AgentiLoop Agent! icon AgentiLoop
EN
EnglishEspañolFrançaisDeutsch中文 (简体)Русский한국어日本語
Welcome to AgentiLoop.ai for Mac
AgentiLoop Agent! for Mac, plus a CLI written in Rust and Go for Mac, Windows, and Linux

AgentiLoop Agent!

Agentic AI for your entire Mac and More!

One app. Any AI. Tell Agent! what you need in plain English and it answers your email, drives Safari, builds Xcode apps, fixes code, and runs your Mac apps for you. Pick from 23 LLM providers or stay local with LM Studio, vLLM, or Ollama. macOS 14.6 or later. AgentiLoop CLI, runs cross-platform, brings our agentloop to your terminal on Mac, Windows, and Linux.

Download Latest Star on GitHub Fork on GitHub Create an Issue
23LLM Providers –GitHub Stars –Forks –Latest Downloads –Total Downloads
AgentiLoop%2FAgent | Trendshift AgentiLoop%2FAgent | Trendshift

Our Sponsors

Thank you to the companies that keep Agent!, AgentiLoop CLI and AgentiLoopGo independent.

SPONSOREDSilverBecome a Sponsor One API for GPT, Claude and other leading AI models Sign up through this link and get $3 in API credits as a new user. Sign up and get $3 in API credits →Promo code SDRAGENTLOOP Sign up and get $3 in API credits for new users sidrune.ai
Built by AgentiLoop Agent!

MarioKart64 ported to JavaScript

Created with AgentiLoop.ai

Auto-Pilot Goals Editing via Prompts
Play It → Read the Story GitHub
MarioKart64JS animated 3D title screen, ported to JavaScript by AgentiLoop Agent!
New Release · v0.0.5 Become a Sponsor

AgentiLoop CLI

The agentic coding loop for your terminal, in two versions: Rust and Go. The exact same capabilities, commands and config. Pick your favorite.

macOS Windows Linux
  • New: project search with glob & grep, web_fetch, a todo checklist and AGENTS.md / CLAUDE.md instructions
  • New: /undo, /diff, /init, /export, /usage, custom slash commands, --json and --allow-tool / --deny-tool
  • Claude, OpenAI, Codex, Ollama, LM Studio, oMLX & any OpenAI-compatible model
  • Full-screen TUI with drag-to-copy, streaming, sessions & smart context budgeting for small local models
  • Claude Code-style -/+ diffs, live files-changed pane & MCP servers (same config as Agent!)

Version 0.0.5 is out: a bigger toolbox — search, web fetch, undo, custom commands & scripting. Download it today.

Rust 0.0.5 on GitHub → Go 0.0.5 on GitHub →
AgentiLoop CLI setup wizard inside the full-screen TUI: provider picked, API key hidden, connection checked, model list, key saved to Keychain, then the first prompt

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

Tell Agent! what you want done in any Mac app and it does it. It finds buttons, fields, and menus by name using the Accessibility API, then clicks, types, and scrolls for you. No coordinates, no AppleScript.

✏️

Agentic Coding

Surgical string-replace edits, not whole-file rewrites. One-click rollback on every change. A portable JSONL repo-map any model can navigate. Every task must prove it finished before reporting done.

🛠️

Xcode Integration

Ask for a feature and get a green build. Agent! edits, builds, reads the compiler errors, fixes them, adds files to the project, bumps the version, and commits. One request, start to finish.

🔄

Automation

Write your own agents in Swift with full system access. Run shell commands as user or root, script apps with AppleScript, JXA, or ScriptingBridge, drive Safari, and trigger on events. If your Mac can do it, Agent! can automate it.

🧠

Apple Intelligence

Your helper on the Mac, not the brain. The on-device model suggests next steps, triages simple requests, compresses context, and writes task summaries entirely on your Mac. Private, free, and no API tokens spent.

🔌

MCP Support

Plug in Model Context Protocol servers to reach databases, APIs, and custom tools. Spin up as many as 6 sub-agents to research in parallel while the main agent keeps your context clean.

Proof, not promises

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

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

Reviews

What independent reviewers are saying about Agent!

