DMNENGINE

Apolo — AI skill for Claude Code

AI community

Open-source AI desktop companion: a 3D robot that watches, approves and directs your AI agents (Claude Code, Gemini CLI, Ollama, OpenAI…).

How to install Apolo

This entry records only its repository, not the path inside it, so there is no exact command to give. Open DMNENGINE/apolo and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Apolo does

Open-source AI desktop companion: a 3D robot that watches, approves and directs your AI agents (Claude Code, Gemini CLI, Ollama, OpenAI…).

Alternatives in AI

AIHawk — Open-source AI browser agent: describe any task in plain language and it autonomously browses, clicks, types a 30.3k ★
Omniget — Udemy & Hotmart course downloader, YouTube downloader (yt-dlp GUI, 1,800+ sites) + desktop app for AI agents 13.9k ★
Opencodex — Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama… 12.3k ★

README

English · Español

**APOLO** is an open-source desktop companion that lives at the top of your screen as an animated 3D robot. It watches, approves and directs your AI agents: **Claude Code**, **Gemini CLI**, and its own **multi-model core** (Ollama, OpenAI, Anthropic, Gemini, OpenRouter…).

You stay in control. Every risky action asks first, from the floating island, Discord, a Stream Deck, or your phone.

✨ Features


🏝️ Floating island	Always-on-top HUD with live terminals, subagents, code being written, plan usage, and context per session.
🛡️ Permission control	Allow, deny or "always allow" from the island, Discord, Stream Deck or mobile. Dangerous commands (`rm -rf`, `format`, …) need a second confirmation.
🧠 Multi-model core	Its own agent loop with tools, persistent semantic memory, scheduled tasks, parallel subagents, context compaction and Mission Control.
🌐 Browser agent	Chrome/Edge/Brave extension with per-site permissions. It never touches password or card fields.
🖥️ Computer use	Sees the screen and uses mouse and keyboard with per-task consent, a visible red border and a panic stop (move the mouse to take back control).
🗣️ Voice	Neural voice replies and s