Portland, OR
Joined December 2006
"Mom, can we get GPT?" "No, we have GPT at home." Introducing preowned: a local server that puts the models built into macOS behind an OpenAI-compatible API. github.com/mattt/preowned Your Mac drove off the line with a language model, an image maker, a transcriber, a translator, and a trunk full of voices. Point any OpenAI client at preowned, and chat (with streaming and structured output), embeddings, transcription, translation, and speech run right there on your Mac. Ask for gpt-4o or whisper-1, and you get Apple's model for the job. Don't worry about what's under the hood. Any API key works — no credit check required! Sold as-is: no tool calling, no Responses API, and on macOS 27, Image Playground wants a person to click Done (or a hack that clicks it for you). Requires macOS 26 or later on Apple silicon, with Apple Intelligence turned on for chat and images. Take it for a test drive: brew install mattt/tap/preowned preowned serve Come on down! 🚗
4
7
68
7,156
iMCP 1.8.0 is out, and it packs in so many new features that we had to add a second row to fit them all! Mail, Notes, Voice Memos, and Music join the lineup. github.com/mattt/iMCP/releas…
4
18
311
29,326
If you use Home: iMCP Helper now pairs with iMCP once, using a one-time code. Before, any local process could connect to it. After you update, quit iMCP Helper, check out the 1.8.0 tag in your clone, rerun Scripts/install-helper.sh, and pair.
1
3
792
iMCP is free and open source. Existing installs update automatically, or grab it fresh: brew install --cask mattt/tap/iMCP Can't wait to hear what you ask it first 📬 github.com/mattt/iMCP
6
792
Are you in Portland, Oregon? Lately I've been getting coffee with folks in town who build things and want the city to work better. It's been a highlight of my year. Who else should I meet? Reply, DM, or tag them below ☕️
2
10
2,186
Mattt retweeted
Pain is information As a child, you touched something hot, and it burned you. That pain gave you a piece of information: be careful touching hot things. When you sign up to run a marathon, you are signing up for pain. But whether or not you keep running is up to you. In Haruki Murakami’s words “pain is inevitable but suffering is optional”. You can choose pain without choosing suffering. Pain is information, and information is painful. Rewiring your brain is not a frictionless process. Some knowledge can only be discovered the hard way. The sooner you can convert pain into knowledge, the sooner you can experience the next useful pain. Don’t put yourself through the same pain too many times. To access new information you must experience new pains. They say “knowledge is power”. If pain is information, then pain can be converted to power. To do so, you must learn to control your suffering, accept that scars are beautiful. If you felt pain, ask what information it gave you. If that information was useful, seek the next pain. You are learning.
29
131
16
1,226
123,496
AnyLanguageModel turns one, and it's 1.0 🎂 Our drop-in replacement for Apple's Foundation Models framework lets you choose the model and provider your app uses. Here's what changed this year, and what's next: huggingface.co/blog/anylangu…
2
5
39
3,709
Hosted providers now include OpenAI, Anthropic, Gemini, Ollama, any Open Responses endpoint, Private Cloud Compute on OS 27, and Hugging Face Inference Providers. AnyLanguageModel runs on Linux, too, so the same code can work on a server.
1
2
1
925
Along the way, we also built swift-huggingface and swift-xet, for accelerated model downloads from 🤗 Hub. Thanks to everyone who contributed this year, and to @pcuenq for his help with all these projects. Excited to share more projects soon, so stay tuned!
1
547
Mattt retweeted
Beam is a token-efficient, frontier-scale model for your coding agents, comes with its own harness 🔥 A23B/501B model, also comes with NVFP4 & FP8 and day-0 transformers support 🤗 check out our blog ⤵️
Beam is now available across platforms, with open weights under the Apache 2.0 license - in collaboration with an ecosystem of 40+ partners. We're releasing: - Weights, tokenizer, and reference implementation - BF16, FP8 and NVFP4 weights and a DFlash2 drafter - The open source harness we built and trained Beam on: Mirror CLI Weights and model card on Hugging Face: huggingface.co/reflection
12
9
112
5,364
And of course Muse Spark Open works great with llama.cpp 🦙🔥 Behold this amazing demo courtesy of @mervenoyann, running on a Mac (M3 Ultra 512). This is a frontier model that runs on your (beefy) desktop. Local AI is only getting better 🚀
4
4
1
22
4,828
iMCP 1.7.0 is here, with a new Home service for HomeKit, Voicemail, and editable Reminders and Calendar events. Good timing, with Apple announcing HomeView yesterday — now your Mac's assistant can help run the house, too 🏠 github.com/mattt/iMCP/releas…
7
12
4
202
17,758
Also in 1.7.0: Voicemail lists visual voicemails and fetches transcripts and audio, Reminders can repeat and manage lists, Calendar gains events_update, and Messages can read attachments. Thanks to @bradhallett for much of this!
1
1
817
iMCP is free and open source. Existing installs update automatically, or grab it fresh: brew install --cask mattt/tap/iMCP Can't wait to see what your assistant does with the house keys 🔑 github.com/mattt/iMCP
5
806