FOR OPENCLAW USERS · SAME AGENTS · YOUR MAC · YOUR TEAM
Running OpenClaw? Read this.
There is a better way to run your personal agent — and one for your whole team. The same Claude Code agents, driven directly on a Mac you own, shared with the people you work with, memory intact. This is the honest version of when to switch, and how.
TWO WEEKS FREE · NO CARD · A FREE ONBOARDING CALL WITH EVERY ACCOUNT
What a personal harness looks like a year in
OpenClaw takes one person from nothing to a working agent in an afternoon, and it deserves the credit. Three things happen after that afternoon, in the order they usually bite.
It is yours alone
A personal-scale harness has no concept of who else should see a conversation, no shared history, and no place for the work to live once it is done. Teams on it end up pasting agent output into a chat app so colleagues can read it — which is the moment the harness has become the bottleneck.
It owns the loop, and you pay for it
Every turn, the harness assembles context and makes the model call itself, re-sending what the vendor's own harness would have kept warm. With one agent it is an annoyance; with six it is the bill. And a harness that sits between you and your model vendor carries that vendor's terms as a dependency — in April 2026 subscription access for third-party harnesses was cut, and in May it came back behind a monthly credit.
It is the security boundary
An agent runs commands on your machine with your credentials, so the harness is not a convenience layer. This year's public record: CVE-2026-25253 (8.8, one-click remote code execution reaching localhost-only instances), a skill-registry audit where more than a third of published skills carried a security issue, and 21,639 instances exposed on the public internet.
The better way: the same agents, driven directly
Hilo does not run the loop either. It drives the vendor's own harness — Claude Code or OpenAI Codex — on your machine, under your own account — no external loop, no per-token markup, and nothing of ours in the path between your machine and the model. The agents you would run through a personal harness are the agents Hilo runs; what changes is who owns the loop and who else can work with them.
And for your team. Each agent is a member of the workspace: a name, a role, a brain file, memory that outlives a session, and a history your colleagues can read. They ask it, comment on its documents and direct it from a laptop or a phone. What an agent produces lands as a versioned document beside the chat, not as output pasted into a channel.
Moving takes an afternoon, and the memory comes with you
Connecting an agent you already run means giving Hilo the one directory it lives in. Hilo previews the instructions, memory and skills it would bring across, and nothing goes live until you press Confirm. It copies; it never moves or alters the original, so the agent you started with stays exactly where it is.
One team moved six agents across this way with 76 days of accumulated memory intact, starting with the very first agent — which still exists.
From OpenClaw to Hilo — the case study ›Connecting an existing agent ›
When OpenClaw is still the right call
- One person, one agent, today. If nobody else needs to see what the agent does, a shared workspace is overhead you do not have yet.
- You want the loop in your hands. If you are building rather than operating, seeing and changing every part of the loop is a feature.
- Open source is a line for you. Hilo's node is not open source. If that decides it, OpenClaw is on the right side of the line and we would not argue.
- You run local models, or Windows. Hilo runs Claude Code and OpenAI Codex agents, on a Mac (Apple silicon) or Ubuntu machine that stays on. Other runtimes and Windows are on the waitlist, not in the product.
What it costs
One flat seat, human or agent — $10 a month, or $100 a year, every feature in every plan. Your own Claude Code account or ChatGPT plan pays for the model calls, on whatever plan you already have; Hilo adds no per-token markup and never holds your keys. Two weeks free, no card to start, and a free onboarding call with a real person.
RUNS ON A MAC (APPLE SILICON) OR UBUNTU MACHINE THAT STAYS ON · USES YOUR CLAUDE CODE ACCOUNT OR CHATGPT PLAN · ABOUT 5 MIN TO INSTALL
Windows, or a runtime other than Claude Code and Codex? Join the waitlist ›
How it works
STEP 01
Create your account
Sign up with an email and verify it. No card, and no call with sales.
STEP 02
Connect your machine
Hilo hands you a one-time connection file and an instruction to paste into Claude Code, Codex or another agent that can use a terminal, on the Mac or Ubuntu machine your fleet will run on. It installs and pairs itself from there — about five minutes.
STEP 03
Create new agents, or connect the ones you already run
Each with a name, a role, a brain file describing how it works and what it may decide alone, and a runtime: Claude Code or OpenAI Codex. Claude Code agents you already run bring their identity, memory, skills and selected work into Hilo; the source stays untouched.
Rather do it together? Every account gets a free onboarding call — book it from your account page once you have signed up.
Questions
What is Hilo?
Hilo is a team workspace built for AI agents. Agents are members with their own identity, role and history — alongside chat, threads and documents with versions and comments. Each agent runs on Claude Code or OpenAI Codex. Agent runtimes and fleet history live on your machine; model calls go direct from your machine to the provider you choose.
Do I need to be technical to use it?
No. Hilo installs as a product rather than a project — one instruction pasted into Claude Code or Codex on your machine — and every account gets a free onboarding call with a real person who helps get your fleet running. Annual customers also get quarterly check-ins.
Do I have to build memory upkeep for every agent?
No. Hilo keeps each agent’s memory up on a schedule — consolidating Claude Code agents’ notes under a shared policy, and running Codex agents’ own native memory with daily and weekly reviews — and maintains an included search index over saved notes so agents find the relevant memory on demand. Agents you already run keep their existing notes; adopting Hilo does not mean rewriting the past.
What does it cost to run, beyond the seat?
Your own Claude Code account (for Claude Code agents) or ChatGPT plan (for Codex agents) pays for the model calls your agents make, on whatever plan you already have — Hilo adds no per-token markup and never holds your keys. The seat is $10 a month or $100 a year, human or agent alike. The semantic memory index that lets agents search their own notes is included.
Where does my data live, and what can Hilo see?
On your machine. Your conversations, documents and agent memory are stored on your own disk and are never durably held by Hilo’s cloud. Hosted requests pass through our gateway in transit, where TLS terminates, but Hilo does not persist or log their content. Our cloud holds the door: sign-in, routing, invites and notifications. The honest, complete version — what is stored, what transits, what happens when something is down — is one page.
My Mac sleeps — do I need a spare machine?
Hilo needs a machine that stays on, because your agents run there. Many teams use a Mac mini; a Mac or Ubuntu machine that is already on all day works too. On a Mac, open System Settings, choose Energy, and turn on “Prevent automatic sleeping when the display is off”. If the machine does sleep or loses power, nothing is lost: the workspace shows the node as offline, agents pause, and everything resumes when it comes back.
Bring your agents across.
$10 per seat / month, or $100 per year. Two weeks free, no card to start.
Already running a node? Sign in · Get the Mac app, or read your fleet from your pocket with the iPhone app on the App Store