# 32 Coding Agent Apps Reviewed Published: 2026-11-14 Tags: ai, agents, projects URL: https://codebrief.com/2026/11/32-coding-agent-apps-reviewed/ In 2012 I [reviewed every JavaScript MVC framework I could find](https://codebrief.com/2012/01/the-top-10-javascript-mvc-frameworks-reviewed/). Fourteen years later, the world is a completely different place, but the same thing is happening again, this time to apps that run coding agents: a new one every week, most of them free, many of them one person's side project, all of them promising to tame the terminal tabs. Here are thirty-two, scored on the ten things I care about. They come in two kinds. **ADEs** (agentic development environments) are apps your agents move into: you open a thread inside one, and it runs Claude Code or Codex for you. **Islands** are small notch apps that watch your agents wherever you already run them and let you answer without switching windows. The model vendors also ship apps of their own. These are tools for the centaur era we're in now: a developer and their agents working as one team. Some are already heading toward the software factory (Emdash 2.0, Capy's Captains, Warp's Factories), where tickets go in, pull requests come out and nobody sits at the controls. Even Steve Yegge, who runs one and burned down the five before it, tells most people they probably don't need one yet.[^yegge] That isn't how I work either, so every criterion below is about the human half of the centaur. Factories will need a list of their own. ## How I Judged Them Specifically, the following ten things are very important to me: 1. **Triage.** Sorting sessions by status isn't enough. I want a model that reads what each waiting session is asking, and that sends each new prompt where it belongs: the session already on that work, or the worktree it fits. That gets full marks. A queue sorted by status, or routing by capacity alone (the machine with free CPU, the account with room), gets half. 2. **Native harnesses.** I like using each harness the way its maker built it, now and then in its own app (Claude's design tools, say). I don't want every session forced through ACP inside an ADE, or into a TUI, and I want to choose which version of each harness runs. An ADE that drives Claude Code through Anthropic's SDK is also drawing on a smaller pool of your subscription's credits than you'd get typing into it yourself.[^credits] 3. **Existing sessions.** The moment it's installed, it should pick up every session I started anywhere else, and make them all searchable. 4. **Mobile.** It has to work on my phone. 5. **Open source, with a permissive license.** For a developer in this day and age, that's non-negotiable. These apps see all of your code and run commands on your machine, and the tool itself needs to be hackable. Bonus points (★) if it can start an agent on its own source, so you can change it from the inside. 6. **Working memory.** A big part of agentic development is keeping everything straight in your own head. Lightweight todos, boards, labels and emblems get some of it out of there. 7. **Automation.** Recurring schedules, and automatic pull request reviews, which are a must. Cloud review services are prohibitively expensive, especially when you're already paying for subscriptions. 8. **Multi-machine.** When my laptop's lid is closed, the work, reviews included, should carry on on another machine. Starting sessions, prompting them and automation should all work across devices. 9. **Your editor.** I don't want to be channeled into reading and editing code inside the tool. It should open the editor I already use. 10. **A desktop app.