A native macOS app that turns the files you already have into the things you actually need — running on your own machine, with no account, no upload, no cloud.
For thirty years your operating system has answered the same question: which app opens this file? MachineFabric answers a better one: what do you want this file to become?
Right-click anything in Finder. Pick Transmute. See what's possible. A PDF turns into searchable text, page thumbnails, an audiobook, or an answer to a question. A folder of receipts turns into a spreadsheet. A meeting recording turns into minutes. No new app to launch. No new window to learn.
One menu, every possibility
A Finder menu that starts from outcomes instead of apps.
Drop a video. Pick “transcribe.” MachineFabric finds the path on its own — extract the audio, decode it, run it through speech-to-text — and shows you the route before it runs. You watch your file travel from what it is to what you asked for.
You don't pick the steps. You pick the destination. The system composes the journey, every time, from the parts you have installed. Add a new cartridge tomorrow and yesterday's files unlock new destinations on their own.
A graph appears, then runs
The full route is visible before the run begins.
MachineFabric is a native macOS application. There is no account to create, no key to paste, nothing to subscribe to. Your files stay on your disk. Your work stays on your desk. Disconnect the network and the only thing that changes is which models you can download — the ones already there keep working.
Sandboxed by default. Signed and notarized. Apple Silicon native. The intelligence happens here, not somewhere else's server.
Airplane mode, full speed
An offline run completing entirely on the local machine.
PDFs split into pages or rendered as images. MP3, WAV, FLAC, OGG, AAC, M4A, AIFF, OPUS — every common audio format, converted between any pair. JPEG, PNG, WebP, BMP, TIFF, GIF — same. MP4, MOV, WebM, MKV — frames out, audio out. CSV, JSON, YAML — every direction. Plain text rendered, page-imaged, concatenated.
Real coverage, real today. Not a roadmap, not a teaser — open the cartridges browser and these are already there to install.
One input per category
Different kinds of files, each flowing through their own transformation path.
Paste a HuggingFace model id. Watch it download. The moment it lands, every cartridge that knows how to use it picks it up — embeddings, transcription, vision, generation. Apple's MLX, llama.cpp, Candle: pick the runtime, pick the size, pick the quant.
The 0.5B model that fits in a few hundred megabytes? It works. The 70B beast that needs your whole GPU? It works. Same surface, same right-click, same Transmute menu — only the speed and the answer change.
Paste, download, dispatch
A newly added model appears immediately as something the system can use.
A long pipeline shouldn't be a beach ball. Every step shows you what it is doing right now — the page being rendered, the frame being decoded, the token being generated. Memory, throughput, time elapsed — all in plain view.
If something stalls, you see why. If something fails, you see where. There is no opaque green checkmark waiting for you to come back later — there's a system that explains itself while it works.
Per-step progress, end to end
Live progress shows each step as the work moves through the pipeline.
A cartridge is a small program. Fifty lines of Python — or Rust, Swift, or Go — and your tool joins the system. The Transmute menu picks it up. The planner routes through it. Other cartridges call it. You didn't write a plugin; you wrote a citizen.
Open protocol. Open SDK. Open registry. The path from idea to installable cartridge is the kind of weekend project that ends with something real on every Mac that runs MachineFabric.
Thirty seconds to a new capability
A custom cartridge going from source file to installed capability.
The fastest way to understand MachineFabric is to right-click something on your own Mac. Download it, open Finder, pick a file you've been meaning to do something with — and Transmute it.
