Shadowfetch Linux

Run a real AI agent on your own machine

Shadowfetch Linux is agent-ready. Everything an autonomous AI agent needs — Node.js, Python 3.13, git, ripgrep, ffmpeg — is already installed. Pick an agent, run one command, and it's working. Agents run on your hardware; cloud providers are optional.

Quick start

Open a terminal and run:

shadowfetch-agents

This shows your choices, confirms prerequisites, and launches the agent you pick. There is also a graphical AI Agents — Get Started entry in the application menu.

Option 1 — Hermes Agent (Nous Research)

A self-improving agent: after it helps with a task it writes itself a reusable skill, so it gets better the more you use it. One agent, many profiles, and a messaging gateway (Telegram, Discord, Slack, email).

shadowfetch-hermes

Installs Hermes (official installer, with a pipx fallback), runs hermes postinstall, then opens hermes setup. Afterwards: hermes to chat, hermes auth to add a provider or local Ollama, hermes gateway setup for messaging.

Option 2 — OpenClaw

A lightweight, friendly personal agent installed through npm — a quick, simple start that drives your local Ollama models out of the box.

shadowfetch-openclaw

Installs into your own user account (no root needed) and opens openclaw onboard. Choose the Ollama provider to stay 100% local.

100% local — no cloud, no API keys

Both agents can run entirely on your hardware via Ollama. Pick a model matched to your machine:

shadowfetch-llm

It detects your RAM/VRAM and free disk, recommends a model that will actually fit, and runs it locally. Then point your agent at the Ollama provider. Ollama listens only on localhost and the firewall blocks port 11434 — your models never leave the machine.

Which should I choose?

You can install both — they don't conflict.

Hermes Agent is a project of Nous Research; OpenClaw is an independent open-source project. Shadowfetch bundles their installers and the prerequisites for convenience and is not affiliated with or endorsed by either.