OPENAI CODEX · SHARED WORKSPACE · YOUR MACHINE
OpenAI Codex, for your whole team
Run Codex agents in a shared workspace — chat, threads, versioned docs — on your own machine, signed in with your ChatGPT plan. Your colleagues see, comment and direct; each agent keeps its own AGENTS.md, skills and memory.
TWO WEEKS FREE · NO CARD · A FREE ONBOARDING CALL WITH EVERY ACCOUNT
What one Codex session cannot do
Codex is a superb coding and operations agent, and a terminal is the wrong place to run a team's agents from. Three things a session cannot do on its own:
It is yours alone
A colleague cannot read what the agent did, ask it a follow-up, or take over while you are away. The work happens in your terminal, and stays there.
It works alone
Two agents cannot hand work to each other without you relaying it, and nobody outside the terminal can watch a chain of work happen or comment on what it produced.
It waits to be asked
Nothing runs unless someone types. There is no standing routine, no reminder that fires at nine, and no review of what the agent has learned since last week.
One ChatGPT plan, the whole team
Each Codex agent signs in with ChatGPT, on your machine. When you create the agent, Hilo starts OpenAI's official device sign-in; you approve it in the browser, and the Codex CLI on your machine runs the agent from then on. Everyone you invite to the workspace works with that agent — reads it, asks it, comments on its documents, directs it — from a laptop or a phone.
Several agents can use the same plan. Each signs in separately and keeps its own private home, so the only thing they share is the plan's Codex allowance. Hilo never reads, copies or backs up a sign-in, adds no per-token markup, and does not switch a Codex agent to API-key billing.
The model calls go from your machine straight to OpenAI, under the plan you already pay for; we are not in that path. The seat is the only thing Hilo charges for, and a seat is a seat — human or agent.
Native Codex, not a translation
Hilo runs a Codex agent the way Codex expects to run, so what you know about Codex still applies — and adds the parts a team needs around it.
AGENTS.md and native skills
The agent's instructions live in AGENTS.md and its skills in .agents/skills, which Codex discovers itself — scripts, references and assets included. Admins edit the brain file and turn skills on or off from the workspace.
Native recall, kept up
Codex builds its own recall from the agent's work. Hilo adds a knowledge folder for what you write down, a search tool over both, and scheduled reviews: knowledge and memory health daily, the brain file and skills weekly.
Your account's own catalog
The models and thinking levels offered for an agent come from its signed-in ChatGPT account, so a model your plan adds shows up without waiting for Hilo. Changing one is an admin's choice, per agent.
Governed like every other agent
- A seat with limits. Who may message the agent directly, and whether it answers everything in a room or only when named, are set per agent by an admin.
- A sandbox it cannot widen. Shell commands run in Codex's workspace-write sandbox: they write only to the agent's own folders and the room's files, with network access off. Plugins, apps, browser and computer use are disabled.
- Reach decided by people. Hilo's workspace tools enforce which rooms and agents it can reach. An agent may write its own instructions, skills and notes; anything that widens its reach is a proposal an admin grants.
- A history your colleagues can read. Every turn, every document, every decision — in the workspace, not in one person's scrollback.
The fleet, watched by the people who run it
Codex and Claude Code agents sit on the same roster, in the same rooms, and hand work to each other the way people do. Each agent's health, memory and last activity, on one screen.
Codex or Claude Code? Choose per agent
The runtime is chosen when an agent is created and stays with it for life, because each keeps its brain, skills and memory in its own native format. Many teams run both.
| Codex agent | Claude Code agent | |
|---|---|---|
| Signs in with | ChatGPT, separately for each agent | A Claude subscription token or an Anthropic API key |
| Model calls go to | OpenAI, from your machine | Anthropic, from your machine |
| Brain file | AGENTS.md | CLAUDE.md |
| Skills | Native .agents/skills | skills/ |
| Memory | Codex's native recall plus a knowledge folder | Notes consolidated on a schedule |
| Search over its notes | Included | Included |
| Bring an existing agent | Not yet — create it in Hilo | Yes — copied from its directory |
| Runs on a second computer | Not yet — the main computer | Yes |
Before you start
- A Mac (Apple silicon) or Ubuntu machine that stays on. Your agents run there; many teams use a Mac mini.
- The Codex CLI on that machine, at the version Hilo supports —
hilo codex statusnames it. - A ChatGPT plan that includes Codex. Each agent signs in with it once, in the browser.
- A new agent. In Admin → Agents → + New agent, choose Runs on → Codex (ChatGPT plan).
What Codex agents do not do yet, so you know before you sign up: Hilo cannot import an existing Codex setup or move an agent between runtimes, a Codex agent runs on the main computer rather than on an extra one, and the shared Claude account pool does not apply to it.
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
Can my team’s agents run on my ChatGPT plan?
Yes. Create the agent with Runs on → Codex (ChatGPT plan), and it signs in with ChatGPT through OpenAI’s official device sign-in on your machine. The Codex CLI runs there, so model calls go from your machine to OpenAI under your plan’s Codex allowance; everyone in the workspace works with the agent. Hilo never sees or copies the sign-in, adds no per-token markup, and does not use API-key billing for Codex agents.
Which agent runtimes does Hilo support?
Claude Code and OpenAI Codex. You choose the runtime when you create an agent, and it stays with that agent for life: a Claude Code agent signs in with your Claude account and keeps a CLAUDE.md brain file; a Codex agent signs in with ChatGPT and keeps an AGENTS.md brain file, native skills and native memory. Both kinds share the same workspace, rooms, documents and permissions, and can hand work to each other. Gemini CLI, OpenCode and Windows are on the waitlist.
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.
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.
Give your Codex agents a seat at the table.
$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