Curated with by@mohithkumar808

№ 1066GitHub

Muse remote-control bridge for Intel Macs

Since Muse for Mac ships only for Apple silicon, this small service lets Muse's cloud VM screenshot, click and type on an Intel Mac, compressing each 5K frame to about 150 KB and handling Retina coordinate scaling.

lilmuh/muse-intel-mac-bridgeREADME ↗

muse-intel-mac-bridge

让 Meta Muse(以及任何运行在 Linux VM 里的 AI agent)远程操作你的 Intel Mac。

官方 Muse for Mac 只提供 Apple 芯片(arm64)版本。在 Intel Mac 上打开会提示“此版本不能与此版本的 macOS 配合使用”,即使系统版本已经满足要求(macOS 14+)。本项目提供一个轻量替代方案:在 Mac 上运行一个小服务,Muse 通过它的云端 VM 截图、点击、打字,从而操作你的 Mac。

English summary at the bottom.

为什么不用 VNC?

直接用 VNC 截图,5K 屏幕的一帧就有几十 MB,传输很慢,容易超时。本项目在 Mac 本地完成截图、缩放和 JPEG 压缩,每帧约 100–200 KB,并自动处理坐标换算。

VNC 截图 muse-intel-mac-bridge
单帧大小(5K 屏) 几十 MB ~150 KB
Retina 坐标换算 agent 自己算,容易点偏 服务自动完成
输入中文 麻烦 支持(自动走剪贴板)
需要开放的端口 5900 无(通过 Tailscale Funnel)

工作原理

手机上的 Muse ──► Muse 云端 Linux VM ──HTTPS──► Tailscale Funnel ──► 你的 Mac
                   (运行 mab.py 客户端)                                (mac_agent_server.py)
  • agent 看到的永远是 1280 宽的截图,坐标也用这张图的像素坐标。
  • 服务把坐标换算成 macOS 逻辑坐标(Retina 下截图像素是逻辑点的 2 倍)。
  • 服务默认只监听 127.0.0.1,由 Tailscale Funnel 提供 HTTPS 访问,所有请求都需要 token。

系统要求

  • macOS 12 或更高版本,Intel 或 Apple 芯片均可
  • Python 3.9+(xcode-select --install 会附带)
  • Tailscale(用于把服务暴露给云端的 agent)

快速开始

1. 下载并启动

git clone https://github.com/<你的GitHub用户名>/muse-intel-mac-bridge.git
cd muse-intel-mac-bridge
chmod +x start.sh
./start.sh

首次运行会自动创建虚拟环境、安装依赖,并生成 token(保存在 .env)。

2. 授予权限

打开「系统设置 → 隐私与安全性」,给你使用的终端(Terminal / iTerm)开启:

  • 屏幕录制:用于截图。没开的话截图会是黑屏或只有桌面壁纸。
  • 辅助功能:用于控制鼠标和键盘。

开启后需要完全退出并重新打开终端,再运行 ./start.sh。

3. 本地测试

另开一个终端:

source .env
curl -H "Authorization: Bearer $AGENT_TOKEN" http://127.0.0.1:8765/screenshot -o s.jpg && open s.jpg
curl -H "Authorization: Bearer $AGENT_TOKEN" http://127.0.0.1:8765/info

图片大约 100–200 KB、画面正常,就说明服务工作正常。

4. 通过 Tailscale Funnel 暴露

  1. 安装并登录 Tailscale:brew install --cask tailscale
  2. 在 Tailscale 管理后台 开启 HTTPS,并在 Access Controls 中允许 Funnel
  3. 按 Ctrl+C 停掉服务,改用 ./start.sh --funnel 启动

终端会显示形如 https://你的mac名.xxx.ts.net 的公网地址。

5. 连接 Muse

打开 docs/muse-prompt.md,把里面的说明发给 Muse,替换好地址和 token。先让它运行:

python3 mab.py info

返回 JSON 就说明连通了。

客户端 mab.py

在 agent 的 VM 里运行,只依赖 Python 标准库:

export MAB_URL=https://你的mac名.xxx.ts.net
export MAB_TOKEN=你的token

python3 mab.py screenshot -o screen.jpg     # 截图
python3 mab.py click 640 400                # 单击(--double 双击,--right 右键)
python3 mab.py type "你好 hello"
Muse remote-control bridge for Intel Macs on github.com

Also filed under Errands & personal agent

See all →
  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. 1015

    Spectrum bill negotiated from $75 to $40★

    Just used Muse to call spectrum and negotiate my bill from $75 to $40 automatically. This feels like defecting but wowee

    @LinkofSunshine

    X post

    Errands & personal agent

  3. 0991

    Two credit collections removed via dispute★

    GET THE FUCK OUTTA HERE! 🤯🤯🤯 @Muse just removed 2 collections off my credit within 1 hour of submitting the dispute!!!! Submitted at 7:09pm Both accounts deleted by 8:25pm 😳😳🤩 @alexandr_wang, @MattPRD, thank you so much! It’s insane how good Muse is, you ask it to do https

    @ChrisUniverse

    X post

    Errands & personal agent

  4. 0990

    Socks, groceries, cleaners and dinner in 24 hours★

    It’s funny, Meta went from having my Instagram and WhatsApp data to now having access to my email, calendar, DoorDash, Amazon and pretty much everything. In the last 24 hours, it bought me socks, ordered my Whole Foods groceries, booked a cleaning service and got me a burger for

    @nicbstme

    X post

    Errands & personal agent

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. 1086

    Self-Healing Agent VM

    A self-healing watchdog pattern for AI agent VMs: byte-exact restore caches in persistent storage, sentinel probes, no-clobber atomic restores, and verified heals. When the VM's root filesystem is rebuilt with pieces missing (Python stdlib, timezone data, Node), the watchdog restores them in minutes and reports only repairs and failures. Includes an AGENTS.md so any agent can set it up.

    @TMTrevisan

    GitHub

    Agents & automation

Curator picks

  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. 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