MultiAgentOS
New · Nine native Mac apps join the catalog — video, audio, photos, data and storage
Our flagship app, MultiAgentOS, is the budget-friendly alternative to frontier LLM subscriptions. Plug in a cheaper API from a provider like DeepSeek or Groq, or run a private local model, then put it to work with a full desktop tool harness: a coding agent, document creation, browser and desktop automation, and more. And brand new: our AI Engineering, Data Engineering, Software Engineering, and ML Engineering apps: full-featured software for learning each career, with 40 courses and 400 interactive lessons apiece, on your own Mac. And newest of all: nine native Mac apps — VideoNotes, Lectern, Broadcut, Shorts, Sift, SpaceLens, Recast, Alembic and Tidyset — covering video editing, live streaming, transcription, study notes, photo cleanup, file conversion, storage analysis and data cleaning. Every download is the complete, fully activated app.
The apps share a practical philosophy: visible automation, local control, useful defaults, and human approval before important actions.
See the runtime toolsNew releases
AI Engineering, Data Engineering, Software Engineering, and ML Engineering are complete, interactive career curriculums in native Mac apps: 40 courses and 400 hands-on lessons each, portfolio project labs, and a private AI tutor that works fully offline. Available now as donation downloads.
Available now
Full-featured software for learning AI engineering: 40 courses, 80 modules, and 400 interactive lessons from first Python to a Principal AI Architect capstone, with 140 editable code labs, 40 portfolio projects, and a private offline AI tutor.
Explore AI Engineering →
Available now
Full-featured software for learning data engineering: 40 courses, 80 modules, and 400 interactive lessons across SQL, Python, pipelines, Airflow, dbt, Spark, Kafka, and lakehouse architecture, with 40 portfolio projects and a private offline AI tutor.
Explore Data Engineering →
Available now
Full-featured software for learning software engineering: 40 courses, 80 modules, and 400 interactive lessons across Python, TypeScript, Swift, APIs, testing, CI/CD, and system design, with 140 code labs, 40 portfolio projects, and a private offline AI tutor.
Explore Software Engineering →
Available now
Full-featured software for learning machine learning engineering: 40 courses, 80 modules, and 400 interactive lessons from first Python through PyTorch, pipelines, serving, and MLOps, with 140 code labs, 40 portfolio projects, and a private offline AI tutor.
Explore ML Engineering →See it in action
The core tools are built around visible, interruptible workflows: browser sessions, desktop tasks, files, terminals, coding lessons, and job-search drafts.
Connect an API key or a local model, then watch the LLM gain web research, GitHub, memory and RAG, image generation, OCR, subagents and more.
Ask a research question; MAOS searches multiple sources, cross-checks them, and writes a designed, accent-styled PDF report on its own.
Ask in plain English and MAOS navigates job sites itself, extracting live listings, salary bands and market trends.
The budget-friendly alternative to frontier LLM subscriptions. Connect a cheaper provider API or a private local model, and MultiAgentOS gives it frontier-level reach through its own desktop tool harness, so you get top-tier capability without a monthly bill.
The best companion to MultiAgentOS. Train your own open-source LLM into a custom specialist with no code, then run it inside MultiAgentOS for even more tailored performance, all without expensive subscriptions. Don't start from a blank page: begin with the Training Recipes Database, hundreds of one-click "train a ___ specialist" recipes you can mix and match into one personalised model.
A desktop browser built for humans and AI agents. Browse normally, or let an LLM navigate, click, fill forms, execute JavaScript, take screenshots, and report back through a visible bridge panel and local JSON-RPC/WebSocket server.
A desktop app for job seekers and recruiters. A real browser and an AI assistant sit side by side: find roles or candidates, draft tailored emails and cover letters from your CV or role brief, and send from your own inbox, only after you approve.
A fully local desktop app for learning to code with an AI tutor, built on the same Avalonia shell as MultiAgentOS. It pairs the full chat-and-sidecar workspace with structured language tracks, thousands of interactive lessons, multi-file coding projects, and a built-in glossary.
