Local AI Apps and Tools for Mac

ONNX Runtime is an AI inference and training engine for developers adding models to apps and services. It supports deployment on a user's device or a server, including applications that need the same model format across platforms.

Palace gives AI coding agents persistent memory of project decisions, conventions and fixes. Developers can carry that context between sessions in Cursor, Claude Code, Codex and Claude Desktop.

Halo is a desktop AI workstation for people who want agents to write code, manage files and handle recurring work through a visual interface. You can switch between Claude Code and Codex within the same app.

Augmentoolkit turns documents into datasets for training an LLM on a particular subject. It's for people building custom models around material such as research papers or fictional lore.

Translate Books With LLMs translates books, documents and subtitles using a local or cloud model. It's for readers and translators working with long texts who need formatting and terminology to carry through the translation.

Backyard AI is a desktop AI app powered by llama.cpp. The desktop app is deprecated and no longer supported, which limits its suitability for people choosing software for ongoing use.

SwarmLLM is a ChatGPT alternative for people who want to run AI models on their own hardware. It can use a single computer or combine several machines to handle a model that won't fit on one.

sonible pure:unmask is a proprietary AI audio plug-in for music creators and audio mixers whose tracks compete for space in a mix. It uses spectral unmasking to reduce frequency overlap, letting a priority track come through more clearly while processing the track beneath it.

Tolmach translates complete books for readers and translators who need consistent terminology across chapters. It uses local LLMs through Ollama, with optional Ollama Cloud models.

Lotti is a private logbook for people who want to keep their plans and a record of what actually happened together. It connects daily planning with personal notes and work history while keeping the underlying record on your devices.

OpenChamber is a workspace for developers who want to run AI coding agents on their own computer or server and review the results. It uses OpenCode to run agents and keeps projects and sessions accessible across devices.

Claude Task Master helps developers turn product requirements into tasks they can work through with a coding assistant. It keeps task planning and progress tracking inside the editor or terminal where development happens.

PicoClaw is a self-hosted personal AI assistant that can use local models through Ollama or vLLM. It's aimed at people who want an agent on their own hardware, including small Linux boards and Android phones. Hosted providers are optional, but choosing OpenAI, Anthropic, Google Gemini or DeepSeek sends model requests to those services and requires internet access and API keys.

Lap is a desktop photo manager for family albums, photographers, and large personal libraries. It works with photos in your existing folders and uses local AI to help you find images without uploading them to a cloud photo service.

Candle is a Rust machine learning framework for developers embedding local AI in applications or deploying models on their own servers. It supports inference and training, including small CPU deployments for serverless applications.

Kelivo is an LLM chat client for people who want local and cloud models in one app while keeping conversation history on their device. It connects to Ollama, self-hosted OpenAI-compatible services and providers including OpenAI, Gemini, Claude, DeepSeek and OpenRouter.

LongMemory gives LLM applications and AI agents persistent memory across sessions. Developers can use it to retain project decisions and conversation context while distinguishing current facts from information that was true earlier.

Parler-TTS is a text-to-speech library for developers adding speech to applications and researchers adapting speech models. It generates audio with a voice style you describe in text.

WhisperLive turns speech into text as audio arrives, using OpenAI's Whisper models. It's for developers and teams who want to run transcription on their own machine or server and connect it to live audio or recorded files.

TokensBurned tracks AI coding activity for developers who want usage statistics on their GitHub profile. Its client processes records locally, but the profile cards depend on a hosted service that receives aggregate data.

AI Notebook is a desktop research notebook for asking questions about your own documents and checking the passages behind the answers. It suits people who want a local NotebookLM alternative with their research and notes in one workspace.

BitNet is Microsoft's local LLM inference framework for developers and researchers working with compatible 1-bit models. Its bitnet.cpp runtime focuses on faster inference and lower energy use on your own hardware.

Yap is a voice dictation app for people who prefer speaking to typing emails, messages or prompts on their Mac. It transcribes speech on-device and inserts the result into the text field you're using.

Magnitude is a local LLM engine for people who want to run AI agents on their own hardware. It adapts model execution to your machine and connects to coding assistants you already use.

GPT4All is a local AI chatbot for people who want language models and document conversations on their own computer. Model inference and LocalDocs processing run on the device without a cloud connection.

spaCy is a Python library for developers and data scientists who need to extract structured information from text in their own applications. It runs on macOS, Windows and Linux, with model packages that become part of your application. It's free and open source under the MIT license.

NextChat is an AI chat interface for people who want to use self-deployed LLMs and cloud models in one application. It connects to LocalAI and RWKV-Runner, and supports OpenAI, Claude, Google Gemini and DeepSeek.

CleanStream filters unwanted speech in live OBS audio for streamers and people recording spoken content. It runs speech recognition on your machine with Whisper through whisper.cpp, and introduces a playback delay while it decides which audio to keep.

Obsidian Local GPT is an AI writing assistant for people who keep their notes in Obsidian. It helps you work with selected text and related notes, using local models or a remote AI service.

ilastik is a desktop tool for researchers who need to identify, classify or count cells and other objects in experimental images. It runs on Linux, macOS and Windows. Its main draw is interactive training: you mark examples in an image with brush strokes and see predictions as you work, without needing machine learning expertise.

Crush is a terminal AI coding assistant for developers who want an agent to work with their code and existing tools. The application runs on your machine; your chosen backend determines where model requests go.

Parrot is an open-source desktop app that reads selected text aloud in other applications. It's for people who prefer listening to written material or need text-to-speech for accessibility. It runs on macOS, Windows and Linux, and builds on Handy by CJ Pais as an MIT-licensed fork.

Dive is a desktop AI agent for people who want a language model to work with files, shell commands and connected tools. It supports models with function calling and acts as a host for Model Context Protocol (MCP) servers.

Scrieb transcribes recordings and meetings for people who need to keep sensitive conversations on their own computer. Speech recognition, summaries and meeting chat all work locally, with no cloud processing option.