Your own AI agent,
on your own machine.

Helm lives on your hardware with full shell, files, web and screen. You message it from Discord; it actually does the work and reports back. Owner-locked, private, and powered by any model you like: your Claude subscription, an API key, or a free local model.

Runs on macOS, Windows and Linux · Discord & iMessage · No new SaaS bill

What Helm can do

Not a chatbot. An agent that acts.

Most assistants answer in a web tab. Helm has your terminal, your files, your browser and your screen, and the judgment to use them.

Lives on your machine

Full shell, file system and web access, not a locked cloud sandbox. It builds, runs and fixes things for real.

Message it anywhere

DM it on Discord, or iMessage on a Mac. No dashboard to babysit. It works like texting a very capable friend.

Owner-locked & private

Only your ID can command it. Your data, keys and conversations never leave hardware you own.

Real long-term memory

A structured memory store plus a synced Markdown knowledge base that learns your preferences and stays consistent across your machines.

Your whole fleet

Swap between your Mac and Windows box mid-conversation over Tailscale. One agent, every machine.

Sees and drives your screen

Takes screenshots, clicks and types. It captures whichever machine the brain is on, your Mac or your Windows box. It operates apps that have no API when it has to.

Thinks 24/7, upgrades itself

Background cognition during the day; nightly self-improvement gated by tests that auto-revert on failure.

Runs on any model

Claude (subscription or API key), or any other model: local (Ollama, $0, no account) or hosted (OpenAI, Gemini, Groq, OpenRouter). Your choice at install.

Encrypted secrets vault

Hand it credentials safely: encrypted at rest, never echoed into chat, logs or git.

How it works

Three moving parts. That's it.

01

You message

Send a DM from Discord or iMessage: a task, a question, anything.

02

Helm acts on your machine

It runs Claude with full tools right on your hardware: shell, files, web, screen, memory.

03

It reports back

You get the result (files built, problems fixed, a screenshot) straight back in the chat.

From your terminal too

One command: helm.

Don't want to open Discord? Talk to Helm straight from your shell. The terminal is a live window into the same running agent: one brain, one memory, one conversation, shared with Discord and iMessage. Type in the terminal and your phone sees it; reply on Discord and the terminal shows it.

terminal macOS · Windows · Linux
# register the `helm` command once (works in PowerShell, bash and zsh)
$cd ~/helm; npm link
# then, from anywhere
$helm   # open the chat (starts Helm if it isn't running)
$helm "what changed in this repo today?"
$echo "summarize my downloads" | helm

Run helm with no arguments for an interactive chat, or pass a message for a one-shot reply. It connects to the agent you're already running, so nothing is duplicated. Other commands: helm start (run the service), helm setup (wizard), helm --help.

Windows tip: in PowerShell, join two commands with ; not && — e.g. cd ~/helm; npm link.

How Helm compares

Built for you, not a data center.

The OpenClaw ecosystem and the hosted players each nail one slice: lightweight, secure, edge, or memory. Helm is the one that does all of it on your own hardware and ties your whole fleet together.

Discord + iMessage gateways Runs on any model: free, local or hosted Multi-machine fleet (Mac + Windows) Persistent memory + synced brain Thinks 24/7 & self-upgrades Clicks & types in any app Parallel build swarm Encrypted secrets vault
How Helm compares to other AI agents across capabilities
Open-source & local Managed & hosted
Capability Helm OpenClaw Hermes Agent TrustClaw ZeroClaw PicoClaw NanoClaw Claude Cowork Manus Perplexity Computer Kimi Claw Vellum
Runs on your own machine
Open / self-hosted
Chat from Discord / iMessage~~~
Full shell + file access~~~~~
Clicks & types in any app (no API)~~~~~
Persistent memory + synced brain~~~~~~~
Multi-machine fleet (Mac + Windows)~
Background thinking 24/7~
Self-upgrades (auto, tested)
Parallel build swarm~
Encrypted secrets vault~~~~~~~
Owner-locked & private~
Uses your subscription / BYO key~~~~~~
Runs on free / local models~~~
No extra monthly bill~~~~~

Scroll horizontally to compare all agents →

Yes ~Partial / limited No

Positioning based on each project's public description, not an exhaustive benchmark. "Partial" means the capability is limited or hosted-only. Product names belong to their owners. Tell us where we've got a row wrong and we'll fix it.

Get Helm

One command. Then it's yours.

BETA
# Works everywhere. Installs everything. You message it from Discord.
$npx github:GOODMAN-PRO/helm

Brings everything it needs: Node, Claude Code (the engine) and dependencies are installed for you. Then pick any model in the wizard; the free/local path (Ollama) needs no Anthropic account at all. macOS, Windows and Linux.

Windows tip: the PowerShell line works even when scripts are "Restricted". If a bare npx says "running scripts is disabled", use the PowerShell line above, or run npx.cmd github:GOODMAN-PRO/helm.

Setup, step by step

The command above handles 1-2; the wizard walks you through 3-5. Same on macOS, Windows and Linux.

01

Prerequisites

The installer auto-installs Node 18+ and Claude Code (the engine) if they're missing. Nothing to set up by hand.

02

Fetch & install

Downloads Helm and runs npm install for you.

03

Make a Discord bot

Developer Portal → New Application → Bot → Reset Token. Copy the token.

04

Run the wizard

Paste the token + your Discord user ID, then pick your gateway, your model (incl. free), and whether to run 24/7.

05

Message it

DM your bot on Discord (or iMessage on a Mac). It acts on your machine and reports back.

Multiple gateways

A guided setup screen turns on Discord, iMessage, or both. More on the way.

Any model, including free

Claude (subscription or API key), or pick a free local model from a list, and the setup downloads it for you (via Ollama, $0, no account). Hosted models (OpenAI, Gemini, Groq, OpenRouter) work too.

Run it 24/7

Optionally install it as a background service so it's always there.

Create your Discord bot (~2 min)

The one part that's yours to do. Discord requires a bot you own:

1

New Application

Developer PortalNew Application → name it → Create.

2

Get the token

BotReset TokenCopy. That's your DISCORD_TOKEN. Keep it secret. No special intents needed.

3

Your user ID

Discord Settings → Advanced → Developer Mode on, then right-click your name → Copy User ID. That's OWNER_ID. It locks the bot to you.

4

Add & DM it

OAuth2 → URL Generator → scope bot → open the URL → add to a server. Then DM the bot. Paste both values into the wizard.

Safety & permissions

Helm is a real agent on your machine: shell, files, web, screen, mouse/keyboard, scheduled actions, and a tested nightly self-upgrade. It's owner-locked to your Discord ID, secrets live in an encrypted vault, and it confirms before anything destructive. Start in “ask before each action” mode (the wizard's recommended default) and switch to full autonomy only once you trust it on that machine. Run it on hardware you own. It uses your own Claude account.