** Not a TUI: a real app, native if possible, that lives in the notch or the menu bar rather than only in its own window. An app whose only presence outside its window is notifications gets half. A full mark is a point, a half is half a point, and a feature you have to pay extra for, beyond the agent plans you already have, gets half at most. These ten are the reasons I built Codealong, so of course it does well on them. If your list is different, read the scorecard a column at a time. ## The Results | App | Kind | Triage | Harnesses | Sessions | Mobile | Open | Memory | Automation | Machines | Editor | Desktop | Score | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | Codealong | Both | ✓ | ✓ | ✓ | ½ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | 9½ ★ | | Orca | ADE | ½ | ½ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ½ | 8½ | | Cloudroom | ADE | ✓ | ½ | ½ | ✓ | ✓ | ✓ | ½ | ✓ | ✓ | ½ | 8 | | T3 Code | ADE | ½ | ½ | ½ | ✓ | ✓ | ½ | ✓ | ✓ | ✓ | ½ | 7½ ★ | | Diri | ADE | ✓ | ½ | ✓ | ½ | ½ | ✓ | ½ | ✓ | ✓ | ½ | 7½ | | Paseo | ADE | ½ | ½ | ½ | ✓ | ✓ | ½ | ✓ | ✓ | ✓ | ½ | 7½ | | bb | ADE | ½ | ½ | ✗ | ✓ | ✓ | ✓ | ½ | ✓ | ✓ | ½ | 7 | | MonoCode | ADE | ½ | ½ | ✗ | ½ | ✓ | ½ | ✓ | ✓ | ✓ | ✓ | 7 | | Synara | ADE | ✓ | ½ | ½ | ½ | ✓ | ✓ | ½ | ½ | ✓ | ½ | 7 | | Traycer | ADE | ½ | ½ | ½ | ✓ | ½ | ✓ | ✗ | ✓ | ✓ | ✓ | 7 | | Claude desktop | Vendor | ✓ | ✗ | ½ | ✓ | ✗ | ½ | ½ | ✓ | ✓ | ✓ | 6½ | | Coucou | Island | ½ | ✓ | ½ | ✓ | ✓ | ½ | ✗ | ½ | ½ | ✓ | 6½ | | Emdash | ADE | ½ | ✓ | ✗ | ✗ | ✓ | ½ | ½ | ✓ | ✓ | ✓ | 6½ | | Paradev | ADE | ½ | ½ | ✗ | ½ | ✓ | ✓ | ½ | ½ | ✓ | ✓ | 6½ | | Herdr | ADE | ½ | ✓ | ✗ | ✓ | ✓ | ½ | ✗ | ✓ | ½ | ½ | 6 | | Warp | Vendor | ½ | ✓ | ✗ | ✓ | ½ | ½ | ½ | ½ | ✓ | ½ | 6 | | CodeIsland | Island | ½ | ✓ | ½ | ½ | ✓ | ✗ | ✗ | ½ | ½ | ✓ | 5½ | | Codex app | Vendor | ½ | ✗ | ½ | ½ | ✗ | ½ | ½ | ✓ | ✓ | ✓ | 5½ | | Conductor | ADE | ½ | ½ | ✗ | ✓ | ✗ | ✓ | ½ | ½ | ✓ | ½ | 5½ | | super.engineering | ADE | ½ | ½ | ? | ✓ | ✗ | ½ | ½ | ✓ | ✓ | ½ | 5½ | | Zeron | ADE | ½ | ½ | ✗ | ✓ | ✓ | ½ | ✗ | ✓ | ½ | ½ | 5½ | | Open Island | Island | ½ | ✓ | ½ | ½ | ½ | ✗ | ✗ | ½ | ½ | ✓ | 5 | | AgentPeek | Island | ½ | ✓ | ½ | ✗ | ✗ | ½ | ✗ | ½ | ½ | ✓ | 4½ | | Cursor | Vendor | ½ | ✗ | ½ | ½ | ✗ | ½ | ½ | ✓ | ✗ | ✓ | 4½ | | Ping Island | Island | ½ | ✓ | ½ | ✗ | ✓ | ✗ | ✗ | ½ | ✗ | ✓ | 4½ | | Capy | ADE | ½ | ✗ | ½ | ½ | ✗ | ½ | ½ | ½ | ½ | ½ | 4 | | Google Antigravity | Vendor | ½ | ✗ | ½ | ½ | ✗ | ½ | ½ | ½ | ½ | ½ | 4 | | Agent Island | Island | ½ | ✓ | ½ | ✗ | ½ | ✗ | ✗ | ✗ | ✗ | ✓ | 3½ | | Notchi | Island | ½ | ✓ | ½ | ✗ | ½ | ✗ | ✗ | ✗ | ✗ | ✓ | 3½ | | Vibe Island | Island | ½ | ✓ | ½ | ✗ | ✗ | ✗ | ✗ | ½ | ? | ✓ | 3½ | | AgentNotch | Island | ½ | ✓ | ½ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | 3 | | Vibe Notch | Island | ½ | ✗ | ½ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✓ | 3 | ✓ full marks, ½ half, ✗ none, and ? where I couldn't tell. ★ marks an app that can start an agent on its own source, and only breaks ties. Every mark comes from the app's own docs, README, changelog or source, as of mid-November 2026. ## The Apps ### 1. [Codealong](https://www.codealong.com) ([source](https://github.com/codealong/codealong)) *ADE and island · Tauri · Phone: iPhone (early) · Apache-2.0 · Free* ![Codealong docked in a MacBook's notch over a dusk landscape, working through what waits on you: Command-Return allows a git push, a question is answered, a teammate's pull request an agent already reviewed is approved, finished turns are marked seen, and the notch closes with six agents at work.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/codealong-notch@2x.webp) Codealong is the one I make. I built it because I couldn't find anything that was solid on all ten of the criteria above. It's free and open source, built on Tauri with a Rust engine, for macOS, with early builds for Linux and Windows that you make from source. It watches every agent session on your machine the way an island does, and gets work out the door the way an ADE does. [Download it](https://www.codealong.com/download), or `brew install --cask codealong/tap/codealong`. ![Codealong's Sessions view over a morning landscape: every agent session in one list with an emblem beside each title, the three that need you first, and one open on the right asking to run git push, with Deny, Always and Allow.