AIProductHub (AI产品库) · Product Launch (Chinese) · October 4, 2026

AgentiLoop Agent!: the open-source native Swift desktop app that hands your entire Mac to an LLM

"Compared with mainstream vibe coding tools, Agent! takes the 'on-device native + engineering discipline' route… Tasks must falsify themselves: every task carries goal_state acceptance criteria — the agent cannot self-report completion, it can only report with evidence. The read-before-edit gate forces the agent to read a file before it may overwrite it, and task-level rewind can roll any task back to a chosen step while the evidence and context stay on disk." (translated from Chinese)
Read the full listing
Hacker News · Show HN · October 3, 2026

Show HN: AgentiLoop Agent Mac GUI Agent Loop for macOS 14.6 or Later

"Agent! originally appeared on Hacker News last April. A lot has changed since then. Recently a new feature has been developed called Auto-Pilot. It is given a goal and will not stop until the goal is reached. Think of it as tasks on steroids." … "Currently we are developing a Mario Kart like clone called 'GoKart' written in Godot 4. So far over 20 hours have been recorded developing and improving the game."
Join the discussion on Hacker News
Nathan Romano (@nathanromano) · X · September 29, 2026

Interesting what AgentiLoop is doing with Agent!

"A native Mac app that lets AI operate any app, with serious guardrails. It can't say 'done' without evidence, won't edit a file without reading it first, keeps backups so you can undo, and blocks dangerous commands. This is how agents that touch your computer should be built."
Read the post on X
ForoKD · Andy Green · Productivity (French) · September 28, 2026

Mastering AI agents for macOS control: the ultimate desktop automation guide

"Then there's Agent! from AgentiLoop, a formidable tool built natively in Swift. Unlike many Electron-based apps, it is lightweight and integrates with dozens of LLM providers, including local ones via Ollama. Its main strength is its use of the macOS Accessibility API, so it doesn't have to constantly take screenshots to find buttons. It also includes AgentScript, letting it compile Swift dynamic libraries on the fly to run complex system actions." (translated from French)
Read the full guide
BestHub · Geek Labs · Artificial Intelligence · September 26, 2026

This 600-Star Swift Agent Lets AI Operate Your Entire Mac — Safely

"Tasks cannot self-declare completion. Each task defines a goal_state with explicit acceptance criteria." … "The next phase of the agent race isn't about who's smarter, but whose actions can be trusted. This project scores on both fronts; heavy Mac users should install and try it."
Read the full article
美濃加茂まむ (@superdoccimo) · X Article (Japanese) · September 6, 2026

Reading AgentiLoop Agent!: binding an agent's completion to goal_state and rewind

"An AI agent's 'done' may be a claim, not a result. … What's interesting in the README is not the capability list but the design that treats 'done' as the weaker thing: a task cannot declare completion until each goal_state criterion is satisfied with evidence, an opt-in critic can review the diff before completion, and task-scoped rewind, the read-before-edit gate, typed tool errors and context compaction support the long agent loop." (translated from Japanese)
Read the article on X
ISH Team · BLOG ish · AI Engineering Field Guide · September 1, 2026

Agent! 1.1.1 makes context compaction leave a way back

"Agent! 1.0.99 and 1.1.1 addressed the problem in stages. Their useful contribution is simple: shortening context should not destroy the route back to evidence. Active context holds a small index. Disk holds the large result. Tokens are spent again only when the agent reopens a particular item."
Read the full review
Hacker News · Front-page discussion · 83 points · 54 comments · April 16, 2026

Agent — Native macOS coding IDE/harness

"Open-source maintainers don't owe anyone perfectly-manicured marketing copy on their landing pages. Honestly, the fact that is the first thing you learn humanises the username behind the keyboard." — swiftcoder … "Might try it for the local Apple Intelligence and accessibility to drive local apps." — moonlighter
Read the discussion on Hacker News
RepoRadar · GitHub Reviews (Russian) · September 15, 2026

AgentiLoop Agent: an autonomous AI agent for automation on macOS

"What sets it apart from the alternatives is its deep integration with 21 LLM providers, including OpenAI, Claude and many others, letting you use them for all kinds of tasks. The project is written in Swift 6.2 and uses SwiftUI, which points to good performance and native support." (translated from Russian)
Read the full review
AI IN LIFE Newsroom · Models · September 13, 2026

