Agent

What it is

🌐 Official website: agentiloop.ai — downloads, docs, reviews and news.

The homepage listed on the repository, agentiloop.ai, puts it like this: AgentiLoop Agent! is a 100% native macOS agentic AI. One app, 23 LLM providers, total command over your Mac. Build apps, automate workflows, control any app — through natural language.

What the README says it does

• 🧠 Self-verifying task loop — reasons, executes, observes results, self-corrects. A task can't declare itself done until goalstate criteria are marked with evidence; an opt-in critic reviews the diff first.
• 🖥 Desktop automation — drives any Mac app through the Accessibility API (AXorcist), element-based with fuzzy auto-retry. Plus NSAppleScript, JXA and 51 ScriptingBridge app bridges, all in-process with TCC.
• 📜 AgentScript — Swift dylibs compiled at runtime and dlopen'd in-process with full TCC. Deleted scripts go to .Trash and are restorable.
• 🛡 Privileged execution — shell as you via a Launch Agent, or as root via a Launch Daemon you approve exactly once (SMAppService + XPC). See docs/SECURITY.md for why SMAppService already enforces signing identity.
• 🎙 Voice — say "Agent!" followed by your task; on-device SFSpeechRecognizer, auto-runs after 2.5s of silence, loops.

From the project’s README.

Getting started

From the README:

brew update && brew install --cask agentiloop-agent

Where the decision sits

Agent calls the hosted decision API rather than running its own weights. That keeps the project small and means its behaviour moves whenever the vendor ships a new model version. It also means an API key and a network round trip sit in the path of every decision.

Models it references: Jev.

How active it is

Created 2026-03-11, last pushed 2026-11-01, 652 stars and 71 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.