Superagent
A persistent Mac workspace that puts your coding agent beside a controllable browser, project files, and an iOS Simulator.
- Source repo
- pungme/superagent-desktop
- Stars
- ★ 36
- Last updated
- 4d ago
- License
- MIT
- Primary language
- TypeScript
- FA score
- 62/100 · Some gaps
At a glance
- How it runs
- Works with
- Portable with changesCodex · Claude Code
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- A Mac-based web developer using Claude Code or Codex who wants to watch code changes and the resulting local page update in the same window.
- Not a fit if
- Users on Intel Macs, Windows, or Linux — only Apple Silicon is supported
- Teams unwilling to let automation act inside their logged-in browser sessions
- Source review
- 62/100 · Some gaps
What does this agent do, and when should you use it?
Superagent is an Electron, TypeScript, and React desktop application for Apple Silicon Macs that gives Claude Code or Codex a persistent visual workspace, with the agent selectable per chat. A project conversation can sit beside a real browser, the file tree, and an optional streamed iOS Simulator, allowing the agent to modify software and inspect the running result in one window. Each new conversation can receive a private project checkout and branch on its first message; Keep folds the result back as one change, while Throw away removes it. Conversations, panes, open files, and active state survive restarts, while scheduled Routines, project boards, PDF annotation, local speech transcription, and context usage are built into the desktop interface. Core execution stays on the Mac and uses the user's existing agent subscription without a separate API key; optional phone access connects the companion iOS app through an end-to-end encrypted blind relay.
After the user submits a task in a project chat, Superagent starts the selected coding agent and lets it read and edit project files, run commands, start a local development server, and update code on the conversation's isolated branch. The agent can operate Superagent's own browser pane by opening pages, clicking, typing, and reading results; automation does not enter the user's personal browser. For iOS work, tools including sim_list_devices, sim_boot, sim_screenshot, sim_open_url, and sim_install_and_launch call xcrun simctl, while an optional stream displays the Simulator inside the application; this workflow requires Xcode. A completed checkout can be folded into the project as one change with Keep or deleted with Throw away. Routines repeat browser checks on natural-language schedules, and the file viewer opens source, Markdown, images, and PDFs, including in-place PDF annotation. Once a phone is paired, the Mac and iPhone exchange conversations, pages, prompts, and approvals through superagent-relay using end-to-end encryption with a per-device key; the relay is described as unable to read or store the plaintext.
- A Mac-based web developer using Claude Code or Codex who wants to watch code changes and the resulting local page update in the same window.
- A developer who needs an agent to click, type, and read within authenticated websites while keeping automation isolated from their personal browser.
- An iPhone application engineer with Xcode installed who wants the agent to build, launch, inspect, and iterate against an iOS Simulator.
- A developer exploring several features or fixes concurrently who wants each conversation isolated in its own checkout and branch.
- A user who needs to answer agent questions or approve actions away from the desk through the companion iPhone or iPad application.
- An individual developer who wants scheduled browser checks expressed as natural-language Routines, such as checking a site every hour.
How do you install or deploy this agent?
The prebuilt application requires an Apple Silicon Mac. Download SuperAgent.dmg from the releases page, open the disk image, and install the signed and notarized application. For Claude Code chats, install Claude Code and sign in first; the product also explicitly advertises per-chat Codex support, although the supplied material does not give a separate Codex installation command. Install Xcode only if you need the iOS Simulator. For remote phone access, install the companion application through TestFlight or build pungme/superagent-ios from source, then pair it under Settings → Phone. To run the desktop application from source, execute cd app, npm install, and npm run dev. Run unit tests with npm test; npm run test:e2e builds the application and drives it with Playwright.
How do you use this agent?
Add a project, create a conversation, and describe the coding task in the first message; Superagent then creates that conversation's private project copy and branch. Select Claude Code or Codex for the chat and choose the corresponding model and permission mode. Ask mode requests approval before the agent acts, either on the Mac or on a paired phone. Point the browser pane at a local development server or live site; the agent can start the server and interact with the visible page. For iOS projects, ask it to build and launch in Simulator. Use the scissors control on the browser or Simulator, or press ⌘⇧S, to crop a region into the message. When the work is ready, choose Keep to fold it back as one change, or Throw away to delete the conversation's working copy. Pair a phone under Settings → Phone for remote interaction, and describe a timed browser task in plain language to create a Routine.
What are this agent's strengths and limitations?
- The browser is visible and user-takeover-friendly rather than a hidden automation instance, while still preserving its own authenticated session.
- Per-conversation checkouts and branches isolate concurrent experiments, with explicit Keep and Throw away outcomes.
- Coding chat, live diffs, files, browser content, PDFs, and an iOS Simulator share one restorable desktop workspace.
- Local execution reuses an existing Claude Code or Codex subscription and does not require a separate model API key.
- Phone communication uses per-device end-to-end encryption, and users may run their own
superagent-relay.
- The desktop application explicitly requires an Apple Silicon Mac; no Intel Mac, Windows, or Linux build is documented.
- Simulator support requires Xcode, and live framebuffer capture relies on a native helper and private framework path with a slower screenshot fallback if it stops working.
- The browser can act within real authenticated sessions. Although automation is confined to Superagent's pane, adopters must still assess account permissions and automation risk.
