Agent comparisons
OpenAI Dots vs OpenClaw: Always-On Agents, Controls, and Cost
Choose OpenAI Dots if you are on ChatGPT Pro or Business Premium, work in Slack or Microsoft Teams, and want OpenAI to run the agent with its own computer, thousands of app connectors, and approval rules. Choose OpenClaw if you want to pick the model, edit the files that drive the agent, decide how often it wakes up, run several agents, and reach it on WhatsApp, Telegram, or Slack. Both are agents that keep working after you close the chat. The difference is who holds the controls. Lobsterland runs OpenClaw as a managed instance, so the open option does not mean running a server.
Deploy OpenClaw See hosting costs
First, the names. Dots is OpenAI's always-on personal agent, launched from ChatGPT or Codex and powered by GPT-6 Astra. It is not the Agents SDK for developers. OpenClaw is the open-source agent runtime. It is not OpenClaw Launch or any other hosting company that uses the name.
Is OpenAI Dots built on OpenClaw?
Nothing in the launch coverage says it runs OpenClaw code. The connection is the idea and the person. The Register wrote on September 29, 2026 that Dots follows OpenClaw, "whose founder Peter Steinberger joined OpenAI." OpenClaw made popular the agent that stays on, lives in the messaging apps you already use, and does work between conversations. Dots puts that idea inside ChatGPT.
The main difference is openness. Dots runs on OpenAI's model, on OpenAI's computers, under rules OpenAI designed. OpenClaw leaves those parts open: which model answers, which instruction files it reads, how often it wakes up, and which channels it listens on. That openness is useful when you want to change something. It is work when you would rather not decide.
OpenAI Dots vs OpenClaw: what actually differs?
| Decision | OpenAI Dots | Managed OpenClaw |
|---|---|---|
| Who runs it | OpenAI, inside your ChatGPT plan | Lobsterland, as an isolated instance per customer; the runtime is open source |
| Model | GPT-6 Astra | A provider you connect: OpenAI, Anthropic, Google, OpenRouter, and others |
| What drives behavior | Your instructions, Custom Rules, and what it learns over time | SOUL.md, AGENTS.md, USER.md, HEARTBEAT.md and memory files you can read and edit |
| Proactive work | Pursues goals in the background; read-only research while you are inactive | Heartbeat every 30 minutes by default, plus cron jobs at exact times |
| Several agents | One dot included; more dots and teams of dots described as coming | Several agents on one instance, routed per person, group, or channel |
| Where you talk | ChatGPT, Slack, Microsoft Teams; texting later | Built-in chat, WhatsApp, Telegram, Slack, OpenClaw mobile app |
| Apps and browsing | Its own cloud computer and browser; 4,000+ apps through plugins | Its own instance, an optional Hosted Browser, and skills |
| Before a risky action | Allow, require approval, or block, per action | Channel allowlists decide who can instruct it; no per-action prompt |
| Price | First dot included in Pro and Business Premium | Hosting from $6.90 per month plus your model bill |
The Dots column follows TechCrunch and VentureBeat, both from September 29, 2026. The OpenClaw column is what you can operate through managed OpenClaw hosting on Lobsterland.
How does each one work without being asked?
OpenAI describes a dot as pursuing the goals you give it, continuously, in the background. VentureBeat adds that while you are inactive, its proactive research is read-only: it can look things up, but it cannot send messages, change app content, or drive a browser. You do not set a schedule. The product decides when to act on a goal.
OpenClaw has two mechanisms, and you configure both. The heartbeat wakes the agent on a fixed interval and has it work through HEARTBEAT.md, a plain checklist in its workspace. Cron jobs run a specific task at a specific time, such as a 7:30 summary of overnight alerts. Our OpenClaw cron guide covers the scheduling side.
To get a dot-style standing goal, write it down. For example, add this line to HEARTBEAT.md: "Check the error summary the monitoring bot posts in this Slack channel. If a new error class appears, reply in the thread with what changed and one next step. Otherwise stay silent." The agent can only watch what it can see, so the checklist has to point it at a channel, a page, or a feed it can actually reach.
Dots does not show you the cost of this, but OpenClaw does. On a managed instance the heartbeat runs every 30 minutes by default, which is 48 wake-ups a day. Each one is a model turn billed by the provider you connected. You can set a longer interval, such as 2h, or 0m to turn the heartbeat off and use cron for anything tied to a time. Heartbeat turns run in an isolated session. Since September 25, 2026, a heartbeat's message goes to the channel and thread you last used. We made that change after a long task started in a group chat delivered its result to the owner's private messages instead.
One dot, or several agents?
At launch, the first dot is included in Pro and Business Premium. OpenAI says you will be able to add more dots later for a flat monthly fee, and that "over time, we envision teams of Dots working together on your behalf." For companies, OpenAI is piloting specialist dots with their own identity, credentials, and a defined business responsibility, such as invoice processing or customer support. Those pilots are run with enterprises, and OpenAI has not published their pricing.
OpenClaw can do the routing half of that today. One instance can run several agents. Each has its own workspace files, name, and model. A binding sends a specific conversation to a specific agent: one person's Telegram or Slack direct messages, a Telegram group, or a Slack channel. A small team could run a support agent in the #support channel, a finance agent in #invoices, and a personal agent for each person's DMs, all on one instance. Multi-agent routing is set up in the dashboard, without editing config files.
The trade-off is that you design the split and write each agent's files. OpenClaw bindings decide which agent answers a conversation. They are not a manager that hands work between agents on its own.
Where do you talk to it?