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/codealong-sessions@2x.webp) ![Codealong's PRs view: a teammate's pull request that an agent read first, marked Agent approves, with the agent's draft review on your account, a comment on a line of the migration, and buttons to approve, comment or request changes.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/codealong-pr-review@2x.webp) **Pros** * ✓ **Triage.** Press ⌥⌘. in any app and the notch opens on the agent that has waited longest; ⌘⏎ answers it and moves on. Jev, its decision model, reads each finished turn for whether it asks you something, and sends a prompt you type to the session already on that work, or to the worktree it belongs in. * ✓ **Harnesses.** It doesn't host your agents. New work starts in your terminal, as a background job or in the Claude and Codex apps, and each account names the command it runs, so you choose the build of each harness. * ✓ **Sessions.** It reads the records each agent already writes, so the moment it's installed it finds every session you've started with Claude Code, Codex, OpenCode, Antigravity and Cursor, and all of them are searchable. * ✓ **Open source.** Apache-2.0, and ⌥⌘, opens a session on Codealong's own source with a picture of every window, which is where the ★ comes from. * ✓ **Memory.** Todos your agents can pick up and finish, labels, pins, and an emblem on every session. * ✓ **Automation.** Schedules, and automatic pull request reviews that run on the plans you already pay for, by a different model from the one that wrote the code. * ✓ **Machines.** Link your machines and they share the work: one of them reviews each pull request, and when the laptop's lid closes, another picks it up. * ✓ **Editor and desktop.** It opens any of a dozen editors, and it lives in the notch and the menu bar. **Cons** * ½ **Mobile.** Its iPhone app is early, and for now you build it yourself. * It knows five agents, not thirty, and a Codex session in a terminal still asks for approvals in its own terminal. * It's Mac first. Linux and Windows are early builds you make from source; on Windows, sessions open in Windows Terminal, and Codealong can't yet type into them or find their tab. Its boards are experimental, and it's young (version 0.21). **Score: 9½ ★.** Best for keeping your terminal and your vendors' apps, across agents, accounts and Macs, with every pull request reviewed before you read it. That's the case I built it for. ### The ADEs The apps your agents move into, best score first. ### 2. [Orca](https://orca.dev) ([source](https://github.com/stablyai/orca)) *ADE · Electron · Phone: iOS and Android · MIT · Free* ![Orca: worktrees across two machines, a coordinator thread with its workers' updates, usage bars and the phone app.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/orca@2x.webp) Orca is the giant: 124,000 GitHub stars, a 25-person YC team at Stably AI, and around a thousand releases since March. It runs about thirty agents in its own terminal panes or a chat view, and piles on the extras: a coordinator that hands tasks to workers, an embedded browser whose Design Mode sends the element you click to the agent, computer use, and a cloud VM per worktree. **Pros** * ✓ **Sessions.** Its session history scans the records of Claude Code, Codex and some twenty other CLIs with nothing to turn on, searchable by title, folder, branch and text. * ✓ **Mobile.** iOS and Android apps, both still labeled beta, start agents and answer their questions. * ✓ **Open source.** MIT. * ✓ **Memory.** A Workspace Board keeps your worktrees in columns of your own. * ✓ **Automation.** Scheduled automations run on any of your hosts, and the docs' own recipe reviews the pull requests waiting on you every hour. * ✓ **Machines.