Agent comparisons

Meta Muse vs OpenClaw: SOUL.md, WhatsApp, and Model Choice

Choose Meta Muse if you want a personal agent that works the minute you sign in, with Meta running the machine, the model, the credential vault, and a second agent that screens what goes out. Choose OpenClaw if you want to pick the model, edit the files that define the agent, and put it on your own WhatsApp, Telegram, or Slack. Muse was modeled on OpenClaw, so the ideas overlap. 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

By Lobsterland · Reviewed September 28, 2026

We host OpenClaw and Hermes. This comparison uses Meta's announcements, published reporting, and our managed OpenClaw feature set. We have not run a hands-on Muse test. Muse is three weeks old, and its features and prices are still moving.

Two names first. Muse here is the personal agent Meta launched on September 8, 2026. It is not Muse Spark, the model behind it, or Muse Code, Meta's terminal coding agent. OpenClaw is the open-source agent runtime. It is not OpenClaw Launch, which is a hosting company with its own Muse comparison page.

Is Meta Muse based on OpenClaw?

In design, yes. In code, Meta says no. By September 22, users had noticed that Muse carries a SOUL.md file, the plain-text file OpenClaw uses for an agent's personality, values, and boundaries, and that its contents were nearly identical to OpenClaw's. Asked about it, Nat Friedman, head of product at Meta Superintelligence Labs, told TechCrunch on September 22, 2026 that Muse was "definitely heavily inspired as a product by OpenClaw" but "built from scratch," and that the team "thought that Peter [Steinberger, OpenClaw's creator] got those things exactly right." The Next Web reported the same exchange.

So the useful question is not whether Muse copied OpenClaw. Meta has said it did, at the level of product ideas. The useful question is what changes when the same design is run by Meta instead of by you.

Meta Muse vs OpenClaw: what actually differs?

The Muse column follows Meta's launch announcement and TechCrunch's launch coverage. The OpenClaw column describes what you can operate through managed OpenClaw hosting on Lobsterland.

What does SOUL.md do, and who can edit it?

In OpenClaw, SOUL.md is one file in a small set that together define the agent. SOUL.md holds voice, temperament, and the lines it should not cross. AGENTS.md is the operating contract: priorities, workflow, quality bar. USER.md holds your preferences. HEARTBEAT.md says what to check on each background pass. MEMORY.md keeps durable facts, and dated notes under memory/ hold the day-to-day. Our guide to OpenClaw's memory files walks through each one.

The reason the Muse story landed is that these are ordinary files. When the agent does something you did not want, you can open the file that shaped the behavior and change a sentence. On a managed instance the workspace is browsable and editable from the dashboard, so there is no SSH session involved. You can see what the agent has written into memory and delete what it should not keep.

Muse keeps the idea and hides the files. Meta describes customization as the agent's name, avatar, look, and settings. Memory is something you manage by telling Muse to forget specific things. That is the right trade for most consumers: a file that controls behavior is also a file you can break. If you want a well-behaved agent without ever reading its instructions, Muse's approach is the easier one to live with.

How does each one work in WhatsApp?

Both reach you in WhatsApp, and that is where the two designs differ most in practice.

Muse is a Meta agent that you message inside WhatsApp. The contact belongs to Meta, and the agent lives on Meta's side of the conversation.

OpenClaw links to a WhatsApp account you control. On Lobsterland you choose personal number mode, where you chat with the agent in your own self-chat, or dedicated number mode, where the agent has its own number and people message it. You set a DM policy (pairing, allowlist, open, or disabled) and an allowlist of numbers and groups. Then you scan a QR code from WhatsApp's Linked Devices screen. Our WhatsApp setup guide has each step. The consequence is that the policy on who may give your agent instructions is yours to set, and a stranger who finds the number gets nothing unless you allow it.

Which one does work without being asked?

Muse's pitch leans on proactivity. Meta says it remembers what matters to you, so it can make suggestions unprompted and act on details you mentioned once. That is a product behavior Meta tunes for you.

OpenClaw has two mechanisms you configure yourself. The heartbeat wakes the agent on a fixed cadence, 30 minutes by default and adjustable per instance in Lobsterland's settings, to work through whatever HEARTBEAT.md tells it to check. Cron jobs run specific tasks on a schedule. See the OpenClaw cron guide for how those are set up.