- Remote phone access adds a companion application and relay connection; installations that do not pair a phone do not receive that capability.
- The supplied documentation is inconsistent about setup scope: the product text says Claude Code and Codex are switchable per chat, while the requirements section only details installing and signing in to Claude Code.
- Adapters for additional CLIs and local models remain roadmap items, so the current application is not a general-purpose agent host.
How does this agent compare with similar options?
Compared with running Claude Code or Codex only in a terminal, Superagent adds persistent desktop state, a visible and controllable authenticated browser, per-chat checkouts, an embedded iOS Simulator view, and remote phone interaction. It still runs those existing coding agents on their existing subscriptions and does not supply an AI model of its own. Support for other CLIs and local models is described as future work, so the present release should not be treated as a universal desktop shell for arbitrary agents.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Superagent This agent | 62 · Some gaps | Desktop appFree + model costs | ★ 36 | 4d ago | TypeScript | Codex · Claude Code |
| Pi Agent Desktop | 78 · Good | — | ★ 333 | today | TypeScript | OpenAI API |
| wmux Agent Workspace | 75 · Good | Desktop app | ★ 447 | today | TypeScript | Codex · Claude Code |
| wsp | 59 · Major gaps | Desktop appFree + model costs | ★ 14 | 3d ago | TypeScript | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The packet describes context isolation, computer use disabled until enabled, app-level permissions, a stop key, and layered remote-control consent with expiry and rate limits. This supports reasonable permission handling and confirmation, earning 2. The deduction is that many security and encryption assurances come mainly from the README and maintainer notes; the supplied code excerpts cannot fully verify their implementation. There is also no dependency inventory or audit evidence. Network traffic, credential boundaries, and local data clearing receive some explanation, but much of it is self-reported.
agent.ts describes backend separation and handling for process exits and session-loss notification races. The release workflow requires type checking and tests, and the README lists test commands, giving some evidence of consistency and failure reporting. The deduction is that the packet contains no dependency lockfile or availability policy, and static excerpts cannot establish the coverage of actual error paths.
The README identifies intended users, supported agents, Apple Silicon Macs, and optional Xcode and phone scenarios. It states that computer use is off by default and describes its scope and limits, as well as per-chat agent selection. The deduction is that some capability boundaries and scenarios remain product claims; the packet has no complete compatibility matrix or detailed configuration reference.
The README clearly organizes features, requirements, network behavior, FAQ, source setup, and roadmap. CLAUDE.md describes repository development, release, and implementation conventions rather than an Agent skill. The packet includes the full MIT license, and provides evidence for version-triggered releases and release notes. The deduction is that maintenance responsibility is attributed only to contributors and the supplied changelog evidence is limited.
The project combines coding agents with a browser, simulator, parallel worktrees, and phone interaction. The README gives concrete workflows and outputs that support practical value. Free access and use of existing subscriptions lower stated costs. The deduction is that benefits and costs are described by the project itself, with no independent usage evidence; configuring and operating several system capabilities may also add maintenance overhead.
The README makes specific claims about requirements, network traffic, and features that are partly corroborated by index.ts, preload, agent.ts, CLAUDE.md, and the release workflow. The deduction is that many claims cannot be traced directly to the supplied source excerpts, and the README mixes verifiable facts, design intent, and product claims. Fact and inference separation is therefore only partial.
- Computer use and remote control can interact with other apps or system input. The packet describes consent and safeguards but does not include enough implementation to verify every protection.
- Network and end-to-end encryption descriptions are primarily project claims; the packet is insufficient to independently verify the full data flow or dependency security.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/superagent-desktop)<a href="https://followagents.com/en/agents/superagent-desktop"><img src="https://followagents.com/badge/superagent-desktop.svg" alt="FARS review"></a>Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
v2.1.2 Superagent 2.1.2
Release notes excerpt
Superagent 2.1.2 Dictation shows your words as you speak. Hold the mic (or ⌥Space) and the words appear in the message box while you talk, about a second behind you, in the chat and in the dot. When you let go, the whole recording is read once more and the final text replaces the guess. It still runs entirely on your Mac. Dictation no longer freezes the window. The speech model now runs in the background, so the app stays responsive while it works.View on GitHub ↗ -
v2.1.1 Superagent 2.1.1
Release notes excerpt
Superagent 2.1.1 Your claude.ai skills show in Settings → Skills. Claude Code already brings the skills of your claude.ai account to this Mac, and your chats could use them, but the Skills page said "No skills yet". They are listed now, marked claude.ai. They are changed on claude.ai, so there is no Remove for them here.View on GitHub ↗ -
v2.1.0 Superagent 2.1.0
Release notes excerpt
Superagent 2.1.0 Everything from the 2.1 betas, in one release. - Split view. Up to eight chats side by side, from any project. ⌘-click a chat or drag it in; resize, rearrange, or give one the whole window. A split is a row in the sidebar you can name, ⌘1–8 jumps between its windows, and ⌘⇧] and ⌘⇧[ go round them. Opening one never stops your other chats. Four on iPad. …View on GitHub ↗
FAQ
Does it require another AI subscription or API key?
Can it control my everyday browser?
Can I use it without an iPhone or Xcode?
Does phone traffic pass through a third-party service?
What happens if native Simulator capture breaks?
simctl io screenshot.Thanks — we use this to improve the page.