FAQ

General

What is ArgentOS?

ArgentOS is an always-on personal AI operating system. It runs a persistent AI agent that you can talk to through Telegram, Discord, WhatsApp, Slack, Signal, iMessage, or a web dashboard. The agent has persistent memory, can execute commands, browse the web, manage tasks, and learn from interactions.

How is ArgentOS different from ChatGPT or Claude.ai?

ArgentOS is self-hosted and always-on. Unlike web-based AI chat interfaces:

Your agent runs on your hardware with your API keys
It has persistent memory that spans all conversations
It can execute commands and interact with your system
It connects to your existing messaging platforms
It can work autonomously through the task and heartbeat systems

Is ArgentOS free?

ArgentOS has a free Community tier with core functionality. Pro and Enterprise tiers unlock additional features. You still need your own API keys for model providers (Anthropic, etc.).

What API keys do I need?

At minimum, an Anthropic API key or Max subscription setup token. Optionally, you can add keys for MiniMax, Z.AI, OpenRouter, Ollama (free, local), and ElevenLabs (for TTS).

Setup

What Node.js version do I need?

Node.js 22+ is required. Use nvm (not Homebrew) on macOS to avoid ABI compatibility issues with native modules like better-sqlite3.

nvm install 22
nvm use 22

Does ArgentOS work on Windows?

Yes, through WSL2 (Windows Subsystem for Linux). Install Ubuntu in WSL2 and follow the Linux setup guide.

Does ArgentOS work on Docker?

Yes. See the Docker installation guide.

Can I run ArgentOS on a Raspberry Pi?

Yes, ArgentOS supports ARM64 Linux. A Raspberry Pi 4+ with 4GB+ RAM is recommended.

Usage

Can I use multiple messaging platforms at once?

Yes. ArgentOS supports running all channels simultaneously. Your agent shares the same memory and context across all platforms.

Does the agent remember things between conversations?

Yes. MemU (the memory system) persists information across all sessions and channels. The agent stores important facts, preferences, and events automatically.

How does the model router save money?

The model router scores each message's complexity and routes simple queries to cheap models (Haiku) and complex tasks to powerful models (Opus). Most conversations use the balanced tier (Sonnet), and simple greetings use the local tier (free).

Can the agent run tasks while I'm away?

Yes. The heartbeat system periodically wakes the agent to check for pending tasks. Combined with quiet hours configuration, the agent can work through task queues autonomously.

Security

Is my data sent to the cloud?

Only the messages sent to the LLM API (Anthropic, etc.) leave your machine. Memory, tasks, sessions, and configuration are all stored locally. ArgentOS does not phone home or collect telemetry.

Can the agent access my entire system?

Only if configured to. The sandboxing system controls what the agent can do. In sandboxed mode (default), dangerous operations require your approval. In locked mode, command execution is disabled entirely.

What happens if the agent makes a mistake?

In sandboxed mode, destructive commands require your approval. The agent cannot delete files, modify permissions, or run sudo without explicit confirmation.

Technical

What's the difference between MemU, openclaw-mem, and claude-mem?

Three separate systems:

MemU -- The active agent memory at ~/.argentos/memory.db. This is the agent's real brain.
openclaw-mem -- A legacy plugin (stale). Superseded by MemU.
claude-mem -- Used by Claude Code sessions only. Completely separate.

Why does ArgentOS fork OpenClaw?

ArgentOS started as a fork of OpenClaw and is being transformed into a full AI operating system with additional features: always-on loop, model router, task system, dashboard, and more.

How much disk space does ArgentOS use?

The base installation uses under 100MB. Memory and session data grow over time. A typical installation with months of use is under 500MB.

On this page