A dot is reachable in ChatGPT on the web and mobile, in Slack, and in Microsoft Teams. It keeps context across them. Texting is announced for a later release. Reports disagree on whether phone calls work at launch, so check your account before you plan around voice.
Managed OpenClaw offers built-in chat in the dashboard, the official OpenClaw mobile app, WhatsApp, Telegram, and Slack. WhatsApp is what Dots does not have. You can talk to the agent in your own self-chat, or give it a dedicated number of its own, and a DM policy plus an allowlist decides who else can reach it. The WhatsApp setup guide covers each step.
Lobsterland has no Microsoft Teams connection, and no phone or SMS. If your company works in Teams, that one fact may decide the question for you.
What stops it before a risky action?
OpenAI built Dots around per-action policy. VentureBeat describes Custom Rules that allow an action, require approval, or block it. Activity View lets you inspect background work and step in. An auto-review checks actions against your instructions, and sensitive steps such as password changes stay with you. We have not tested those controls.
Managed OpenClaw works differently. Elevated tools, the ones that run commands, run in full mode by default. They can be triggered by the people your channel settings let in, and they do not pause for a confirmation on each action. So the main control is who can instruct the agent, not an approval screen for each step. That makes "allow anyone" a serious setting. If you open a WhatsApp number to everyone, everyone who messages it can trigger those tools. You can write "draft, do not send" into AGENTS.md, and a good model will follow it. That is an instruction, not an enforced rule.
In practice: keep allowlists tight, have the agent report in a channel you read, and don't sign the Hosted Browser into accounts where a mistake would be costly. If a workflow must stop for approval before every send, Dots is the better fit today. Our security overview explains where the managed boundary stops.
Where is Dots ahead of OpenClaw?
Approval controls. Per-action rules, an activity view, and an auto-review are built in. On OpenClaw, you would have to design those yourself.
Its own computer and connectors. A dot has a cloud computer and browser of its own, plus more than 4,000 apps through OpenAI's plugins. OpenClaw works through a Hosted Browser you sign into and the skills you install.
Teams, and no setup. Dots is in Microsoft Teams, and it starts from the plan you already pay for. There is no model to choose, no HEARTBEAT.md to write, and no interval to tune.
Enterprise identity. Specialist dots get their own organizational identity and credentials, and OpenAI engineers are working with pilot customers to set them up. OpenClaw has no equivalent managed offering.
What do access and cost look like?
As reported on September 29, 2026, the first dot is included at no extra charge in ChatGPT Pro and Business Premium, in eligible markets. Enterprise, Edu, and Healthcare workspaces can try a beta once an administrator enables it. PYMNTS reported that Pro access excludes the European Economic Area, Switzerland, and the UK. According to VentureBeat, OpenAI "has not disclosed" the allowance for intensive work or the cost of additional dots. OpenAI also announced a $500-a-month ChatGPT tier that day. That is a plan price, not the price of a dot.
Managed OpenClaw on Lobsterland starts at $6.90 per month. Model usage is billed by the provider you connect, or counted against a ChatGPT or Claude subscription if you log in with one. Using your ChatGPT subscription with hosted OpenClaw explains how that login works. It powers OpenClaw with OpenAI models, and it does not bring your dot along. Your heartbeat interval is one of the settings that changes your model bill. Every plan starts with a 7-day trial, and a card is required up front. The pricing page shows hosting and model access separately, so you can estimate both. If you already pay for Pro, Dots may cost you nothing extra. OpenClaw would then be an added cost you pay for control.
How do you try OpenClaw without a server?
- Create a Lobsterland account and choose OpenClaw for a new instance.
- Connect a model provider, or a supported ChatGPT or Claude login.
- Write USER.md (who you are, how you like answers) and three lines of HEARTBEAT.md: what to check, when to message you, and when to stay quiet. Our guide to OpenClaw's memory files explains each file.
- Connect Slack, Telegram, or WhatsApp, set the heartbeat to an interval you can live with, such as
2h, and watch a day of results before adding cron jobs or a second agent.
A fair first test is the one OpenAI leads with: an alert to investigate. Point the heartbeat at a channel where alerts land. Ask it to say what changed, quote the evidence, and propose one next step without acting on it. If it misses an alert or repeats itself, change the checklist and run it again. Being able to make that edit is the main thing OpenClaw gives you.
If you only need chat, Telegram or Slack, and a runtime with readable skills, OpenAI Dots vs Hermes Agent covers that narrower choice. For Meta's take on the same idea, see Meta Muse vs OpenClaw. If you are weighing plain ChatGPT rather than Dots, read ChatGPT vs OpenClaw.
Frequently asked questions
Is OpenAI Dots built on OpenClaw?
Nothing in the launch coverage says Dots runs OpenClaw code. The Register described Dots as following OpenClaw, whose creator Peter Steinberger joined OpenAI. OpenClaw itself is still an open-source runtime you can run yourself or on a managed host.
Can I use my ChatGPT subscription with OpenClaw?
Yes, as the model. Managed OpenClaw supports ChatGPT/Codex login, subject to your plan's limits. That gives OpenClaw access to OpenAI models. It does not bring your dot, its cloud computer, or its app connectors.
Can OpenClaw run several agents like a team of Dots?
One managed instance can run several agents today, each with its own workspace files, name, and model. Bindings send a person's Telegram or Slack messages, or a group or channel, to a chosen agent. OpenAI describes teams of Dots as a future direction.
Does OpenClaw work in Microsoft Teams or over the phone?
Not on Lobsterland. Managed OpenClaw connects to built-in chat, WhatsApp, Telegram, Slack, and the OpenClaw mobile app. There is no Teams connection, phone calling, or SMS.