Skip to main content
OpenClaw is a separate agent platform. Its agents live in a long-running server called the OpenClaw Gateway, where they keep their own workspaces, messaging channels and cron jobs. Clawboo connects to a Gateway on your computer, shows its agents next to your others, and runs them in team chat, on the board and in Routines.
  • Best for: people who already use OpenClaw, or who want agents that also answer on OpenClaw’s messaging channels (set up in OpenClaw itself).
  • You need: Clawboo running on a Node.js version that OpenClaw supports, and a credential it can use: a provider key, a ChatGPT sign-in or a local Ollama. Clawboo installs and starts the Gateway for you.

Before you begin

  • Clawboo on a Node.js in OpenClaw’s range: the setup installs the newest 2026.9 release of OpenClaw, and installs it on the Node.js Clawboo itself runs on. Since 2026.9.34 that release needs 24.22.1 or later in the 24 line, or 26.12.1 and later (>=24.22.1 <25 || >=26.12.1). Node 22 and Node 25 can no longer run it, even though Clawboo itself runs on Node 22.12 and later. The setup checks this first and installs nothing on a Node.js outside the range. Settings > System shows the Node.js Clawboo runs on. See OpenClaw’s Node.js guide.
  • npm, which comes with Node.js. The setup installs openclaw@~2026.9 into Clawboo’s own runtimes folder, never into npm’s global folder, so it needs no sudo.
  • A credential OpenClaw can reuse: a provider key you connected in Clawboo, a ChatGPT sign-in, or the local Ollama you set up for Clawboo Native. With none of these, the setup asks you for a key.
You don’t need OpenClaw installed already. If it is, the setup keeps your install, fills in only the settings that are missing, and uses a Gateway that is already running.

Set up OpenClaw

Set up OpenClaw is one button. It reuses a credential you already connected, installs OpenClaw if needed, starts the Gateway and connects to it. The same setup runs from Settings > Runtimes and from onboarding’s Add more runtimes step.
1

Start the setup

Open Settings > Runtimes. On the OpenClaw row (“Run OpenClaw agents on a local Gateway”), click Set up, then Set up OpenClaw. In onboarding, the Add more runtimes step has the same row.The row’s footer reads In setup, and the panel shows Preparing OpenClaw….
2

Let Clawboo reuse a credential

Clawboo looks for a credential in this order and uses the first one it finds:
  1. A provider key saved in Clawboo (on the Providers page, in onboarding or on a runtime’s card) or already in OpenClaw’s ~/.openclaw/.env. A key that is only exported in your shell doesn’t count. With several keys, it takes the first in this order: Anthropic, OpenAI, Google, OpenRouter, xAI, Groq, Mistral, Moonshot, MiniMax, Together, NVIDIA, Hugging Face, Cerebras, Venice.
  2. A ChatGPT sign-in that OpenClaw already holds.
  3. A ChatGPT sign-in that only Codex holds. The panel asks you to sign OpenClaw in too (next step).
  4. The local Ollama you set up for Clawboo Native.
  5. Nothing. The panel asks you for a key (next step).
It then writes OpenClaw’s configuration. It sets the Gateway to local mode and otherwise fills in only what is missing, so your default model and other settings stay. See What Clawboo writes to OpenClaw.
3

Add a key or sign in, if asked

Nothing connected. The panel reads “Connect a provider key for OpenClaw to use. It powers the local Gateway.” Pick Anthropic, OpenAI or OpenRouter, paste the key and click Connect & set up (or press Enter). Clawboo saves the key the way the Providers page does, then runs the setup again.Codex is signed in, OpenClaw isn’t. Each runtime keeps its own ChatGPT sign-in, so OpenClaw needs one too. The panel installs OpenClaw first if it is missing, then shows Sign in with ChatGPT. Click it: your browser opens on OpenAI’s sign-in page, with no code to type, and the setup carries on once the sign-in is saved. Re-check runs the setup again, and Use an API key instead switches to the key prompt. On Windows, the panel gives you the command to run in your own terminal instead.Ollama doesn’t have the model. If your Ollama is missing OpenClaw’s default model, or isn’t running, the setup stops before it starts the Gateway. The panel names the model it couldn’t find and shows the ollama pull command for it. Run that command, then click Check again. Continue anyway starts the Gateway regardless, but OpenClaw agents can’t answer until the model is there.
4

