Local AI Apps and Tools for Mac

Utsuwa is an AI companion for people who want a virtual character that remembers their conversations. It combines a 3D avatar with voice chat and optional relationship progression inspired by dating sims.

MCP Gateway & Registry gives platform teams a shared catalog and access gateway for the tools their AI agents and coding assistants use. It addresses scattered server connections, credentials and access policies across an organization.

Optuna is a Python framework for machine learning developers and researchers who want to automate the search for model settings. Its search spaces can change with the choices made during a trial, so it can compare model architectures or classifiers as well as tune individual parameters. It's open source under the MIT license and can run on your own hardware as part of a Python workload.

NeuTTS is a collection of on-device text-to-speech models for developers building voice assistants and speech-enabled apps. It generates audio on your own hardware rather than sending speech generation to a cloud API.

Video2X processes video on your own hardware to increase resolution or add frames for smoother motion. It's for people improving existing footage, with several processing methods suited to anime and other video.

Atomic Chat is a local LLM app for people who want to chat with models on their own device or use them with coding assistants and AI agents. It began as a fork of Jan by Menlo Research.

LLMKube manages self-hosted LLM inference for teams and homelab owners who need several machines to serve models together. It brings Linux GPU servers and Apple Silicon Macs into the same Kubernetes-managed fleet.

Practical-RIFE generates intermediate video frames to increase frame rates. Built on RIFE and SAFA, this Python project is aimed at engineers and developers incorporating interpolation into video processing workflows, including animation and some diffusion-generated footage.

SLEAP helps behavioral researchers measure animal movement in recorded video. It trains models to estimate poses for single animals or groups, with human review during dataset creation and prediction checking.

MLX VLM is a Python package for developers and researchers who want to run multimodal models on their own Mac. It supports local inference and fine-tuning through MLX.

OpenEnsemble is a self-hosted AI assistant platform for people who want shared access on their own server, with a separate workspace for each user. Linux is the main installation target; macOS supports local development with different feature support. You can choose a single assistant or an ensemble of specialist agents using different models. It's open source under AGPL-3.0.

Codex CLI is a terminal coding assistant that works in your local repository on macOS, Windows and Linux. Developers can use it with models running locally through Ollama, including gpt-oss:120b, or connect to OpenAI through a paid ChatGPT account or API key. With OpenAI access, model requests go to the remote service even though file edits and commands run on your computer.

Falcon-H1 is a family of language models from the Technology Innovation Institute for developers building AI applications on their own hardware. Smaller models suit edge devices, while larger variants target server deployments.

MLX Audio is a Python library for developers building speech and audio applications on Apple Silicon Macs. It runs models locally using Apple's MLX framework, with support for generated speech, transcription and audio processing.

Swarm Fleet manages multiple terminal AI agents on your machine for developers coordinating coding, review and ticket work. Each agent has its own terminal, with shared controls for supervising their work.

Stable Fast 3D generates a textured 3D asset from a single object image. Built on TripoSR, it's aimed at game and VR developers, designers and people making product models for e-commerce.

LocalWriter adds AI writing assistance inside LibreOffice Writer for people who want to draft and revise text within their documents. It works with selected passages and requires a separate language model runner.

Chatless is a desktop AI chat client for people who want local models and cloud services in one app. It keeps conversation history on your computer and lets you ask questions about your own documents.

Tandem Browser is a desktop browser for people who want AI agents to carry out web tasks alongside them. You and the agent work in the same logged-in session, so you can watch its actions and step in when needed.

WhisperBuddy is a native macOS app for people who need transcripts, subtitles, or voice dictation while keeping their recordings on their own computer. It transcribes audio and video files, listens to live input, and translates transcripts offline. Audio and text stay on your Mac.

Semantic Kernel is an SDK for developers building AI agents and coordinated workflows inside applications. It lets developers choose local model backends or cloud providers for those applications.

Voibe is a paid AI dictation and meeting notes app for people handling confidential work, including legal, healthcare and finance professionals. It types spoken text into other apps and captures meetings on a Mac without a bot joining the call. Dictation works on Mac and Windows; meeting capture is Mac-only.

dstack is a self-hosted AI compute orchestration tool for teams running development, training and inference across cloud providers and their own servers. It gives those workloads a shared interface across Kubernetes, VMs and bare-metal clusters.

webctl gives developers and AI agents command-line control of a browser for website tasks. It uses Chromium through Playwright and connects with coding assistants through skills and prompts.

Jan is a desktop AI chat app for people who want to run models on their own computer while retaining the option to use cloud providers. Local model use works offline; choosing a hosted model sends requests to that provider.

GuideLLM benchmarks LLM deployments so engineering and ML teams can assess capacity and response times under expected traffic. It can test self-hosted servers through OpenAI-compatible or vLLM-native interfaces.

NullClaw runs AI agents on your own hardware or server for coding work and automated background tasks. It's aimed at developers who want an assistant that can carry out multi-step jobs with controls over its access and actions.

Fabric organizes reusable AI prompts by task for people who want repeatable ways to analyze content, write, or work with code. Its community-contributed prompts, called Patterns, provide a starting point without requiring you to write each prompt yourself.

Opcode gives developers a visual interface for working with Claude Code across projects. It brings coding sessions, reusable agents, and usage records into one desktop app.

BrowserSkill connects AI agents to your signed-in Chrome or Microsoft Edge profile for web tasks and website debugging. It's for people who want agents to work with existing accounts and developers investigating browser bugs.

Scarf gives people running the Hermes AI agent a native interface for conversations, project work and host management. It requires an existing Hermes installation; the iPhone companion, ScarfGo, connects directly to your hosts over SSH.

Super Agent Party is an AI companion platform for people who want a desktop character that can also carry out tasks. It combines character conversations with agents that operate applications and interact through messaging or live streams.

TalkToPaste is a voice dictation utility for macOS and Windows that runs speech recognition on your computer. The official site links to the VoiceToClipboard repository, which documents the local implementation and installation scripts. Transcription works offline after the speech model has been downloaded.

Slotstream runs Qwen3.8-Flash-Next on Apple Silicon Macs with too little RAM to hold the whole model. It's aimed at Macs with 16 to 64 GB of memory, for people who want local chat, answers about pictures or a backend for coding assistants.