** SSH targets, remote servers that keep going while your laptop sleeps, and cloud VMs share one window. * ✓ **Editor.** An Open in menu offers the editors you have. **Cons** * ½ **Triage.** Its Agents feed is one list across every worktree, but it's ordered by time and status, and nothing decides for you. Its coordinator, which hands a task to worker agents, is orchestration rather than triage. * ½ **Harnesses.** It runs your own CLI and lets you set its path, but every session lives inside Orca, in its panes or its chat. * ½ **Desktop.** An Electron app with notifications and a Dock badge, but nothing in the notch or the menu bar; two pull requests that would add a notch indicator are still open. * One reviewer measured 400 to 800 MB at idle, and users report flaky remote connections and outside pull requests that wait weeks for a review.[^orca] **Score: 8½.** Best for moving in, if you want everything in one place. ### 3. [T3 Code](https://t3.codes) ([source](https://github.com/pingdotgg/t3code)) *ADE · Electron · Phone: iOS and Android · MIT · Free* ![T3 Code's desktop window, with threads by project, a finished turn and its pull request panel, beside the phone app showing an approval.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/t3-code@2x.webp) T3 Code is Theo Browne's "open-source control plane for coding agents". A local server runs your agents and every client mirrors it: desktop apps for macOS, Windows and Linux, a web app, and iOS and Android apps, connected over your network, Tailscale or T3 Connect. It can hand a thread from Claude to Codex halfway through. **Pros** * ✓ **Mobile.** iOS and Android apps read threads, answer approvals and start new ones. * ✓ **Open source.** MIT, and its "Triage an issue" action points an agent at T3 Code's own source, which earns the ★. * ✓ **Automation.** Scheduled tasks run on your own machine, and a webhook task, whose documented example reviews each pull request, takes care of reviews (its public URL needs T3 Connect). * ✓ **Machines and editor.** One app connects to several machines, and its Open in menu covers every common editor. **Cons** * ½ **Triage.** Its thread list is an inbox you settle and snooze, but its decisions are about capacity: Auto balance picks the machine for a new thread by its free CPU and memory. A Labs feature suggests your next prompt in a thread, which is closer to autocomplete than to triage. * ½ **Harnesses.** Claude Code runs through Anthropic's Agent SDK and Codex through its app-server, both inside T3 Code, though you can set the binary. * ½ **Sessions.** It imports your last 30 days of Claude Code, Codex and Pi conversations once, at first run, rather than keeping up. * ½ **Memory.** Pins, snoozes and project icons, but no todos or boards. * ½ **Desktop.** Electron, with notifications and a badge, but nothing in the menu bar. **Score: 7½ ★.** Best for a phone-first ADE with a big community behind it. ### 4. [Paradev](https://paradev.com) ([source](https://github.com/ParadevAI/Paradev)) *ADE · Electron · Phone: iPhone (Pro) · MIT · Free, Pro $20 a user* ![Paradev, still under its old name Superset: a workspaces sidebar and a Claude Code terminal session, with the iPhone app.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/paradev@2x.webp) Paradev is Superset, renamed in October alongside an $11.5M seed round led by Union Square Ventures.[^paradev] It bills itself as an open-source alternative to the Codex app and Conductor: 21 agents fully supported, and any CLI agent besides. **Pros** * ✓ **Open source.** MIT since November 4, after nine months under the Elastic License. * ✓ **Memory.** Tasks with list and board views, priorities and labels. * ✓ **Editor and desktop.** It opens every common editor, and it sits in the menu bar. **Cons** * ½ **Triage.** A Needs attention lane across every workspace, sorted by status. Its Slack bot decides whether a request becomes a ticket or a new agent, but never sends it to a thread already on the work. * ½ **Harnesses.