Running proactive agents for customers taught us that the hard part is not the timer. It is where the message ends up. A heartbeat that lands in the middle of your Telegram thread becomes the "previous message" in your next conversation, so managed instances run heartbeat turns in an isolated session. Since September 25, 2026, we also route a heartbeat's delivery to the channel and thread you last used, instead of OpenClaw's default owner direct message. With that default, the result of a long-running task started in a Telegram group could arrive in the owner's private chat instead of the group. Muse handles this kind of routing for you. With OpenClaw, it is a setting, and on Lobsterland the defaults are already chosen.

Where is Muse ahead of OpenClaw?

Trust machinery for money and email. Muse runs a second agent, the Sentinel, on the same VM, and Meta says nothing Muse does reaches the internet unless the Sentinel approves it. Passwords and cards go into storage Muse can use but not see, and checkout goes through Stripe Link with a one-time card and Link's purchase protections. Muse asks before sending email or buying anything. OpenClaw has no built-in equivalent to a Sentinel. On an OpenClaw instance your controls are narrower grants, allowlists, and reviewing what the agent is allowed to do. Our security overview spells out where the managed boundary stops.

Connectors on day one. At launch Meta listed email, calendar, payments, health, smart-home, dining, shopping, music, and events connectors. On September 23, 2026 it added retail partners including Best Buy, Gap, Sephora, Walmart, and Wayfair, plus GitHub, Granola, and Notion connectors, according to TechCrunch. OpenClaw reaches services through skills, tools, and an optional hosted browser that you configure one at a time.

Zero setup and a free tier. You sign in and it works. There is no instance, provider key, or channel to configure. Meta also previewed desktop control, a Muse email address, a video avatar, and glasses support. All four were announced as coming, not shipped. Judge Muse on what it does today.

Is OpenClaw cheaper than Muse?

For light personal use, no. Muse has a free tier, and Meta has said it expects most people to stay on it. It plans to earn money from small transaction fees rather than subscriptions. At launch Meta listed a Power plan at $20 per month and a Maximum plan at $100 per month. Muse was US-only at launch.

As of September 28, 2026, managed OpenClaw on Lobsterland starts at $6.90 per month. Model usage is billed by the provider you connect, or counted against a Claude or ChatGPT subscription login if you use one. Every plan starts with a 7-day trial, and a card is required up front. For heavy use, compare Muse's plan against $6.90 plus your model bill, and the answer depends on how many tokens your work burns. The pricing page keeps hosting and model access separate so you can estimate it.

How do you try OpenClaw without a server?

1. Create a Lobsterland account and choose OpenClaw for a new instance.
2. Connect a model provider, or a supported Claude or ChatGPT login.
3. Open the workspace and write three lines into SOUL.md and USER.md: who the agent is, what it must never do, and how you like answers.
4. Test in built-in chat, then link WhatsApp, Telegram, or Slack. Add a heartbeat checklist or a cron job once one task works reliably.

A fair first test is something Muse would also do: summarize the week's plans from a message you forward, and list what is still undecided. If it misses something, change the instruction file and try again. That edit is the step Muse does not offer.

If you want a personal agent with readable memory but do not need WhatsApp or cron, read Meta Muse vs Hermes Agent. For another big-vendor comparison, see Grok Bot vs OpenClaw. Add agents to the same instance with multi-agent routing once one agent is doing its job.

Frequently asked questions

Is Meta Muse based on OpenClaw?

Meta says Muse was built from scratch but was heavily inspired by OpenClaw. Users found that Muse carries a SOUL.md file nearly identical to OpenClaw's, and Meta's Nat Friedman said the team thought OpenClaw's creator got those things exactly right. Muse does not run the OpenClaw runtime.

Can I edit Muse's SOUL.md the way I can in OpenClaw?

Meta's materials describe customizing Muse's name, avatar, look, and settings, not editing its instruction files. In OpenClaw, SOUL.md, AGENTS.md, USER.md, MEMORY.md and the other workspace files are plain files you can open and change; on Lobsterland they are editable from the dashboard.

Do Muse and OpenClaw both work in WhatsApp?

Yes, differently. Muse is a Meta agent you message inside WhatsApp. OpenClaw links to a WhatsApp account you control, personal or dedicated number, through WhatsApp's Linked Devices QR flow, with a DM policy and allowlist deciding who can reach it.

Is OpenClaw cheaper than Muse?

Not for light use: Muse has a free tier. At launch Meta listed paid plans at $20 and $100 per month. Managed OpenClaw on Lobsterland starts at $6.90 per month plus your model provider's bill, so heavy use depends on your model spend.