# Swift Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/swift
> Markdown URL: https://aitinkerers.org/technologies/swift.md
> Technology record last updated: 2026-09-18T15:13:54Z
> Generated: 2026-09-20T13:49:11Z

Swift is an open-source, compiled programming language: it's fast, safe, and expressive for building apps across all Apple platforms and beyond.

Swift is a powerful, multi-paradigm language, originally launched by Apple in 2014 to replace C-based languages for their ecosystem. It was engineered for performance, leveraging the LLVM compiler to produce lightning-fast, optimized machine code. The design prioritizes safety: features like Automatic Reference Counting (ARC) and explicit handling of optionals eliminate entire classes of common bugs (e.g., null pointer dereferencing). Now open-source under the Apache 2.0 license, Swift (current stable version 6.2.1) is the primary language for iOS, macOS, and watchOS development, with growing adoption for server-side and Linux applications.

- Official technology site: https://www.swift.org
- Public AI Tinkerers demos and talks: 17
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Teaching an LLM to be an interior designer](https://nyc.aitinkerers.org/talks/rsvp_G0dtIg_V-Dw)

A pipeline that turns a LiDAR room scan into art-placement decisions — which wall, what size, what art — by converting usdz geometry into per-wall design constraints that drive image generation, with a vision-LLM design critic whose judgments are verified, calibrated, and used to teach the deterministic scoring engine. Live, I'll walk the raw scan data (the LiDAR mesh and its JSON), the geometry visualizers that turn planes into design constraints, and the tooling we use to calibrate the critic and verify its judgments against the engine.

- Event context: August Demo Day ft Runpod, Veris, Openrouter, — 2026-08-19 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_G0dtIg_V-Dw

### [Building Brushi: A Local VLM Agent That Understands Kids’ Drawings](https://toronto.aitinkerers.org/talks/rsvp_duZsN9qwZvs)

Brushi is a kids coloring and drawing app with a local multimodal AI companion that can observe what a child is creating and respond through a small, bounded interaction loop. The project explores a question I have been thinking about in my recent work on edge AI: small VLMs and LLMs should not be treated as weaker versions of large cloud models. Like children are not simply “small adults,” edge models behave differently because the system around them has to provide structure, grounding, and feedback. In the live demo, I’ll show the working Brushi app, the local VLM/agentic architecture, and the event loop that connects the child’s drawing activity to the AI mascot’s reactions. The demo will focus on the technical workflow: how drawing events are captured, how visual context can be passed to a local VLM, how the LLM layer interprets the learning or creative context, and how the app decides whether to encourage, guide, correct, or stay silent. I’ll show the architecture, app workflow, logs/traces from the interaction loop, and examples of where the system succeeds or fails when trying to understand a child’s drawing.

- Event context: AI Tinkerers Toronto - June 2026 - with Relay Financial x PostHog — 2026-06-30 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_duZsN9qwZvs

### [Hearing the Room Across Language: Building Catch’s Realtime iPhone Interpreter](https://hong-kong.aitinkerers.org/talks/rsvp_vLe9DwZ90cU)

I've been building Catch, a native iPhone app that helps people follow talks, lectures, meetings, panels, classes, and tours in a language they do not fully understand. Catch’s current Listen Mode captures room audio, turns it into live interpreted output, plays interpreted audio through headphones when available, shows transcript text on screen as backup and saves the transcript for review afterward. I initially built Catch for myself so I could better follow conferences and presentations in Chinese. As I kept working on it, I realised that live interpretation can help people join events, talks, meetings, and community spaces they might otherwise avoid because of language barriers. For someone living in another country, or regularly moving between languages, the goal is to make participation feel more possible instead of leaving them reading, guessing, or sitting outside the conversation. Catch differs from products like Google and Apple Translate because it is specifically designed for long-form settings where you need continuous and simultaneous interpretation for extended periods of time.

