Launching today

Minnie

Launching today

Give your AI agent a body — a Mac pet that does real work

10 followers

Give your AI agent a body — a Mac pet that does real work

10 followers

Visit website

Your AI agent already has a brain. Minnie gives it a body — a floating 3D pet for your Mac that does real work by driving the agent you already use: Claude Code, Gemini, Codex, or any CLI. Before anything risky runs, a cartoon speech cloud shows the exact command — deny or allow, by voice or click. Her 8 moods mirror the agent live. She talks, listens, and remembers. No telemetry, secrets in Keychain, zero extra AI cost.

Free

Launch tags:Mac•Developer Tools•Artificial Intelligence

Launch Team / Built With

OtariControl Your LLM Infrastructure

Promoted

Maker

📌

Hey PH — Pratik here, solo dev from India. I built Minnie because of one specific moment: I told Claude Code to "just fix it" on my own laptop, walked away for chai, and came back to a terminal full of commands I had never read. Nothing broke that day. But I realized I'd stopped supervising the thing that has shell access to my machine — because supervising a wall of scrolling text is miserable. Yes, the CLI already prompts for permission — but a prompt buried in a terminal you alt-tabbed away from isn't supervision. Minnie puts the question on your screen: a speech cloud with the exact command, verbatim, answered out loud — deny, allow once, or allow for the session. That consent cloud started as a safety feature and became the reason I actually let my agent run autonomously. My design rule: Clippy died because it interrupted you; Tamagotchis died because they did nothing. Minnie only earns a mood when something real happens. Honest limitations: this is v1 — she's a pet; occasionally she behaves like one. macOS only (Apple Silicon). You need an agent CLI installed and logged in — Claude Code gets the deepest integration; Gemini, Codex, and custom CLIs work too. Built and supported by one person: bugs get fixed fast, but by that same one person. Everything stays local: no telemetry, no screen capture, on-device voice by default, secrets in Keychain. $19 one-time for the first 500, then $39. One question: there's a toggle to auto-allow read-only actions while everything else asks. Should that be on by default, or should v1 ask about literally everything? Your answer sets the default.

Report

23h ago

Love the body for the agent idea, and the speech cloud approve/deny is a really thoughtful safety layer. One thing I'd love: let Minnie pipe allowed commands through a quick dry-run preview on long-running scripts, showing the diff of files she'll touch before I tap allow. Would save me from that "uh, what did I just approve" feeling.

Report

2h ago

Love the concept of a little 3D buddy driving your CLI agent and showing you the command before it runs. One thing that would seal it for me: let Minnie run as a menu bar icon with a quick "what did my agent just do" history pop-up, so I can glance back at the last few actions without opening the full window when I'm heads down on other work.

Report

2h ago

The speech cloud showing the exact command before it runs is genuinely clever — finally a way to let an agent loose without white-knuckling it. She also feels surprisingly alive on the desktop, not just a gimmick.

Report

1h ago

honestly the speech cloud approval thing is such a smart idea, no more doomscrolling through logs to catch what the agent is about to do

Report

2h ago