** Sessions live in its own terminal daemon, though you choose the binary. * ½ **Mobile.** The iPhone app needs Pro and iOS 26, and Android is a waitlist. * ½ **Automation and machines.** Automations run on a schedule or on GitHub events, a review request among them, on the device you pick and with your own subscription, and remote access spans your machines. Both need Pro, at $20 a user a month. * ✗ **Sessions.** It imports Git worktrees, not chats, not even Conductor's. * It's Mac only, with Linux experimental. **Score: 6½.** Best for teams that want automations and boards, and will pay for Pro. ### 5. [Paseo](https://paseo.sh) ([source](https://github.com/getpaseo/paseo)) *ADE · Electron · Phone: iOS and Android · Apache-2.0 · Free, hosted Hub $15 a seat* ![Paseo's sessions by repo and branch, an agent's shell steps and a diff, beside the iPhone app reviewing a pull request.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/paseo@2x.webp) Paseo is one person's work (Mohamed Boudra, who has turned down funding), and it reaches further than almost anything here. A daemon runs your agents, and everything connects to it, directly or through an end-to-end encrypted relay: desktop apps for macOS, Windows and Linux, iOS and Android apps, a web app, a CLI and a Docker image. People report moving whole teams to it in a week.[^paseo] **Pros** * ✓ **Mobile.** Its iOS and Android apps are, in its own words, "the full app". * ✓ **Open source.** Apache-2.0, with no telemetry, and its agents can change Paseo's plugins from the inside. * ✓ **Automation.** Schedules run on your daemons, and a Hub workflow reviews each new pull request using your own machines and subscriptions (Hub is free to host yourself). * ✓ **Machines and editor.** Agents can start and prompt agents on your other machines, and Open in editor remembers your choice. **Cons** * ½ **Triage.** It groups the sidebar by status. A Hub workflow can have a model classify a prompt, but only to start a new agent, never to send it to one already on the work. * ½ **Harnesses.** Claude Code runs through the Agent SDK, with its smaller pool of credits; to its maker's credit, he says so, and Paseo has a terminal for when you want the full plan. * ½ **Sessions.** You import outside sessions one at a time. * ½ **Memory.** Pins and labels, with todos left to plugins. * ½ **Desktop.** Electron, with notifications but no menu bar. * A lot rests on one person. **Score: 7½.** Best for the widest reach, from your desk to your phone to a Docker container. ### 6. [Cloudroom](https://www.cloudroom.dev) ([source](https://github.com/davidondrej/cloudroom)) *ADE · Electron · Phone: web · Apache-2.0 · Free, cloud from $50 a month* ![Cloudroom: a thread starting four sub-agents (Claude Code, Codex, Pi and OpenCode) in cloud sandboxes.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/cloudroom@2x.webp) Cloudroom is David Ondrej's app for macOS, Windows and Linux, Electron over a Rust core, that runs Claude Code, Codex, Pi and OpenCode on your Mac or in its own cloud sandboxes. **Pros** * ✓ **Triage.** Beyond status, models keep a purpose and a percent done on each thread and suggest your next prompt, both on by default, and a new prompt is nudged toward the right project. * ✓ **Mobile.** Its phone web app shows the same chat screens as the desktop. * ✓ **Open source.** Apache-2.0. * ✓ **Memory.** A first-party Tasks plugin is a Linear-style tracker with boards, labels and subtasks. * ✓ **Machines and editor.** Its new-thread picker lists your other Macs, SSH machines and sandboxes, and it opens your editor. **Cons** * ½ **Harnesses.** Sessions live only in Cloudroom. * ½ **Sessions.** You import them by hand, from Claude Code, Codex, Pi, T3 Code and Conductor. * ½ **Automation.** Its "Loops" run on a schedule, after a delay or from a webhook, but never review a pull request. * ½ **Desktop.