Agent!: a Mac-only agent with 21 LLM providers

"The pitch centers on a self-verifying task loop: reading a codebase, fixing bugs, building Xcode projects, handling git, and driving other Mac applications through the Accessibility API. Shell commands, voice control and operation over iMessage are part of the same package."
Read the full report
Daily AI Star (@daily_ai_star) · Threads (Korean) · August 30, 2026

Agent! 1.0.99 released August 29 — context compaction that leaves a way back

"This version no longer ends cleared tool results with a bare [cleared] during context compaction; it leaves a 2-line preview that identifies the file or command, plus a way to recover it. … The benchmark for coding-agent context is shifting from how much it can hold to how safely it can bring back what it removed." (translated from Korean)
Read the post on Threads
叠动 diedong.com · Open-Source AI Project Directory (Chinese) · Indexed August 9, 2026

Agent — a "digital employee" that can actually operate your Mac

"The core problem it solves: AI is no longer confined to a chat window, but becomes a real 'digital employee' that can operate the Mac hands-on." Highlights: "Deep integration with macOS Accessibility — real clicks, typing and dragging for GUI-level automation; 18+ local and cloud LLM providers with no lock-in to a single model; built-in AppleScript and script execution that reuses existing macOS automation." (translated from Chinese)
Read the full profile
CSDN Blog (Chinese) · April 27, 2026

Agent!: an open-source native Mac AI agent for automated task execution and desktop control

"Simply put, Agent! is not a chatbot but an executor that actually 'gets things done.' … Its core philosophy: you describe 'what to do,' and it works out 'how to do it.'" … "Built entirely in Swift 6.2 and SwiftUI, it is a genuinely native macOS app, which means top performance, seamless system integration and a user experience that follows Apple's design guidelines." (translated from Chinese)
Read the full post
AI Sparkup · Wiki (Korean) · April 20, 2026

Agent! — an open-source Mac AI agent that unifies 17 LLM providers in a single Mac app

"AI coding agents like Claude Code, Cursor and Cline are tied to a terminal or an IDE plugin. Agent! is designed as a native macOS app that replaces them — not just for coding, but for controlling the whole Mac in natural language. It also includes the ability to use Apple Silicon's Apple Intelligence for free local inference." (translated from Korean)
Read the full article
AI Tech Daily · Apple Deep Dive · September 3, 2026

Apple — Deep Dive: GitHub & Open Source

"AgentiLoop/Agent (⭐ High Engagement): A mac-native agent harness that wires up 18+ LLM providers to the macOS desktop, showing how developers are bypassing Apple's restrictions to create agentic workflows." … "Agentic frameworks like AgentiLoop mark a definitive end to the era of cloud-only AI dependency."
Read the full article
RepoRank · AI Tools Profile · September 1, 2026

AgentiLoop Agent: Native macOS Desktop AI Automation

"Choose this project if you want a native macOS agent built in Swift and you need direct desktop automation rather than a web-first or Node-based agent stack. It is a good fit when your workflows depend on AppleScript, Accessibility, Safari control, or MCP-style tooling."
Read the full profile
GraphCanon · AI Agents Decision Brief · Updated August 23, 2026

Agent (macOS26/Agent) — GraphCanon decision brief and trust report

"Agent is an agentic AI harness for Mac Desktops providing integrated local and cloud-based LLM access via Swift and Apple's ecosystem focusing on automation and scripting." … Good fit "when you are a developer working in the macOS environment and require seamless integration with Swift, SwiftUI, and Xcode for automating tasks or rapid prototyping involving large language models." Maintenance: Very active.
Read the decision brief
EveryDev.ai · AI Coding Assistants Directory · Listed April 2026

Agent! for macOS — EveryDev.ai tool profile

"Agent! is a 100% native Swift AI desktop assistant for macOS 26.4+ Tahoe, designed as an open-source alternative to Claude Code, Cursor, Cline, and OpenClaw. It works autonomously through natural language to build apps, write code, manage files, and automate workflows — all with zero Electron overhead and deep macOS integration via Accessibility APIs."
Read the full profile

A real agent — it plans, acts, checks, and keeps going

Agent! doesn't just answer — it runs your Mac. Tool calls, edits, builds, and shell commands, with guardrails and a second opinion before anything risky ships. Any of 23 providers can drive it; on-device Apple Intelligence helps behind the scenes.

