Formerly macOS26 — now AgentiLoop
AgentiLoop Agent! App Icon

AgentiLoop Agent!

Agentic AI for your Mac Desktop

One app. Any AI. Total command over your Mac. Build apps, write code, manage files, drive any application, and automate workflows — all through natural language. 100% native Swift. Zero Electron. Built for macOS 26.4.1 Tahoe.

18LLM Providers
100%Native Swift
0Electron / NPM
$0Subscription

Everything an agent should do. Natively.

An open-source replacement for Claude Code, Cursor, and OpenClaw — built from original IP, not 65 NPM packages.

🖥️

Desktop Control

Drive any Mac app through natural language. Click, type, scroll, and navigate — powered by the Accessibility API. No AppleScript required.

✏️

Agentic Coding

Surgical string-replace edits, one-click Time-Machine-style rollback, portable JSONL repo-maps, and self-verifying tasks with evidence-backed completion.

🛠️

Xcode Integration

Build, run, analyze, and ship. Fix errors, manage project files, bump versions, and commit — all from a single request.

🔄

Automation

Custom Agents in Swift, shell as user or root, AppleScript, JXA, ScriptingBridge, Safari automation, and event hooks. No limits.

🧠

Apple Intelligence

On-device tool-calling agent — not just a text generator. Intent parsing, context compaction, triage, and task summaries. Private, free, zero API tokens.

🔌

MCP Support

Extend Agent! with Model Context Protocol servers for databases, APIs, and tools. Sub-agents fan out work in parallel — up to 6 researchers.

Proof, not promises

Real sessions, real output — captured straight from Agent! at work.

Builds apps while you make coffee

Paired with any compatible LLM, Agent! reads your codebase, fixes the bug, builds the Xcode project, and commits the diff. Here it codes a Tic-Tac-Toe game in Swift, end to end.

Agent! coding a Tic-Tac-Toe game in Swift, demonstrating real-time code generation and app building on macOS

One-command Xcode version bumps

Say "bump version" and Agent! reads the current version, updates project settings, builds to verify, and commits the change. No manual plist editing, no missed build numbers.

Agent! performing an Xcode version bump, building to verify, and auto-committing the change

Asks before it guesses

When a request is ambiguous, Agent! pauses and asks. No silently picking the wrong path — you stay in control with a quick prompt and a Send or Skip.

Agent! showing an Agent Question dialog asking the user to clarify a DMG name, with Skip and Send buttons

Reviewed and approved by Claude Code

Agent! independently found and fixed a routing bug in its own accessibility code that Claude Code missed across several reviews. When Claude Code reviewed the fix, it confirmed the patch was correct.

Claude Code approving Agent!'s bug fix in GitHub Desktop, showing the code diff

Ships playable games in one session

Ticky Tacky is a neon tic-tac-toe with vs Bot and 2 Player modes, three difficulty levels, persistent scores, and zero dependencies — pure HTML, CSS, and JavaScript. Built by Agent! in a single session.

Play Ticky Tacky
Ticky Tacky neon tic-tac-toe game by Agent! with glowing neon pink X and cyan O marks on a dark purple board

Apple Intelligence — as a real agent

Agent! is the only Mac AI agent that uses on-device Apple Intelligence as a tool-calling agent rather than just a text generator. Everything below runs on your Mac, never leaves the device, and consumes zero API tokens.

1Accessibility intent agent

Say "take a photo using Photo Booth" and Apple Intelligence parses the intent locally and dispatches the macOS Accessibility tool itself — sometimes multiple times in sequence. The cloud LLM never sees the request.

2Token compression

Long tasks past ~30,000 tokens get their older turns summarized on-device — keeping file paths, function names, errors, and key results — slashing input tokens and cost for the rest of the task.

3Local triage

Small talk and direct commands like "list agents" or "run agent FooBar" are handled locally with no round-trip to the cloud LLM — results land in your activity log within a second, marked 🍎.

4Summaries & plain-English errors

After every completed task, Apple Intelligence writes a one-sentence summary. When a tool fails, it translates the error into plain English so you never read a raw stack trace.

Bring your own AI — 18 providers

Cloud APIs, local models, or free on-device Apple Intelligence. Your keys, your machine, your data. No subscription. No telemetry. No vendor lock-in.

🟠Claude
🟢OpenAI GPT
Google Gemini
Grok (xAI)
🌀Mistral
🔵DeepSeek
🐉Qwen
🎯Z.ai
🟪BigModel
🤗Hugging Face
🔀OpenRouter
🦙Ollama Cloud
🏠Ollama Local
👁️vLLM
🔬LM Studio
💻Codestral
🎵Mistral Vibe
🍎Apple Intelligence

Up and running in minutes

Download, drag, pick your AI. Agent! sets up everything else automatically.

1

Prerequisites

  • macOS 26.4 (Tahoe) or later, Apple Silicon recommended
  • Xcode Command Line Tools: xcode-select --install
  • An LLM API key — or a local model via Ollama, vLLM, or LM Studio
2

Install & Run

  • Download the DMG
  • Drag Agent! to /Applications and open it
  • Click Register to install the background services
3

Approve & Configure

  • Allow Agent and AgentHelper in System Settings → Login Items
  • Open Settings (⚙️), pick a provider, enter your API key
  • Click Connect to test the XPC services
4

Go

  • Type a task in natural language
  • Press Run (or ⌘Enter)
  • Agent! takes it from here — voice, iMessage, and hands-free control included

Releases

Recommended pairings — Commercial: Claude Fable 5 · Open Source: GLM 5.3 or Qwen 3.8

Version Release DateDate SizeMB DownloadsClicks
Loading releases…

Contact

Have questions or feedback? We'd love to hear from you.

Open a GitHub Issue