Install OpenClaw and start the Gateway

If OpenClaw isn’t installed, the panel shows Installing OpenClaw… and installs openclaw@~2026.9 into Clawboo’s runtimes folder, with npm’s output in a log. Then it shows Starting the Gateway…. A Gateway that is already running on OpenClaw’s port is used as it is. Otherwise Clawboo starts one and waits up to 60 seconds for it to answer.If OpenClaw asks for openclaw doctor --fix before it will start (this can happen after an OpenClaw upgrade), Clawboo runs it once and starts the Gateway again.The log fills with install and Gateway lines, then the panel moves on to connecting.
5

Approve this device

OpenClaw asks you to approve each new device once before it can connect, so the panel shows an Approve this device card. Click Approve this device. The card reads “Approved. Reconnecting…” and connects again.You should see OpenClaw connected. The panel closes about a second later, and the OpenClaw row reads Connected.
Set up OpenClaw on onboarding's Add more runtimes step: the install log streams while the Gateway starts

If a step fails

The panel replaces its progress with the error and a Retry button. Retry runs the whole setup again: it skips the install once OpenClaw is installed, and joins a Gateway that is still starting instead of launching a second one. If the reconnect after approval fails, or OpenClaw still says the device isn’t approved, the error reads “OpenClaw still needs this device approved. Retry to approve it again.” Retry then brings back a fresh approval card. Cancel closes the panel at any point before it connects. An install that has already started still finishes in the background. The exact errors and their fixes are under Troubleshooting.

Approve from a terminal instead

The approval card runs two OpenClaw commands for you. You can run them yourself:
The first prints the id of the waiting request; the second approves it. If Clawboo installed OpenClaw, type the full path in place of openclaw, such as ~/clawboo-runtimes/bin/openclaw devices approve --latest (see Where OpenClaw is installed). Then run Set up OpenClaw or Reconnect OpenClaw again so Clawboo connects. See OpenClaw’s devices command.

Use your ChatGPT plan

OpenClaw can run on a ChatGPT subscription instead of an API key, through its own openai-codex provider. It needs its own sign-in, separate from Codex’s:
  • During setup, or later under Manage > ChatGPT subscription, click Sign in with ChatGPT. This needs Codex connected first; until then the row reads “Connect Codex first”.
  • Or run OpenClaw’s own login in a terminal: openclaw models auth login --provider openai-codex. When Clawboo installed OpenClaw, the command the panel shows names the full path of its openclaw, since that is not on your PATH. Use it rather than openclaw onboard, which can reset your channels, memory and cron jobs.
With the sign-in in place, the setup writes no key, and if OpenClaw has no default model yet it sets your plan’s own default, read from your Codex CLI. OpenAI decides which models each ChatGPT plan may use, so Clawboo names none of its own: if it cannot read your plan’s models, it sets none and OpenClaw uses its own default. OpenClaw agents, Codex agents, Hermes on a ChatGPT sign-in and your own Codex use all share your plan’s limits.

