Local AI Apps and Tools for Mac

GameStringer translates games for players and fan translators who want a language the game doesn't include. It detects the engine, extracts text and applies translated text to the game, with compatibility depending on the engine and title.

NotebookLlama is a self-hosted NotebookLM alternative for people who want control over the application code while using cloud services to process documents. It relies on LlamaCloud for document extraction and indexing, so self-hosting doesn't make the workflow fully local.

Noema is a local AI assistant for people who want to chat with models and get answers from their files on Apple devices. It brings models, documents and tools into a native workspace on iPhone, iPad, Mac and Vision Pro.

WhisperX is a local speech-to-text tool for transcribing interviews, meetings and long recordings. It builds on OpenAI's Whisper, adding individual word timings and optional speaker identification for subtitles and transcript review.

Deltafin runs full Kimi K3 on a single device for researchers and developers exploring large models on their own hardware. It preserves the original expert weights and complete expert bank, but responses are slow and long conversations take substantially longer than short completions.

AudioLDM 2 is a local AI audio generator for sound designers and researchers experimenting with synthetic sound. It uses pretrained models to produce audio from text and provides a Gradio browser interface alongside command-line access.

NoteGen is an AI note-taking app for collecting research, meeting material and ideas before organizing them into finished documents. Notes remain ordinary Markdown files, with attachments stored on your device by default.

Kiln is a desktop workbench for teams building and testing AI applications. Engineers, QA staff and subject matter experts can work with the same tasks and datasets, including contributing ratings and examples without writing code.

HiKid is a desktop app for children in non-English-speaking countries to practice speaking and listening. Kids talk with an AI in English through a microphone, without needing to type.

ebook2audiobook converts non-DRM ebooks into narrated audio with chapters and metadata. It's for readers who want audio editions of legally acquired books, with a choice of speech engines and narrator voices.

LLaVA is a vision-language model project for researchers and developers who want to ask questions about images on their own hardware.

sonible smart:EQ is a proprietary AI equalizer plug-in for producers and audio engineers who want to correct tonal imbalances while accounting for the rest of a mix. It runs in a desktop DAW on macOS or Windows, with native Apple Silicon support. Its cross-channel processing helps reduce frequency masking between tracks, so competing parts have more room in the mix.

OpenShell is a self-hosted runtime for teams that need autonomous AI agents to work with files and APIs under explicit access limits. It runs agents in isolated sandboxes and enforces policies at the kernel level.

OpenRig coordinates coding agents for developers working on projects that last weeks or months. You talk to a lead agent, which delegates to specialists and brings back results or decisions that need your attention.

Pooled runs a single open model across laptops, desktops and phones in browser tabs. It lets people combine their devices' memory to use a model that wouldn't fit on one device, for shared chat or coding tasks.

Yoji is an AI desktop companion for people who want a conversational assistant that can also act on their computer. It combines a customizable personality with file handling and task automation.

Private LLM runs AI chat on iPhone, iPad and Mac for people who want to use language models without sending conversations to a cloud service. It works offline after the first model download and doesn't require an account.

Emdash is a desktop development environment for developers who want to delegate several coding tasks at once. It keeps each task's branch, terminal, conversation, and review state together so parallel work stays separate.

sonible smart:reverb is a proprietary AI reverb plug-in for producers and audio engineers working on macOS or Windows. It analyzes a track's frequency content and timing to shape a reverb response around the source. Multiple instances can also work together across a mix to manage overlapping frequencies and control how near or far each sound feels.

Cactus is an on-device AI engine for developers adding automation to mobile apps, wearables and other small devices. Its Needle model turns requests into tool calls locally, including when the device has no internet connection.

Whisper Local is a free, MIT-licensed dictation app for Windows and macOS, aimed at people who want voice typing without cloud processing. It's an alternative to Wispr Flow and Dragon that inserts speech into the active text field, including in chat apps, browsers and code editors. It doesn't require an account or API key.

RealtimeSTT is a Python library for developers building voice assistants, dictation tools and apps that turn live audio into text. It can show text while someone speaks and produce a final transcript when they finish.

mcp-proxy connects AI clients and Model Context Protocol (MCP) servers that use different connection types. It's for developers who need desktop clients to reach remote tools, or want other clients to access a local MCP server.

Fed-BioMed lets hospitals and researchers train AI models across institutions while patient data stays on each institution's own infrastructure. It's a self-hosted platform for biomedical research that needs access to data across multiple sites but faces restrictions on sharing clinical records.

MEX keeps project knowledge alongside code so engineers and their AI coding agents can share context across teammates and sessions. Architecture, requirements and decisions live in readable Markdown that travels with the repository through Git.

LeanCTX helps developers control the information their AI coding tools receive. It runs locally between those tools and project files or command output, while your existing application keeps control of the model and workflow.

Open-LLM-VTuber is an AI companion for people who want to talk with a customizable animated character. Local language and speech models let it work fully offline, with conversations staying on your device.

Marker is a local document converter for developers and teams preparing PDFs, scans and Office files for document processing or AI workflows. It extracts text while retaining structure such as tables, equations and page layout.

MiniCPM-V is a family of local vision-language models for developers building applications that interpret images and video. It can run on phones and other hardware you control.

nanochat is a toolkit for researchers and developers who want to train an LLM and inspect the pipeline themselves. Its small Python codebase covers the stages between preparing a tokenizer and chatting with the resulting model.

AppFlowy is a workspace for documents, projects and AI. Its desktop Local AI plugin connects to Ollama for local model use. AppFlowy also offers a self-hosted server deployment with language and embedding models inside your environment, including air-gapped operation. The desktop plugin and server deployment are distinct ways to use AI.

LoopX is an open-source control plane for AI agents working on multi-day coding, research and personal projects. It preserves the goal and decisions between sessions so work can resume after a pause or handoff.

SymForge is a local MCP server for developers using AI coding agents on large repositories or long source files. It gives agents focused views of symbols and their relationships so they can investigate code without reading entire files.

X-AnyLabeling is a desktop annotation workspace for researchers and teams preparing text, image, video, point cloud, and multimodal training datasets. Models generate initial labels, and reviewers correct them in the same workspace before exporting the data. It runs on Windows, Linux, and macOS under the GPL-3.0 open-source license.