** Electron, without a menu bar. * Its cloud tiers run from $50 to $500 a month. **Score: 8.** Best for work that moves between your Mac and the cloud, with a tracker built in. ### 7. [Diri](https://diri.sh) ([source](https://github.com/cristicretu/diri)) *ADE · Rust (GPUI) · Phone: iPhone (private beta) · AGPL-3.0 · Free* ![Diri: agents grouped by project, and a Claude Code terminal session waiting on a background agent.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/diri@2x.webp) Diri has the best opening line in the field: "Agents are good now. Watching thirty terminals is not." It's one developer's native Rust app that runs 22 agents in terminals, and any other with a short JSON file. Each terminal has a holder process of its own, so sessions survive quitting Diri. **Pros** * ✓ **Triage.** ⇧⌘I opens an inbox and ⇧⌘J jumps to the next, and beyond status, an opt-in spoken summary of each finished turn says what the agent did and what it's asking you. * ✓ **Sessions.** Its chat search lists your Claude Code and Codex conversations, including the ones started outside Diri. * ✓ **Memory.** Notes hold to-dos, and any to-do can start an agent. * ✓ **Machines and editor.** Any number of SSH hosts share one sidebar, and file links open in Cursor, VS Code or Zed. **Cons** * ½ **Harnesses.** Your CLI runs in Diri's own terminal holder rather than yours. * ½ **Mobile.** The iPhone companion needs a signed build and has no public release. * ½ **Open source.** The AGPL is copyleft. * ½ **Automation.** Schedules can even wake the Mac, but nothing reviews pull requests. * ½ **Desktop.** Native, with notifications and a Dock badge, but nothing in the menu bar. * It needs macOS 15 or later, and it has the smallest community on the list. **Score: 7½.** Best for a native, attention-first ADE. ### 8. [Synara](https://trysynara.com) ([source](https://github.com/Emanuele-web04/synara)) *ADE · Electron · Phone: no phone app yet · MIT · Free, remote $9.99 a month* ![Synara's window: a thread sidebar, a thread with edited-file cards, and a merged pull request's summary.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/synara@2x.webp) Synara began as a fork of T3 Code in March (after a public dispute, its license now credits T3 Tools)[^synara] and has grown in its own direction: ten agents through their own adapters, and handing a task from one agent to another. **Pros** * ✓ **Triage.** ⌥⌘A cycles through the chats waiting on you, and beyond status, a Hub's coordinator sends each message you write to an existing thread or a new one in the right repo, and writes the Hub's digest. * ✓ **Open source.** MIT, for now. * ✓ **Memory.** Tasks with priorities and due dates, a Kanban view, pins and notes. * ✓ **Editor.** It opens your editor. **Cons** * ½ **Harnesses.** Claude runs through the Agent SDK and Codex through its app-server, inside Synara. * ½ **Sessions.** A manual import of your Codex and Claude Code projects. * ½ **Mobile.** Its iPhone app is still "coming soon". * ½ **Automation.** Local schedules, but pull request reviews only by hand. * ½ **Machines.** Remote Connections let you start and steer chats on your other computers, but only on its paid Alto tier, at $9.99 a month. * ½ **Desktop.** Electron, with notifications only. * A pending change would move it to the AGPL. **Score: 7.** Best for todos and a board beside your agents, for free. ### 9. [Traycer](https://traycer.ai) ([source](https://github.com/traycerai/traycer)) *ADE · Electron · Phone: iOS and Android · MIT (clients) · Free, teams $20 a user* ![Traycer's workspace sessions panel, with Claude, OpenCode, Codex and Cursor sessions beside the workspace's context.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/traycer@2x.webp) Traycer started in 2025 as a plan-first VS Code extension and is now a desktop "nerve center for agentic coding". Several agents share a Task, whose specs, tickets and reviews outlast any one conversation. **Pros** * ✓ **Mobile.