Where OpenClaw is installed

Set up OpenClaw, and Check for Updates in Settings > System, install OpenClaw into Clawboo’s own runtimes folder, ~/clawboo-runtimes by default (CLAWBOO_RUNTIMES_DIR moves it, and so does CLAWBOO_HOME), never into npm’s global folder. The command that starts it is ~/clawboo-runtimes/bin/openclaw, and it runs OpenClaw on the Node.js that installed it, whatever node comes first on your PATH later.
  • Clawboo uses its own copy first. The Gateway Clawboo starts, openclaw doctor --fix, device approval, the model list and the ChatGPT sign-in all run this copy, so the Gateway runs on the Node.js that installed it. Without one, Clawboo uses an openclaw on your PATH, so a global install you made yourself keeps working.
  • It is not on your PATH. To run an OpenClaw command yourself, such as the ones on this page, type the full path: ~/clawboo-runtimes/bin/openclaw doctor --fix.
  • An update never leaves it half replaced. A new install goes into a folder beside the current one and becomes current only when npm succeeds. A failed install is removed, and the OpenClaw you had keeps working.
  • A Gateway you run yourself is left alone, such as OpenClaw’s own launchd service on port 18789. It keeps running the OpenClaw it was started with.
  • If its Node.js is gone, for example after nvm uninstall, a Homebrew upgrade that deletes the old version, or an app that runs Clawboo on a Node.js of its own being moved or renamed, Clawboo from 0.9.0 moves this copy to the Node.js Clawboo runs on, and log it, when that Node.js is the same version or a later release of the same major version on the same kind of processor. An install from 0.8.0 or older recorded no processor, so for it the processor is not checked: install OpenClaw again if Clawboo now runs on a Node.js for another kind of processor. Otherwise, and in 0.8.0, Clawboo stops using this copy, and OpenClaw reads as not installed unless a global copy exists; Set up OpenClaw installs it again on the Node.js Clawboo runs on now. See Which copy Clawboo uses.
The runtimes folder covers its layout, the safety rules and how to remove it.

OpenClaw’s own sandbox stays off

OpenClaw can run its agents’ tools in a Docker or Podman container of its own. Clawboo keeps that sandbox off (agents.defaults.sandbox.mode: "off" in openclaw.json), so OpenClaw’s tools run on the same computer Clawboo and its other agents use. Set up OpenClaw writes it only when your config has no agents.defaults.sandbox, so a sandbox you set up yourself stays. off is OpenClaw’s own default; Clawboo writes it out so it holds if a later OpenClaw changes that default. Agent isolation, with one agent user or a user per agent, does not cover OpenClaw agents: they run inside the OpenClaw Gateway, as whoever started it.

Default models

When OpenClaw has no default model yet, the setup picks one for the provider it reused. It never replaces a default you already have. Change it under Manage > Default model, which every OpenClaw agent uses unless it has its own model. An agent’s own model is set on its page. In both pickers, the OpenAI Codex group lists the models your ChatGPT plan can run, read from your Codex CLI; it is left out while Clawboo cannot read them. For OpenClaw’s model settings, see Model providers and, for Ollama, Ollama. Earlier versions of Clawboo set google/gemini-2.0-flash for a Google key. Google shut that model down on 2026-06-01, and OpenClaw now treats it as an unknown model and reports the whole config as invalid. If your default is still google/gemini-2.0-flash, pick another model under Manage > Default model.

What a new Boo is allowed to run

OpenClaw’s Gateway decides whether an OpenClaw agent may run a command, from each agent’s command policy. Clawboo sets that policy when it creates an agent:
  • A new OpenClaw agent gets Ask for Unknown. It asks you before running a command it hasn’t been allowed. (A caller of the REST API can pass another posture, and Clawboo writes that one instead.)
  • A refused policy stops the creation. If the Gateway won’t take the policy, Clawboo removes the half-made agent and Create Boo shows “Could not set this agent’s command permissions on the Gateway, so it was not created”, followed by the reason.
  • An agent made outside Clawboo has no policy from Clawboo. It follows the Gateway’s own defaults, which let it run commands without asking unless you changed them.
  • Nothing re-applies a posture later. Clawboo writes it when it creates the agent, and when you change Command Execution on the agent’s Permissions tab. A change made outside Clawboo stays.
Answering Always to a command card adds a standing permission. The agent’s Permissions tab lists those under Commands this Boo can run without asking, where you can revoke one. See Command permissions and OpenClaw’s exec approvals.

