Spectrion
AI agent that actually controls your iPhone — 57+ tools
What it does
Autonomous AI agent for iPhone with 57+ built-in tools. Not a chatbot — a real agent that controls your device. Say "remind me at 10am and add to calendar" — it calls both tools in parallel and confirms. • Runtime tool creation (agent writes its own JS tools) • Visual workflow builder • Self-improvement engine (evolves every 24h) • Device Mesh: iPhone + Mac, E2E encrypted • Claude, GPT-4o, Ollama, Apple On-Device • Built solo. Pure SwiftUI. No dependencies.
Does the same job
all alternatives →
- IBI built an AI Agent that uses the iPhone2025 · github.com · ▲53
It’s powered by OpenAI’s GPT 4.1 model. Uses Xcode UI tests + accessibility tree to look into apps, and performs swipes, taps, etc to get things done.
- AOAgentSwift – Open-source iOS builder agentApr 2026 · github.com · ▲63
I'm working on a coding agent for building iOS apps. It's built on openspec and xcodebuildmcp. It's free and open source.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