Bring cloud APIs, local servers, OAuth providers, terminal commands, or fully local model files. The software keeps those options visible instead of hiding them behind a black box.
Connect OpenAI, Anthropic, DeepSeek, xAI, Google, Mistral, and compatible providers.
Use Ollama, LM Studio, llama.cpp, GPT4All, vLLM, or your own compatible local server.
Route prompts through command line tools and collect their output inside the app.
Sign in to supported providers without scattering credentials around your system.
Let the software run supervised shell tasks when the job calls for it.
Point at GGUF model files and run offline where that workflow makes sense.
MultiAgentAI software is designed for repeatable tasks: browsing, code, terminal work, file handling, screenshots, language practice, application drafts, and supervised handoffs.
Local-first where possible, transparent when tools run, practical about model choice, and careful about what leaves your machine.
Your prompts, files, settings, and run history stay on your machine unless you choose a cloud provider.
Use API providers, local servers, terminal tools, or local GGUF models depending on the task.
Support the build, choose a product and platform, and receive a private installer link when builds are available.
Approval walls, visible sidecars, and stop controls keep the human in the loop.
Flagship product
Bring a cheaper provider API or a private local model, then let MultiAgentOS put it to work with a full desktop tool harness: coding, documents, browsing, terminal, and automation, all under your control. Pair it with LLM Academy to train your own custom model.
MultiAgentOSYour AI, your harness
Get the software
Give whatever you like, pick the app and your computer type, and download the installer after checkout when a build is published.
Software catalog
MultiAgentOS with its Mac and Windows builds, LLM Academy, LLM Browser, Jobomate, Codemonkey AI, the AI, Data, Software and ML Engineering learning apps, and nine new native Mac apps — VideoNotes, Lectern, Broadcut, Shorts, Sift, SpaceLens, Recast, Alembic and Tidyset — are all part of the same practical software studio.
Available now
Turn recorded lectures into hand-drawn, source-cited sketchnote study pages: on-device transcription, Vision OCR, 14 note formats, spaced-repetition study mode and ten export formats.
Explore VideoNotes →
Available now
Record meetings and lectures with a live transcript, transcribe on-device with Whisper or Apple Speech, get deterministic notes with action items, and search every word forever.
Explore Lectern →
Available now
A frame-exact multitrack video editor and a scene-based RTMP live streaming desk in one native app, sharing one project and one Metal render engine.
Explore Broadcut →
Available now
Describe a creative brief and get an editable first cut with titles and captions, then finish it on a real multitrack timeline with an assistant that previews each edit first.
Explore Shorts →
Available now
Find duplicate photos, blurry shots and old screenshots entirely on-device, then clear the clutter you approve in one calm monthly sweep — recoverable for about 30 days.
Explore Sift →
Available now
Scan your disk at up to ~230k files per second, explore it as a sunburst or treemap, and reclaim space through a reviewable cleanup basket with undo.
Explore SpaceLens →
Available now
Convert between 58 formats over 589 direct and multi-step routes — images, video, audio, documents and data — with batch queues and live progress, on-device.
Explore Recast →
Available now
Distill messy source data into training-grade datasets: deterministic pipelines for cleaning, near-duplicate removal, PII scrubbing, chunking and eight export schemas.
Explore Alembic →
Available now
Clean CSV, TSV, Excel and JSON deterministically: reviewable suggestions, column profiling, fuzzy clustering, formulas — every action a reversible, reusable recipe.
Explore Tidyset →
Available now
MAOS Mac OS is the Apple Silicon and Intel build on the shared .NET / Avalonia shell. Secrets live in the macOS Keychain, desktop control runs through CGEvent / CoreGraphics, and a zero-setup bundled llama.cpp runtime means you can work fully offline.