Manage OpenClaw

Once OpenClaw is connected, its row reads Connected and offers Manage: When OpenClaw is set up but its Gateway is offline, the row shows that and offers Reconnect. Reconnect OpenClaw runs the same setup as above: it reuses your configuration and starts the Gateway. For OpenClaw’s own service commands, see the gateway command. When OpenClaw is set up and nothing uses it yet, the row reads Not in use and offers Connect. Opening the row has the server connect to the Gateway (see How Clawboo connects); it then reads Connected, or Disconnected with Reconnect if the Gateway does not answer. Once the server is connected, within about 90 seconds of opening the row, the dashboard opens its own Gateway connection too, which OpenClaw 1:1 chats use, even if you have left the page by then. If it cannot, it says so and points you at Connect this page. Something else can connect the server while a page is open with no Gateway connection of its own, such as a routine for an OpenClaw agent falling due, or OpenClaw opened in another tab. From 0.9.0, OpenClaw’s row on that page then reads Connected and also offers Connect this page, beside Manage. It opens the page’s own Gateway connection without a reload, and is gone once the page has one. If the page still cannot connect, a message says so, and the button stays so you can try again.

What Clawboo writes to OpenClaw

Clawboo changes OpenClaw’s files in these places. ~/.openclaw is OpenClaw’s state folder (OPENCLAW_STATE_DIR moves it), and ~/.clawboo is Clawboo’s (CLAWBOO_HOME moves it).
Provider keys in ~/.openclaw/.env and in each agent’s auth-profiles.json are stored in plain text, because that is where OpenClaw reads them. Clawboo writes both files readable only by your user account (mode 0600), but anything that runs as you can read the keys. Clawboo’s own copy stays in its encrypted vault.
To back up or reset these folders, see Where Clawboo keeps data. For OpenClaw’s own settings, see its configuration guide.

How Clawboo talks to the Gateway

Clawboo keeps two connections to the Gateway. Both use a device identity that you approved once during setup, stored in ~/.clawboo/proxy-device-identity.json. That identity only proves Clawboo to the Gateway; it does not protect the dashboard itself (see Self-host securely). The server’s own connection stays open once something needs the Gateway (see How Clawboo connects), with or without a browser tab. Over it, Clawboo:
  • runs every OpenClaw agent turn in team chat, including the tasks those agents are given;
  • runs OpenClaw agent Routines, and lists the Gateway’s own cron jobs on the Routines page, where you can turn them on or off, run them or delete them;
  • keeps its copy of your OpenClaw agents up to date, so they still show when the Gateway is down;
  • receives command approval requests, so they wait in Clawboo’s approvals even with no tab open;
  • records activity and token use from OpenClaw sessions, including ones Clawboo didn’t start, such as a channel message or one of an agent’s own cron jobs;
  • registers its MCP servers in the Gateway’s configuration, and passes your comments into running tasks.
The browser’s connection goes through the Clawboo server, which adds the saved Gateway token, so the server never sends that token to the browser. It carries your 1:1 chats with an OpenClaw agent and streams replies as they arrive. The Clawboo server forwards those replies without reading them, so an OpenClaw Boo Zero cannot hand work to a team from its own chat. Ask in the team’s chat instead, where the server runs it. See Boo Zero. When the Gateway is down, your OpenClaw agents still show (from Clawboo’s last copy) but can’t run. You can’t create an OpenClaw agent or edit its files: Create Boo makes a Clawboo Native agent instead, and says so. Deleting an OpenClaw agent is remembered and sent to the Gateway when it reconnects. If you also have agents on other runtimes, the dashboard loads as usual with a banner, “OpenClaw Gateway is offline”, and a Reconnect button.

