On-device AI execution
Runs requests on your Mac so content does not need to leave the device for local workflows.
Local
Freemium
Local is a macOS app that runs AI on your own machine, tuned to your Mac’s chip and memory for chat, coding, meeting notes, and private on-device workflows.
What is Local?
Local is a macOS app for running AI on your own machine. It is built around the idea that chat, coding, meeting notes, and other common AI tasks can run on-device instead of in the cloud, so your work and memory stay on your Mac by default.
The app uses BaseRT, Base Compute’s inference engine, to tune itself to your chip on first launch. It reads your Mac’s hardware and memory, then recommends models that fit and runs them locally. The product also supports optional cloud models through your own API key, but those requests are separate from Local’s privacy mode.
What can Local do?
Chip-aware model selection
Reads your chip and memory to suggest models that fit your machine.
BaseRT optimization
Ships with BaseRT, which is compiled for your silicon and designed to improve tokens per second on supported Macs.
Chat, coding, and meetings workflows
Covers file-based chat, in-place coding assistance, and on-device meeting transcription with speaker labels.
Memory you control
Keeps lasting facts about you on the device, with the option to mark sensitive memory so it never leaves the Mac.
Cloud model support with your key
Lets you connect GPT/Claude-style providers using your own API key when you need a frontier model.
Use Cases
“Private everyday chat”
Ask questions, draft writing, and summarize files or PDFs while keeping the work local to your Mac.
“Coding in your project folder”
Point Local at a codebase so it can read, edit, and run code in place without uploading the repository.
“Meeting notes on-device”
Transcribe meetings locally and produce written notes with speaker labels.
“Personal memory workflow”
Store a short list of lasting facts that you can review and edit, including sensitive items that stay on the machine.
“Hybrid local-plus-cloud usage”
Use local models for everyday work and switch to your own-key cloud models only for tasks that need more capability.
Frequently Asked Questions
Does Local work offline?
Yes. You need an internet connection to download the app and a model, but after that the product can run offline on your Mac.
Which Macs are supported?
The homepage says Local supports any Mac with Apple silicon.
Does Local collect my data?
No data collection is claimed on the homepage. It says everything lives in a database on your Mac, with no account and no telemetry.
Can I use GPT or Claude with Local?
Yes. The homepage says you can connect those models with your own API key, and those requests go to the provider.
What makes Local faster than other local apps?
The site attributes its speed to BaseRT, its inference engine, which is compiled for your chip rather than shipped as a generic build.
Quick Facts
- Category
- AI Chat
- Platform
- macOS; Windows and Linux are marked as coming soon
- Primary use
- Private on-device chat, coding, and meeting workflows
- Inference engine
- BaseRT
- Source domain
- basecompute.co
- Cloud option
- Optional, using your own API key
Local Traffic Analysis
Traffic data is for reference only.
- Domain Rating
- 18
Local Alternatives
ShogunAI
shogunaios.com
ShogunAI is a private, local-first AI memory assistant for macOS that captures work context on your Mac to help you recall information and draft actions across your tools.
Sigma
sigmabrowser.com
Private AI browser with chat, browser agent, and local AI for research and automation
fx
fx.sh
fx is a tiny, open, native coding agent and CLI for working with code from the terminal. It is designed for research, embeddability, and use as part of larger systems, with support for local or cloud inference.
Deta Surf
deta.surf
An intelligent local-first workspace for browsing, notes, and AI-assisted research
ETok
etok.ai
Developer tutorials for AI coding workflows, models, setup, and CLI tools
NinjaTools
ninjatools.ai
NinjaTools is an AI workspace for search, model comparison, coding, image and video generation, and PDF chat.