Explore MAOS for Mac →
Available now
MAOS Windows is the Windows 10 and 11 build on the shared .NET / Avalonia shell. Secrets live in Windows Credential Manager, the agent drives your desktop and PowerShell / Cmd, and five on-demand tool packs add executable diagnostics only when a task needs them.
Explore MAOS for Windows →
Available now
Full-featured software for learning AI engineering. A native Mac app with 40 courses, 80 modules, and 400 interactive lessons from first Python to a Principal AI Architect capstone, plus 140 editable code labs, 40 portfolio projects, and a private offline AI tutor.
Explore AI Engineering →
Available now
Full-featured software for learning data engineering. A native Mac app with 40 courses, 80 modules, and 400 interactive lessons across SQL, Python, pipelines, Airflow, dbt, Spark, Kafka, and lakehouse architecture, plus 40 portfolio projects and a private offline AI tutor.
Explore Data Engineering →
Available now
Full-featured software for learning software engineering: 40 courses, 80 modules, and 400 interactive lessons across Python, TypeScript, Swift, APIs, testing, CI/CD, and system design, with 140 code labs, 40 portfolio projects, and a private offline AI tutor.
Explore Software Engineering →
Available now
Full-featured software for learning machine learning engineering: 40 courses, 80 modules, and 400 interactive lessons from first Python through PyTorch, pipelines, serving, and MLOps, with 140 code labs, 40 portfolio projects, and a private offline AI tutor.
Explore ML Engineering →
Available now
Train your own custom model to pair with MultiAgentOS. A no-code Expert Builder turns an open-source model into a specialist in three steps, with a full fine-tuning studio, a model hub, recipe templates, and one-click export to GGUF, LoRA, or a local API behind it.
Explore LLM Academy →
Available now
A desktop browser built for humans and AI agents. Browse normally, or let an LLM navigate, click, fill forms, execute JavaScript, take screenshots, and report back through a visible bridge panel and local JSON-RPC/WebSocket server.
Explore LLM Browser →
Available now
A desktop app for job seekers and recruiters: a real browser plus an AI assistant that finds roles or candidates, drafts tailored emails and cover letters from your CV or role brief, and sends from your own inbox, only after you approve.
Explore Jobomate →
Available now
A fully local desktop app for learning to code with an AI tutor, built on the same Avalonia shell as MultiAgentOS. It pairs the full chat-and-sidecar workspace with 20 language tracks, 2,478 lessons across 12 interactive step kinds, multi-file coding projects, and an 88-entry glossary.
Explore Codemonkey AI →More from Luke McLaughlin
A family of independent projects I build and run, spanning local-first AI software, language learning, and practical books for self-teaching.
A desktop web browser with a built-in AI assistant that can read, summarize, and act on any page you visit. Browse as normal, then ask the assistant to navigate, click, fill forms, or automate repetitive tasks using a cloud key or a private local model. It is built for faster research and automation without handing your browsing data to the cloud.
An AI desktop assistant built for both job seekers and recruiters. It pairs a real browser with an AI that finds roles or candidates and drafts tailored cover letters and outreach from your CV or job brief, sending them from your own inbox only after you approve. It works with cloud or fully private local models, so you stay in control of every message.
A bookstore of practical, self-teaching guides covering math, logic, and programming. Titles range from the foundational math and logic that coders actually need to hands-on Python, Java, and JavaScript, plus AI engineering and language learning. Each book is an instant PDF download designed to take you from the fundamentals to real, applied skill.
Constructing Language teaches Mandarin Chinese, Japanese, and German with the Construction Method, building real sentences from grammar patterns instead of rote flashcards. Alongside its audio courses and downloadable books, it offers a whole suite of free, interactive language-learning apps you can use right in the browser. It is also home to Switchboard, an interactive app for learning Chinese, Japanese, and German.
The personal site of Luke McLaughlin, covering his work across technical SEO, digital marketing, and AI software. It brings together his projects, writing, career background, and reading list in one place. Visit to see the person behind these tools, read his insights, or get in touch.