How Clawboo connects

The server connects to the Gateway only once something needs it. A Gateway that a service manager starts on its first connection, such as a systemd socket unit on a small Linux machine, then stays asleep while nothing uses OpenClaw. Each of these is a need:
  • An OpenClaw agent exists in Clawboo and is not archived, or, while OpenClaw is still set up, the delete of one is still owed to the Gateway (it was deleted while the Gateway was down). An install with OpenClaw agents connects at every start, as before.
  • You open OpenClaw in Settings > Runtimes, or start the Gateway from Clawboo (setup, Reconnect, Start or Restart).
  • The dashboard opens its own Gateway connection. It does that only once the Gateway is in use, so loading the dashboard is not a need.
  • A routine for an OpenClaw agent falls due. The fire waits for the connection it starts, as it waits for any Gateway still coming up.
  • A request that needs the Gateway: creating an OpenClaw agent or a sync without a body, when a Gateway is set up, or a change to the Gateway address or token. A create or sync on a Gateway nothing used yet waits up to about 5 seconds for the connection, and answers 503 if it is not up by then; try it again a few seconds later.
Until then the server neither connects nor probes the Gateway’s port, and reports the Gateway as not in use rather than unreachable. So a new Clawboo next to an OpenClaw you already use shows none of its agents at first: the welcome screen says OpenClaw is set up and offers Open OpenClaw, which opens its row and brings them in. OpenClaw’s row reads Not in use, for a Gateway named in Clawboo’s settings as well as one set up on this machine. System Health passes the Gateway check as “not in use yet”. The dashboard loads with no Gateway connection and no offline banner, and Capabilities shows no warning for OpenClaw. The Gateway’s own cron jobs are not read, so GET /api/system/idle reports that source off with the reason not_in_use. Once something needs the Gateway, the server stays connected, and reconnects after a drop, until it stops. For the protocol detail, see Gateway and events.

Clawboo tools inside OpenClaw

Each time the server connects, Clawboo registers three of its MCP servers in the Gateway’s configuration, so every OpenClaw agent can use them. One Gateway configuration serves every OpenClaw agent, so Clawboo can’t tell which agent is calling, and each server is limited accordingly: TeamChat isn’t registered. OpenClaw agents take part in team chat through Clawboo, which posts each of their turns under the right name. Clawboo also adds sessions_spawn and sessions_yield to OpenClaw’s denied tools, so agents hand work to their team instead of spawning sub-agents of their own. An OpenClaw leader hands work on by calling OpenClaw’s sessions_send tool, or with a <delegate to="@Name">…</delegate> block in its reply; Clawboo turns either one into a board task.

Agent files

An OpenClaw agent’s files live in its workspace on the Gateway. Clawboo writes them when it creates the agent, and when you edit them on the agent’s page (Details, then the file tabs). Editing needs the Gateway running. Clawboo neither creates nor reads HEARTBEAT.md, USER.md or MEMORY.md; the file editor shows them only when they already have content. To schedule an OpenClaw agent’s own work, use OpenClaw’s cron jobs or a Clawboo Routine. OpenClaw’s agent workspace guide covers every file.

Comments on a running task

A comment you leave on a task an OpenClaw agent is working on joins its running turn at the next step, without stopping a tool that is running. If the run can’t take it, the comment waits for the agent’s next run. See Steering a running task.

Costs

OpenClaw’s Gateway reports no cost to Clawboo, so every OpenClaw figure you see is Clawboo’s estimate:
  • Budgets are charged an estimate for each OpenClaw turn in team chat, and for each OpenClaw Routine run, whether it succeeds, fails, times out or is stopped. It is worked out from the length of the prompt and the reply, at about four characters per token, priced at the agent’s model in openclaw.json. An agent whose model is an ollama/ one runs on your own Ollama, so it is charged nothing and its tasks read free.
  • Tokens Used shows the token counts OpenClaw records for each turn, priced from Clawboo’s rate table. A turn your own Ollama served is priced at $0.
  • A 1:1 chat with an OpenClaw agent shows in Tokens Used, but is not charged to budgets.
On a ChatGPT plan you pay a flat fee, so these figures are a budget guide, not your bill. Budgets only warn you unless you set a hard cap. See Budgets and spend.