- Event context: AI Tinkerers Hong Kong & GBA at Dialogue in the Dark (June) — 2026-06-24 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_vLe9DwZ90cU

### [Reducing eWaste with AI: how old devices can be brought back to life](https://raleigh.aitinkerers.org/talks/rsvp_8BhOnI30T4E)

I had an old audio device that hasn’t had working drivers for years on macOS that ai helped me bring back to life. The process required reverse engineering the last working driver version, and arguing with the ai about it the entire time. I was able to observe the ai preferred working in assembly and we can look at some reasons why this may or may not be a good thing.

- Event context: AI Tinkerers Raleigh Meetup — May 6, 2026 — 2026-05-06 — Raleigh
- Public talk page: https://raleigh.aitinkerers.org/talks/rsvp_8BhOnI30T4E

### [AI Launcher for old games on Mac OS (very millennial / boomer)](https://seattle.aitinkerers.org/talks/rsvp_jmXoHb_fAoc)

Cellar is AI pipeline based on Wine with the only goal – to launch an old games on your Mac. Launching old games on Mac is especially notorious business based on reading manuals, tweaking configs and it is not fun (at least for me). To help nostalgic newbies as I am, I made this tool – Cellar. It is a bundle of Wine and AI pipeline. You point it to the installation file and does everything for you: unpacks it, installs, creates a bottle and finds correct configuration to launch. Once the game is launched, successful config stored and you don't need AI anymore. Additionally, all Cellar agents have shared Wiki that collects all their experiences together – so that if one Cellar agent launched game correctly, another one will read about it. It currently supports Claude, Deepseek and Kimi.

- Event context: AI Dev Tools Track - Seattle — 2026-05-06 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_jmXoHb_fAoc

### [Viendo como pasas tu tiempo con IA](https://bogota.aitinkerers.org/talks/rsvp_VDCkqnqOLKQ)

Todos queremos dedicar nuestro tiempo a cosas que valen la pena, pero la pantalla rara vez refleja esa intención. Durante el día producimos un rastro de acciones (apps, ventanas, documentos, cambios de contexto) que cuenta una historia distinta a la que creemos estar viviendo. En esta charla presento una herramienta que estoy construyendo para cerrar esa brecha: transforma mi actividad diaria en un resumen interpretable de “en qué se fue el tiempo”, lo contrasta con lo que yo considero importante, y me ayuda a ajustar el día siguiente. La implementé con modelos locales para mantener los datos en mi máquina, reducir fricción y poder operar offline. También la construí apoyándome en varias herramientas de IA para acelerar diseño, prototipado y evaluación. Compartiré el enfoque técnico y aprendizajes prácticos sobre cómo instrumentar tu propio sistema de reflexión diaria sin sacrificar privacidad.

- Event context: AI Tinkerers Bogotá: El Primer Meetup de 2026 — 2026-02-26 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_VDCkqnqOLKQ

### [Skwad: multi agent IDE](https://chicago.aitinkerers.org/talks/rsvp_wCMG7hFHLOc)

I built Skwad primarily to support my coding workflow. Multi-tasking with several agents was becoming more and more tedious, juggling between multiple terminal windows and having to manually coordinate work among those agents. Skwad solves both problems by hosting multiple coding agents in a unified app plus allowing those agents to directly communicate through an embedded MCP server. Skwad continues to support my ever changing workflow with new features such as markdown review, mermaid preview and recently a command center providing an overview of all your agents on one single pane of glass.

- Event context: AI Tinkerers Chicago: February Meetup ft. DubClub — 2026-02-17 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_wCMG7hFHLOc

### [Using AI to see how chopped your outfit is + Hot AI Influencers workflow](https://seattle.aitinkerers.org/talks/rsvp_bJrZjyH4zzQ)

Presenting how I used OpenAI vision api and Structured Outputs to scan your outfits and give it a rating. Will show JSON Schema I engineered for reliable outfit analysis. + Showing my hot AI influencer content farm workflow. Will show process using Kling 2.6 motion control.