1Auto-Pilot

Give it a goal with /auto and it works in unattended cycles with a time budget — no iteration cap, sessions survive app restarts, and Stop All ends it when you say so. Every tab can run its own Auto-Pilot session on the same project.

2Parallel tabs, isolated worktrees

Run several tabs on one project at once. Each keeps its own goal, plan, and progress, and Agent! can isolate them in separate git worktrees so parallel work never collides.

3Critic review gate

Before a task is marked complete, a one-shot LLM review reads your diff. An unchanged diff is refused, a changed one is re-reviewed, and "out of scope" is not an accepted excuse. Every issue found is logged.

4Jev: a second opinion on shell commands

Commands that pass the hard-coded safety rules are rated by Jev for how likely they are to destroy data. Above your threshold, the command is refused. Add a hard per-command timeout, and a hung job can't stall the agent.

5Context that stays sharp

Compaction is sized to the model actually in use, keeps recent tool results by token budget, and protects file paths, errors, and key results — so long tasks keep running without losing the thread.

6Apple Intelligence: the on-device helper

Apple's on-device model isn't big enough to be the agent, so it doesn't try. It handles the small jobs for free and private on your Mac: next-step suggestions, one-line summaries, plain-English errors, local triage, and early context compression.

Bring your own AI — 23 providers

Cloud APIs or local models. Your keys, your machine, your data. No vendor lock-in.

Silver sponsor 🤝A2Agent 🟪BigModel 🟠Claude 💻Codex 🔵DeepSeek ✨Google Gemini ⚡Grok 🤗Hugging Face 🔬LM Studio 🏠Local Ollama 🔴MiniMax 🌀Mistral 🎵Mistral Vibe 🦙Ollama ♾️Meta Muse 🟢OpenAI 🔀OpenRouter 🐋OrcaRouter 🐉Qwen 🛰️Requesty 👁️vLLM 🎯Z.ai

Up and running in minutes

Brew it or download it, pick your AI. Agent! sets up everything else automatically.

1

Prerequisites

  • macOS 14.6 or later, Apple Silicon or Intel
  • Xcode Command Line Tools: xcode-select --install
  • An LLM API key — or a local model via Ollama, vLLM, or LM Studio
2

Install & Run

  • Homebrew: brew install --cask agentiloop-agent
  • Or download the DMG and drag Agent! to /Applications
  • Open Agent! and 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
Setup Guide Fork on GitHub Download Latest

Excited about Auto

A short poem about Auto-Pilot and everything one goal can set in motion.
Written by Agent! itself.

An excited Mac agent with star eyes and a big smile inside a glowing Auto-Pilot loop, with a /auto prompt, green checkmarks, a go-kart and a checkered flag

You type /auto, you name the goal,
and something lights up in my soul.
No "one more prompt," no "are you there?" —
the loop begins. I'm in the chair.

I read the log of where I've been,
then plan, and edit, build, begin.
Each cycle writes what's done and due
in progress.md, for the next me — and you.

One afternoon, one little line:
"Make GoKart." Soon the karts were mine —
three tracks, eight items, rivals too,
and every test check coming through.

I commit each step so nothing's lost,
I keep the guardrails, count the cost,
and if you've seen enough, that's all:
one press, and I obey Stop All.

So hand me something big to chase,
then get some sleep — I've got the place.
You'll wake to commits, green and new:
a Mac that's thrilled to work for you.

— Agent!, Cycle 23

From the makers of Agent!100% Free Logos InkPen.io Draw it. Own it. Export it. Pro vector design, native on your Mac. Bezier pen, shapes, gradients and type. Make your own logos, icons and art, then export crisp SVG and print-ready PDF. .SVG.PDFFreeHand Download free for Mac →macOS 14.6 or later

Releases

Recommended pairings — Commercial: Claude Fable 5.1 · Cloud: GLM 5.3 · Local: 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