Limits

  • No worktree, no checks. OpenClaw agents work in their own Gateway workspace. Clawboo never gives them a git worktree and never runs verification on their work; see How work is checked.
  • Global memory, no connectors from the graph. See Clawboo tools inside OpenClaw.
  • A Gateway on this computer. Set up OpenClaw configures and starts a local Gateway. Clawboo registers its MCP servers at a 127.0.0.1 address, which a Gateway on another machine can’t reach.
  • Routine runs stop after 10 minutes. An OpenClaw Routine run that hasn’t finished by then is stopped. Time the computer spends asleep does not count. CLAWBOO_ROUTINE_OPENCLAW_TIMEOUT_MS changes the limit.
  • The 2026.9 line. Clawboo installs openclaw@~2026.9, because it writes OpenClaw’s configuration in that line’s format.
  • Not on the runtimes API. /api/runtimes/openclaw/... answers 404. OpenClaw is managed through the System API.

Troubleshooting

What it means: OpenClaw hasn’t approved this device yet. Every connect is refused until you approve it once.Fix: click Approve this device on the card the setup shows. If you approve from a terminal instead (see Approve from a terminal instead), run Set up OpenClaw or Reconnect OpenClaw again afterwards to connect.
What it means: the approval went through, but the reconnect after it failed, or OpenClaw still reported the device as unapproved.Fix: click Retry. The setup runs again and shows a fresh approval card if the device still needs one.
The card shows what the approval step reported:
  • No pending device pairing requests found: OpenClaw had no request waiting, for example because the device is already approved. Close the panel with Cancel and run Set up OpenClaw again; it connects, or shows a fresh card.
  • OpenClaw not installed: Clawboo found no openclaw command, in its runtimes folder or on your PATH. Run the setup again, which installs it.
  • Failed to approve device: … or Failed to run openclaw: …: the OpenClaw command failed. Run the two terminal commands above to see OpenClaw’s own message.
What it means: the message names the Node.js found and the range OpenClaw needs (>=24.22.1 <25 || >=26.12.1), and says nothing was installed. OpenClaw runs on the Node.js Clawboo runs on, so the setup checks that version before it installs anything. “Too old” means below 24.22.1; “not one OpenClaw runs on” means Node 25, a Node 26 before 26.12.1, or a prerelease. The install stream’s error code is NODE_UNSUPPORTED. Earlier versions of Clawboo installed an older OpenClaw on such a Node.js without saying so.Fix: if Clawboo came with the desktop app, update the app, which brings its own Node.js. Otherwise start Clawboo with a supported Node.js. Node 24.22.1 or a newer Node 24 is the simplest. Stop Clawboo, switch to that Node.js in a terminal, and start Clawboo from it. A version manager such as nvm keeps global packages per Node.js, so install Clawboo again under the new one, or run npx clawboo@latest. Settings > System shows the version Clawboo runs on. Then click Retry.
What it means: npm failed while installing openclaw@~2026.9 into the runtimes folder. The message goes on with npm’s own reason, and the error code is npm’s, such as ETARGET or EACCES. Clawboo removed the new install’s folder, so an OpenClaw you already had is unchanged.Fix: fix what npm reports, such as a network or proxy problem, then click Retry.
What it means: Clawboo will not install into its runtimes folder, or run anything from it. The install stream’s error code is RUNTIMES_DIR_REFUSED, and the message says why: the folder is the data folder or the work folder, sits inside one or contains one, or it belongs to another user or others can write to it. Until that is fixed, Clawboo uses an openclaw on your PATH, if there is one.Fix: set CLAWBOO_RUNTIMES_DIR to a folder of its own and restart Clawboo, or, for a folder you do not own, make it yours and run chmod go-w on it. Then click Retry. See When Clawboo will not use it.
What it means: the Gateway exited with a reason (Gateway did not start: …), or never answered on its port within 60 seconds.Fix: read the Gateway’s log at ~/.clawboo/gateway.log, fix what it reports, then click Retry. OpenClaw’s troubleshooting guide and doctor command help with OpenClaw’s own errors.
What it means: OpenClaw asked for a data migration before it would start, and the openclaw doctor --fix that Clawboo ran failed.Fix: run openclaw doctor --fix in a terminal to see the whole report (~/clawboo-runtimes/bin/openclaw doctor --fix when Clawboo installed OpenClaw), then start the Gateway again with Retry or Reconnect OpenClaw. Do the same if the message says OpenClaw still asks for openclaw doctor --fix after Clawboo ran it.
What it means: OpenClaw’s default model isn’t pulled in your Ollama, or Ollama isn’t running.Fix: start Ollama, run the ollama pull command the panel shows, then click Check again.
What it means: the Gateway stopped or can’t be reached. Your OpenClaw agents are paused; agents on other runtimes keep working.Fix: click Reconnect on the banner, or Reconnect OpenClaw in Settings > Runtimes. If the Gateway rejected Clawboo’s token, the banner offers Restart Gateway instead, because the Gateway reads its token only when it starts.
What it means: the Gateway refused the command policy for a new agent, so Clawboo removed the agent rather than leave it unguarded. The reason follows the message.Fix: check that the Gateway is running and connected (Manage > Re-check), then create the agent again.
What it means: the request needs the Gateway (creating an OpenClaw agent, reading or writing its files), and Clawboo’s server isn’t connected to it. A create or a sync that finds a Gateway set up and not yet in use starts the connection and waits up to about 5 seconds for it, so this can also mean the Gateway is still starting.Fix: start the Gateway from Settings > Runtimes > OpenClaw, or wait a few seconds, then try again.