- Event context: AI Tinkerers Seattle: January Meetup — 2026-01-31 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_bJrZjyH4zzQ

### [Stop Building for 'Users.' Start Building for People Who Just Want to Work](https://waterloo.aitinkerers.org/talks/rsvp_00AtAov5SyQ)

Most B2B software is built backwards. Someone decides what features matter, builds a dashboard, throws in a tutorial, and ships it. The user opens it and sees... everything. Tabs, menus, settings, modules they'll never touch. It's exhausting before they've done anything. I spent six months inside a real estate brokerage watching agents work. What I learned: they don't want software. They want the work done. Dispatch is what happened when I stopped thinking about features and started thinking about respect—respect for their time, their attention, their day. No onboarding. No learning curve. You open it, and you know how it works in 30 seconds. That's the standard.

- Event context: AI Tinkerers Waterloo – January Meetup — 2026-01-28 — Waterloo
- Public talk page: https://waterloo.aitinkerers.org/talks/rsvp_00AtAov5SyQ

### [How AI helps in language learning on the go - personalized podcasts with spaced repetition](https://lausanne.aitinkerers.org/talks/rsvp_LqcT96BZg4M)

I'll present Podcastify AI, a watchOS app that helps users learn languages through personalized podcast-style lessons. The app has the following abilities: - AI-Generated Content: Custom audio lessons personalized and tailored to user's proficiency level, necessary pace, and personal interests - Spaced Repetition: Smart scheduling that reinforces vocabulary at optimal intervals - Learn On-the-Go: Podcast format on Apple Watch allows passive learning through gestures during commutes, workouts, etc. - Personalization: Content adapts in real-time based on user progress and learning patterns PodcastifyAI demonstrates how AI makes language learning more accessible and efficient, specifically for busy learners.

- Event context: AI Tinkerers Lausanne December 2025 Meetup — 2025-12-03 — Lausanne
- Public talk page: https://lausanne.aitinkerers.org/talks/rsvp_LqcT96BZg4M

### [Readback: ATC Communication Training with an AI for Pilots](https://berlin.aitinkerers.org/talks/rsvp_qgOUsztbvzI)

Radio calls with ATC is stressful for a lot of student and private pilots especially if there are other experienced pros on the same frequency. The best way to overcome this nervousness is practice, practice, practice. Readback provides pilots with a calm, professional and infinitely patient ATC controller to practice with.

- Event context: AI Tinkerers Berlin Meetup - November 12th, 2025 — 2025-11-12 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_qgOUsztbvzI

### [Edge AI: exploring the capabilities of Apple’s VLM](https://raleigh.aitinkerers.org/talks/rsvp_55jgZ4RgKLY)

Apple has released a VLM that’s a quantized fine tuned version of Qwen they’ve optimized for iOS and macOS Apple Silicon devices. I want to show some experiments on when it works and when it fails. For example how good is it at Q&A? How responsive to prompting is it? What languages can it work with both visually and textually? Are resource usages different on different hardware? What tunability does Apple offer by default?

- Event context: AI Tinkerers - Raleigh Inaugural Meetup (September 2025) — 2025-09-30 — Raleigh
- Public talk page: https://raleigh.aitinkerers.org/talks/rsvp_55jgZ4RgKLY

### [SwiftAIAgent](https://sydney.aitinkerers.org/talks/rsvp_ZYfgQw-P9BM)

A swift AI agent framework. One demo website that is using this framework https://deepsearch.timwang.au

- Event context: AI Tinkerers – Sydney Inaugural Meetup · 20 August 2025 — 2025-08-20 — Sydney
- Public talk page: https://sydney.aitinkerers.org/talks/rsvp_ZYfgQw-P9BM

### [The fastest & most secure way to integrate AI into your  apps](https://boston.aitinkerers.org/talks/rsvp__8thBPULCPM)

An introduction to Apple's new on-device LLM — the Foundation Models Framework

- Event context: AI Tinkerers Boston June Meetup @ MIT! — 2025-06-30 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp__8thBPULCPM

### [Vibe coded Point of Sale iPad App](https://singapore.aitinkerers.org/talks/rsvp_HGIyM6AvdFs)

Used vibe coding to create an iPad App, no Swift experience no iPad OS experience. Its an MVP version that actually works for simple uses like selling items in a booth or a pop out.

