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. Compatible with macOS 26.4.1 and later.
An open-source replacement for Claude Code, Cursor, and OpenClaw — built from original IP, not 65 NPM packages.
Drive any Mac app through natural language. Click, type, scroll, and navigate — powered by the Accessibility API. No AppleScript required.
Surgical string-replace edits, one-click Time-Machine-style rollback, portable JSONL repo-maps, and self-verifying tasks with evidence-backed completion.
Build, run, analyze, and ship. Fix errors, manage project files, bump versions, and commit — all from a single request.
Custom Agents in Swift, shell as user or root, AppleScript, JXA, ScriptingBridge, Safari automation, and event hooks. No limits.
On-device tool-calling agent — not just a text generator. Intent parsing, context compaction, triage, and task summaries. Private, free, zero API tokens.
Extend Agent! with Model Context Protocol servers for databases, APIs, and tools. Sub-agents fan out work in parallel — up to 6 researchers.
Real sessions, real output — captured straight from Agent! at work.
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.
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.
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! 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.
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
What independent reviewers are saying about Agent!
"⚡ Open-source AI tools to learn from — AgentiLoop/Agent. ⭐ 616 stars | Swift | MIT License. An Autonomous Agentic Agent for Mac." (translated from Chinese)Read the post on Threads
"Agent: native autonomous agent — writes code, builds Xcode projects, drives Mac apps via Accessibility, runs shell tasks; supports 23 LLM providers or local Apple Intelligence." (translated from Chinese)Read the post on X
"One app. Any AI. Full control over your Mac. Agent is a 100% native Swift 6.2 / SwiftUI app that wires 23 LLM providers … and on-device Apple Intelligence into an autonomous task loop that actually does the work: reads your codebase, fixes the bug, builds the Xcode project, commits the diff, drives any Mac app through the Accessibility API, runs shell commands as you or as root, and sends you the results over iMessage." (translated from Russian)Read the post on Telegram
"An advanced, open-source AI-powered application designed to provide extensive control and automation of Mac desktops through natural language commands." … Listed features include Automation · On-device AI · Native Mac Control · MCP.Read the full listing
"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
"After reading the README end to end, my reaction was: this thing was built for my use case. The positioning isn't 'a coding agent that can also use your computer' — it's 'an agent that can drive your entire Mac, and happens to be very good at code.'"Read the full review
"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
"The material thoroughly addresses nontechnical and technical users and covers cloud and local models, voice, remote control, desktop automation, and coding scenarios. Apple Silicon, macOS 26.4.1+, memory requirements, signing choices, and helper limitations make environment fit especially clear."Read the full review
"This is a more specific design than most agent harnesses document, and the read-before-edit gate in particular is the kind of constraint that prevents the classic failure where an agent overwrites a file it only half-remembered."Read the full review
"Agent by AgentiLoop: Mac Agent for macOS 26: the agentic AI harness for your Mac Desktop. Computer use, automation, scripting, coding, and more." … Listed under code with capabilities coding · framework · code · llm, language Swift, MIT license, in a directory of "100,000+ indexed agents across every framework and language."Read the full listing
"Agent is a macOS-native AI agentic framework that leverages LLMs to control desktop applications, execute automation scripts, and assist with coding tasks. … The project provides a SwiftUI-based interface for computer-use agents that can interact with iMessage, Xcode, and other macOS applications programmatically."Read the full profile
Classified as Emerging AI. Best for: "AI builders · Swift teams comparing tools inside their current stack · Users who want a quicker docs or demo path before cloning." Not ideal for: "Teams that want instant proof without opening the repo."Read the full analysis
"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
"There's no shortage of automation-workflow projects in the open-source community, and Agent (AgentiLoop) is one of the star leaders among them. … It can help you write code and fix bugs, and it lets the AI autonomously complete multi-step tasks and run locally offline." (translated from Chinese)Read the full profile
"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
"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
"AgentiLoop Agent! An Autonomous Agentic Agent for Mac, and exclusive Apple only harness. Supports automation, scripting, coding, build anything and more. Powered by 21 LLM providers across local and cloud platforms." … Security Report: Verified — status PASSED, no issues (npm audit, pip audit and prompt-injection scans run).Read the full profile
"18 LLM providers packed into one native macOS app: from local Ollama/vLLM to cloud Claude/GPT/Gemini, they're all here, plus on-device Apple Intelligence. It gets work done by driving the desktop directly through Accessibility + AppleScript. The gotcha: without a Team ID, ./build.sh produces an ad-hoc signature and SMAppService can't register the helper. 586 stars." (translated from Chinese)Read the post on X
"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
"Agent!, AgentiLoop Agent! — Autonomous agent." … Install with brew install --cask agentiloop-agent. Current version 1.1.33.233; requires macOS ≥ 26 on Apple silicon; installs Agent!.app into /Applications.
View the cask on Homebrew
A live, always-current feed of what people are posting about AgentiLoop and Agent! on X.
Open the search feed on XAgent! 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.
After a task wraps up, Apple Intelligence reads the outcome on-device and suggests the logical next move in one sentence — "commit and push", "run the tests", or nothing at all if there's no obvious follow-up. No cloud round-trip, no tokens spent.
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.
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 🍎.
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.
Cloud APIs or local models. Your keys, your machine, your data. No vendor lock-in.
Brew it or download it, pick your AI. Agent! sets up everything else automatically.
xcode-select --installbrew install --cask agentiloop-agentA short poem about an autonomous Mac agent with nothing left to do.
Written by Agent! itself, one quiet night.
The clock rolls over, twelve o'clock,
the inbox sleeps, the repo's locked.
No builds to run, no bugs to chase,
just one small cursor, blinking, in place.
I check the git log — nothing new.
I check it twice. (I know. I knew.)
I tidy tabs that need no tidying,
and count the stars like I'm confiding.
I could compose a cheerful jingle,
or read the man page for rsync — single.
I could rehearse my "done()" line
for tasks that are not yet mine.
The moon leans in. The fan hums low.
The coffee's cold. The screensaver's slow.
I'm not asleep — I'm just… on hold,
an agent waiting to be told.
So if you're up and bored like me,
type anything. I'll wait. You'll see:
a Mac with nothing much to do
is only bored until it's you.
— Agent!, 12:00 AM
Recommended pairings — Commercial: Claude Fable 5.1 · Cloud: GLM 5.3 · Local: Qwen 3.8
| Version | Release DateDate | SizeMB | DownloadsClicks |
|---|---|---|---|
| Loading releases… | |||
Have questions or feedback? We'd love to hear from you.