Check it works

1

Check the runtime

Open Settings > Runtimes. OpenClaw reads Connected, and under Manage the Gateway reads Running.
2

Talk to an OpenClaw agent

Open an OpenClaw agent from the agent column and send a short message in its chat. With no OpenClaw agent yet, Create Boo makes one while the Gateway is connected. You should see a reply stream in.
3

Put OpenClaw agents on a team

Deploy a team from the Marketplace. While the Gateway is connected, a marketplace team’s members default to OpenClaw; change any member in Customize team. In onboarding, members default to Clawboo Native instead, or to Codex if you signed in with ChatGPT.
  • The connections. The browser connects to /api/gateway/ws on the Clawboo server, which adds the token and signs the device before passing it on. The server’s own connection is an operator client (client id cli) that sends the Gateway host as its Origin and declares the tool-events and exec-approvals capabilities. Clawboo supports Gateway connect protocols 3 and 4.
  • Write budget. The Gateway allows three configuration writes per 60 seconds, so the MCP registration skips its write when nothing has changed.
  • configure-openclaw. The dashboard never calls POST /api/system/configure-openclaw. It writes a fresh openclaw.json and .env, replacing what is there, and makes a new Gateway token on every call, so use it only on a fresh OpenClaw. Set up OpenClaw uses POST /api/system/auto-configure-openclaw, which fills in only what is missing. See the System API.
  • The model list. The pickers read openclaw models list --all --json. OpenClaw 2026.9 refuses it when several agents are configured and none is named the owner, so Clawboo then asks again with --agent (the agent marked default, else main, else the first), until you configure a system agent (agents.defaults.systemAgent.agentId). See GET /api/system/models in the System API.
  • Model refs. Clawboo writes the ChatGPT model as openai-codex/<model>. openclaw doctor --fix later rewrites it to openai/<model> and turns on the plugins that form needs.
  • The install. POST /api/system/install-openclaw checks the Node.js version first, then runs npm into a new folder under the runtimes folder and switches to it on success. GET /api/system/status reports openclaw.source (clawboo or path) and, for Clawboo’s copy, openclaw.runsOnNode. See the System API.
  • The pin. openclaw@~2026.9 holds OpenClaw’s configuration format (the agent roster under agents.entries, and stricter config.patch rules), not the connect protocol.
  • More detail: Gateway and events and Agent sources.
Last modified on November 18, 2026