Shadowfetch Linux 2.1.3 «Umbra»

Run a real AI agent on your own machine

Shadowfetch Linux is agent-ready. Pick a runtime, create a separate workspace for each job, and deliberately enable only the browser, terminal, messaging and sandbox capabilities that job needs. Agents run on your hardware; cloud providers are optional.

Quick start

Open a terminal and run:

shadowfetch-agents

That one command shows your choices, confirms prerequisites, and launches whichever runtime you pick. If you would rather not start in a terminal, the same flow has anAI Agents - Get Started entry in the application menu.

A full walkthrough ships inside the OS at/usr/share/doc/shadowfetch/AGENTS.md.

Agent Studio

Projects start with structure instead of an empty directory. Agent Studio creates a private workspace holding AGENTS.md, active tasks, durable memory, a dated work log, artifacts, logs and scratch space. If Hermes is installed, it can create a separate profile and set that workspace as the profile’s working directory.

shadowfetch-agent-workspace

Browser automation, tools and isolation

The guided setup uses each runtime’s own official tool flow. Hermes can configure its local browser or a supported tool gateway. OpenClaw can install Debian Chromium on demand and run its managed, agent-only browser profile. Rootless Podman readiness and the effective sandbox policy are shown to you before you rely on them.

shadowfetch-agent-tools

Run shadowfetch-agent-doctor at any time to check versions, upstream diagnostics, exposed local ports, local-model binding and sensitive configuration permissions.

What ships on the system

Every one of these is on the path of a stock install. Nothing here is a download you have to go and find first.

shadowfetch-agents: The front door. Shows your choices, confirms prerequisites, and launches the runtime you pick. There is also a graphical AI Agents - Get Started entry in the application menu.
shadowfetch-agent-workspace: Agent Studio. Creates a private workspace with AGENTS.md, active tasks, durable memory, a dated work log, artifacts, logs and scratch space.
shadowfetch-agent-tools: Guided setup for browser automation, tool gateways and sandboxing, using each runtime's own official tool flow.
shadowfetch-agent-doctor: Checks versions, upstream diagnostics, exposed local ports, local-model binding and sensitive configuration permissions.
shadowfetch-hermes: Installs or updates Hermes with the official Nous Research installer, falls back to pipx if needed, then opens hermes setup.
shadowfetch-openclaw: Installs or updates OpenClaw into your own user account - no root needed - and opens openclaw onboard --install-daemon.
shadowfetch-ai: The recommended local setup: detects available memory, installs one model that fits, and configures local web chat.
shadowfetch-llm: The advanced model catalog, for when you are ready to compare more than one.

Two runtimes, both bundled

Option 1

Hermes Agent (Nous Research)

Self-improving. 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 for Telegram, Discord, Slack and email.

shadowfetch-hermes

hermes: chat
hermes model: pick a provider, or local Ollama
hermes tools: configure tools
hermes gateway setup: messaging

Option 2

OpenClaw (independent open source)

Lightweight. A friendly personal agent installed through npm - a quick, simple start that drives your local Ollama models out of the box. Choose the Ollama provider to stay 100% local.

shadowfetch-openclaw

100% local - no cloud, no API keys

Both runtimes can run entirely on your hardware via Ollama. The recommended setup detects available memory, installs one model that fits, and configures local web chat. The wider catalog stays available through shadowfetch-llm when you want to compare more.

shadowfetch-ai

Ollama listens only on localhost and the firewall blocks port 11434 - your models never leave the machine.

Which should I choose?

Most capable, learns and grows, messaging built inHermes
Quick, simple, lightweightOpenClaw
Just a private local chatbot, no agentshadowfetch-ai

You can install both - they don’t conflict.

Download 2.1.3 «Umbra»

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.