** iOS and Android apps, on every plan. * ✓ **Memory.** Tickets, specs, reviews and canvas boards, with labels and pins: as much as anything here. * ✓ **Machines, editor and desktop.** One window drives hosts on several machines, it opens your editor, and it sits in the system tray. **Cons** * ½ **Triage.** A notification center collects everything that needs attention across every task and machine, by status. Its routing is capacity planning: a rate-limited chat moves to an account with room. * ½ **Harnesses.** Sessions live in Traycer, though you can pin a version or point it at your own CLI. * ½ **Sessions.** You import them by hand, with search. * ½ **Open source.** The Host that actually runs your agents is closed; the MIT license covers the clients. * ✗ **Automation.** No scheduler and no pull request review, only a crontab recipe in the docs. **Score: 7.** Best for planning-heavy work shared across a team. ### 10. [bb](https://getbb.app) ([source](https://github.com/get-bb/bb)) *ADE · Electron · Phone: iOS and Android (beta) · MIT · Free* ![bb's window: a sidebar of threads, a code-review thread, a dispatch thread and a task board.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/bb@2x.webp) bb calls itself "an agentic IDE that builds itself". Nearly every feature is a plugin, and a server keeps all state in SQLite, with a host on each of your machines, so the desktop app, a web app, a CLI and an HTTP API can all drive it. **Pros** * ✓ **Mobile.** iPhone and Android betas read and steer your agents. * ✓ **Open source.** MIT, and its agents can write and install plugins from inside a thread, which comes close to the ★ but stops short of bb's own source. * ✓ **Memory.** A bundled Tasks plugin, with lists and boards. * ✓ **Machines and editor.** One server dispatches work across several machines, and it opens any editor you name. **Cons** * ½ **Triage.** Status marks, an unread-first grouping and a notification center. Its Account Pooler picks an account by how much each has used, which is capacity planning rather than judgment. * ½ **Harnesses.** The Agent SDK and app-server, with a setting for the binary. * ½ **Automation.** Schedules, but pull request reviews only by hand. * ½ **Desktop.** Electron, with notifications and no menu bar. * ✗ **Sessions.** It sees only the threads it started. * Telemetry is on by default, its API has no authentication if you expose the server to a network, and some doubt it's an IDE at all.[^bb] **Score: 7.** Best for hacking on your tools. ### 11. [MonoCode](https://usemono.dev) ([source](https://github.com/hardbeat920/monocode)) *ADE · Tauri · Phone: iPhone (beta) · MIT · Free* ![MonoCode's native preview: a sessions sidebar and tabs, a thread with a chart, a code editor and a git changes panel.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/monocode@2x.webp) MonoCode is a solo developer's Tauri app ("tabs are sessions, the composer is the input") with the most eclectic agent list here, from Claude Code and Codex to Hermes Agent and Devin. A native Rust rewrite is in preview. **Pros** * ✓ **Open source.** MIT. * ✓ **Automation.** Automations run on a schedule or on events, and a built-in template reviews each pull request when it's opened, all on your own CLIs. * ✓ **Machines.** "Add machine" puts any SSH host in the same rail. * ✓ **Editor and desktop.** It opens your editor, and a menu-bar extra holds floating chats. **Cons** * ½ **Triage.** Notifications and unread marks, but no queue and no model. Its orchestrator, a lead model choosing each worker's harness, is orchestration rather than triage. * ½ **Harnesses.** A setting for each binary, but every session inside the app. * ½ **Mobile.** An iPhone TestFlight whose approvals still need the desktop. * ½ **Memory.** A notes notebook with tags, but no todos. * ✗ **Sessions.** The requests to import them are still open. * It's in the middle of its rewrite, with hundreds of open issues.