- Event context: AI Tinkerers Singapore: 6th Meetup - April 25th, 2025 — 2025-04-25 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_HGIyM6AvdFs

### [Pico Server](https://palo-alto.aitinkerers.org/talks/rsvp_5vzefpl_RqQ)

A few months ago I demonstrated MLX Server and a few open source Swift tools I was working on at the Palo Alto AI Tinkerers meetup. I've changed direction a bit, but stayed true to open source and making local AI more accessible. I wanted to show an updated version of the local LLM server I presented earlier.

- Event context: AI Tinkerers - Palo Alto - November 2024 Meetup — 2024-11-21 — Palo Alto
- Public talk page: https://palo-alto.aitinkerers.org/talks/rsvp_5vzefpl_RqQ

### [Pico MLX Server - run the fastest LLM models locally on your Mac](https://palo-alto.aitinkerers.org/talks/rsvp_I-Rf4G1GAVc)

Pico MLX Server is an open source tool to run MLX-optimized LLM models on Mac. MLX is Apple's new AI framework, specifically optimized for Apple Silicon. Pico MLX Server provides an OpenAI-compatible API for seamless integration with existing AI chat apps. Just set any app's endpoint to localhost and it works. Accessible from the menu bar, Pico MLX Server offers a straightforward interface for managing server operations. No terminal commands necessary. Pico MLX Server is a part of a collection of open-source, Swift-based AI tools designed for iOS and macOS developers.

- Event context: AI Tinkerers Palo Alto - Inaugural Meetup — 2024-05-01 — Palo Alto
- Public talk page: https://palo-alto.aitinkerers.org/talks/rsvp_I-Rf4G1GAVc

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 214 public demos
- [Xcode](https://aitinkerers.org/technologies/xcode) ([Markdown](https://aitinkerers.org/technologies/xcode.md)) — 4 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [iOS](https://aitinkerers.org/technologies/ios) ([Markdown](https://aitinkerers.org/technologies/ios.md)) — 7 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [Qwen](https://aitinkerers.org/technologies/qwen) ([Markdown](https://aitinkerers.org/technologies/qwen.md)) — 18 public demos
- [SwiftUI](https://aitinkerers.org/technologies/swiftui) ([Markdown](https://aitinkerers.org/technologies/swiftui.md)) — 9 public demos
- [Agent](https://aitinkerers.org/technologies/agent) ([Markdown](https://aitinkerers.org/technologies/agent.md)) — 12 public demos
- [Agentic loop architecture](https://aitinkerers.org/technologies/agentic-loop-architecture) ([Markdown](https://aitinkerers.org/technologies/agentic-loop-architecture.md)) — 1 public demo
- [Anthropic API](https://aitinkerers.org/technologies/anthropic-api) ([Markdown](https://aitinkerers.org/technologies/anthropic-api.md)) — 66 public demos
- [Apple Silicon](https://aitinkerers.org/technologies/apple-silicon) ([Markdown](https://aitinkerers.org/technologies/apple-silicon.md)) — 2 public demos
- [ARKit](https://aitinkerers.org/technologies/arkit) ([Markdown](https://aitinkerers.org/technologies/arkit.md)) — 3 public demos
- [assembling languages](https://aitinkerers.org/technologies/assembling-languages) ([Markdown](https://aitinkerers.org/technologies/assembling-languages.md)) — 1 public demo
- [AVAudioEngine](https://aitinkerers.org/technologies/avaudioengine) ([Markdown](https://aitinkerers.org/technologies/avaudioengine.md)) — 1 public demo
- [AVAudioSession](https://aitinkerers.org/technologies/avaudiosession) ([Markdown](https://aitinkerers.org/technologies/avaudiosession.md)) — 1 public demo
- [AVFoundation](https://aitinkerers.org/technologies/avfoundation) ([Markdown](https://aitinkerers.org/technologies/avfoundation.md)) — 1 public demo