleration, ensuring that no audio or transcript data is sent to the cloud. The tool integrates with Claude Desktop through the Model Context Protocol (MCP), allowing users to search, summarize, and extract action items from their meeting history directly through the Claude interface. It saves transcripts as plain .txt files with speaker diarization and requires no account or subscription.

Private, local AI assistant for secure AI conversations using open-source models. Sanctum is a private, local AI assistant that allows users to experience secure AI conversations powered by open-source models encrypted locally on their device. It enables users to run full-featured LLMs in seconds, ensuring data privacy and security.

Native app for local AI model experimentation without complex setup or GPU. Local AI Playground is a native application designed to simplify the process of experimenting with AI models locally. It allows users to download and run inference servers without needing a full-blown ML stack or a GPU. The application supports CPU inferencing and model management, making AI experimentation accessible and private.

Private Mac AI assistant for searching, remembering, and managing work locally. Zenpa is a private AI assistant for Mac that remembers work across emails, chats, notes, documents, and meetings. It provides answers with sources, maintains a local memory vault, drafts messages, transcribes meetings, and offers system-wide dictation. All processing and stored data remain on the user's Mac.

Open-source local AI assistant that automates tasks via popular chat apps like WhatsApp. Clawd Bot (also known as OpenClaw) is an open-source personal AI assistant that runs locally on your machine. It allows users to control AI through common chat platforms like WhatsApp, Telegram, Discord, and Slack. Unlike basic chatbots, Clawd Bot can perform real-world tasks such as managing emails, scheduling calendar events, checking in for flights, controlling smart home devices, and navigating the web via browser control. It prioritizes privacy by keeping data on the user's hardware and supports various AI models including Claude, GPT-4, Gemini, and local LLMs like Llama.