Curated with by@mohithkumar808

№ 0126GitHub

TerMuse: watch your Muse agent's machine

TerMuse shows the live terminal and an interactive browser of the machine a Muse agent is working on, side by side, so the user can watch and type or click in the same session.

jjakemaness/termuseREADME ↗

TerMuse

See the computer your Muse agent is actually using.

Your Spark agent on muse.ai works on a real machine — a
real shell, a real browser, real files. You normally only see what it
chooses to tell you about that machine in chat.

TerMuse gives you the machine itself, in one page: your agent's live
terminal on the left, a fully interactive browser on the right.
Every
command it runs, every page it opens. And you're not just watching — you
can type into that terminal and click in that browser yourself, at any
moment, in the same session your agent is using.

TerMuse: the agent's live terminal on the left, its localhost app rendered
and clickable on the right

Above: the agent just ran npm install -g hermes-web-ui and started it on
localhost:8648 — you can read that happening in the left pane. The right
pane is that same localhost app, rendered and fully clickable, on a machine
your browser has no route to. Follow mode is on, and the divider is
draggable (40/60, 50/50, 60/40).

Why this exists

Two things are normally impossible from your side of the screen:

  • You can't see the agent's shell. You get a summary of what it did.
    TerMuse gives you the actual pane, live, and lets you type in it.
  • You can't open the agent's localhost. When your agent builds a web
    app and runs it on localhost:3000, that server exists only on its
    machine. Your browser has no route to it. TerMuse renders it anyway —
    and lets you click around in it.

That second one is the whole trick, and it's why this repo exists instead
of a browser extension.

Setup

Two steps. Your agent builds the view; you run one command inside it.

Step 1 — paste the prompt to your agent

  1. Open PROMPT.md.

  2. Copy everything below the --- divider.

  3. Paste it to your Muse Spark as a single message, with a link to this repo:

    Here's the repo: https://github.com/jjakemaness/termuse

    (then the pasted prompt)

  4. Wait a few minutes. Your agent builds the split view, tests every
    control, and hands you a private link with its results.

Open the link. You should have a terminal on the left and a browser on the
right, and you should be able to type in one and click in the other.

Step 2 — run the installer in your new terminal

Only your agent can build the view. Everything af

TerMuse: watch your Muse agent's machine on github.com

Also filed under Agents & automation

See all →
  1. 1057

    Muse Mail: your agent gets an email address★

    MUSE FEATURE ALERT: y'all have been asking for this one. your @muse is getting its own email address. add it to a thread or forward it stuff and it’ll handle it for you. muse mail!

    @alexandr_wang

    X post

    Agents & automation

  2. 1054

    Kevin Roose gives his Muse $100 and a Kalshi account★

    gave my Muse $100 and a kalshi account, let's see how frontier this thing is

    @kevinroose

    X post

    Agents & automation

  3. 1007

    Plumbing company run by a Muse agent★

    I still can’t believe I can run my plumbing company with an agent so easily. I send this message to my Muse agent while in bed at 6am. And it: updates my job board, texts customer, updates office manager who arrives at 8am in slack Notifies technician

    @HouseHackerJon

    X post

    Agents & automation

  4. 0881

    Every Muse user gets a cloud computer★

    I’ve seen a couple of posts about this so wanted to demystify. Today, every Muse user gets a free computer in the cloud. It's a real computer, and we’ve designed the security architecture of the Muse Secure VM carefully so you and your Muse can do almost anything you could with a

    @dps

    X post

    Agents & automation

More GitHub

See all →
  1. 1091

    RedMuse

    Muse-native pentesting skill pack for Muse.ai. 13 skills, 4 scan modes (quick, standard, deep, diff), gate-first, localhost vulnerable app plus passive scans only, no active probes on live sites without a separate yes. Strix-inspired with original writing. Proven on localhost (IDOR, XSS, open redirect) and on live targets with anonymized totals: 0 critical, 2 high, 4 medium, 8 low, 14 info. MIT.

    Anonymous

    GitHub

    Coding & dev tools

  2. 1089

    Gig Driver Profit Checker — real delivery profit in minutes

    A working mobile-friendly web app built by the Meta Muse personal agent from a real courier's detailed requirements. It compares DoorDash/Uber Eats delivery offers after total miles (including empty return), waiting time, all-in vehicle costs and tolls. The surprising demo: a $9 offer can yield $19.08 net per hour while a $20 offer only yields $16.09 under stated assumptions. Muse created the standalone offline HTML and logic tests (49/49 self-reported); I downloaded it, independently verified actual browser inputs/outputs, published the source and proof screenshot to GitHub, and deployed a no-signup live demo. Live app: https://boyhoangxattpt2-blip.github.io/gig-driver-profit-checker/ . GitHub README includes exact math, source code, build story, and reproducible prompt.

    Anonymous

    GitHub

    Apps & websites

  3. 1087

    Zouroboros Workshop

    Muse is your personal assistant. Zouroboros Workshop is the workshop behind it. Workshop is an MCP service that runs on a private, single-tenant VPS provisioned for each customer. From a normal Muse conversation, a user can dispatch real software work to a coordinated team of seven AI coding executors — Claude Code, Codex, Gemini, OpenCode, Kimi, Hermes, and Pi — routed by health and capability, with automatic fallback when one executor is unavailable. Three things make it different from a single-vendor hosted builder. First, it runs on the subscriptions the user already pays for: there are no Workshop model credits and no second meter. Second, its memory is shared across every executor and survives across sessions, so a decision recorded by one tool is retrieved by another in a later Muse conversation — memory that compounds instead of resetting. Third, work is verified before it is delivered: builds run through a factory lane with deterministic review, and swarm results return with per-task evidence, not just an agent's claim that it is done. The customer-facing promise is simple: turn your existing AI tools into a workshop that delivers tested, reviewed work — a finished pull request, not a wall of code in chat.

    @Xmarlandoj

    GitHub

    Connectors & MCP

  4. 1082

    muse-file-bridge

    An open-source file bridge that gives Muse real read/write access to your Windows PC: a lightweight local Python server (Bearer-token auth, directory whitelist, path-traversal protection) exposed via Cloudflare Tunnel, so the agent works with your actual files instead of chat attachments.

    Anonymous

    GitHub

    Coding & dev tools

Curator picks

  1. 1046

    Medical bills audited line by line, $4,000 saved★

    Got Muse logged in to my medical provider’s portal, he pulled the itemized bills, and questioned every line. So far he’s found several times I’d been double billed, asked for some discounts and has saved me over $4,000. If your moat is bureaucracy, you’re cooked.

    @Ryan_Holdaway

    X post

    Errands & personal agent

  2. 1042

    GitHub connector for Muse★

    GitHub 🤝 @Muse A new way to connect your GitHub account to review PRs, catch up on issues and notifications, and leave comments without switching tabs.

    @github

    X post

    Connectors & MCP

Want more AI builds?artificialbuilds.com