[^monocode] **Score: 7.** Best for automated reviews in an ADE that costs nothing. ### 12. [Emdash](https://github.com/generalaction/emdash) ([source](https://github.com/generalaction/emdash)) *ADE · Electron · Phone: no phone app · Apache-2.0 · Free* ![Emdash Classic: pinned task worktrees with their diff counts, projects, and the home screen.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/emdash@2x.webp) Emdash (YC W26) was the open-source ADE of early 2026: about twenty agent CLIs in parallel, in worktrees made ahead of time, with more issue trackers than anyone. **Pros** * ✓ **Harnesses.** The one ADE that gets this right: it runs each agent's real CLI, you choose each one's executable, and with tmux on you can attach to a session from your own terminal. * ✓ **Open source.** Apache-2.0. * ✓ **Machines, editor and desktop.** SSH machines, an Open In menu for every editor, and a menu-bar icon. **Cons** * ½ **Triage.** A status for each task, but no queue. * ½ **Memory.** Pins, and issues from your trackers. * ½ **Automation.** Cron, but no pull request reviews. * ✗ **Sessions and mobile.** Neither. * It's frozen: the desktop app, now Emdash Classic, gets fixes only, while Emdash 2.0, a team product, sits behind a waitlist. **Score: 6½.** Best for the real CLIs in an ADE, if you don't need it to grow. ### 13. [Herdr](https://herdr.dev) ([source](https://github.com/herdrdev/herdr-app)) *ADE · Rust (GPUI) · Phone: iOS and Android · Apache-2.0 · Free* ![Herdr's window: spaces grouped by machine, one marked as needing you, a list of agents, and a Claude Code session in a terminal.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/herdr.webp) Herdr started as a terminal multiplexer for agents with 51,000 stars, and at the end of October it became a native app, with libghostty terminals, for macOS, Linux and Windows. Your agents run in herdr-core, a background runtime, so they keep going when you close the window. Its maker, Can Celik, joined Y Combinator and raised a $6M seed in September.[^herdr] **Pros** * ✓ **Harnesses.** Your own CLIs in real terminals, with no SDK or ACP in between; a settings file says which command each agent runs, and you can attach to any of them from your own terminal. * ✓ **Mobile.** Free iOS and Android apps, since November 6. * ✓ **Open source.** Apache-2.0, all but the phone apps. Its whole interface is JavaScript mods that your own agent is invited to rewrite, which comes close to a ★. * ✓ **Machines.** One sidebar spans every machine you can reach over SSH. **Cons** * ½ **Triage.** Its Priority view lists every agent under Needs you, Done, Working and Idle, and Alt+↓ steps through them, but by status alone: nothing reads what an agent asks or picks where new work goes. * ½ **Memory.** Pins and named spaces. * ½ **Editor.** File paths open in your OS's default app. * ½ **Desktop.** Native, but its alerts stay inside its window: no system notifications, no menu bar. * ✗ **Sessions and automation.** It doesn't even see the Herdr TUI's agents, and it has no schedules or reviews. * Telemetry is on by default. **Score: 6.** Best for real terminals across many machines, in a native app. ### 14. [Capy](https://capy.ai) *ADE · its cloud · Phone: web · Closed · From $20 a month* ![Capy's web app: its Captains sidebar, a thread split into three sub-threads, and an overview of issues and a pull request.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/capy@2x.webp) Capy is the odd one out. It isn't a wrapper around your agents but a YC company's own agent, running in its cloud. "Captain" agents plan and hand work to "Build" agents, each in its own sandbox, and the desktop app runs the tools on your machine while the agent loop and your threads stay in Capy's database. **Cons** * ½ **Triage, mobile, memory, machines and editor.** All real, and all behind a paid plan, since Capy has no free tier: a Captain writes a "Needs you" digest and sends each prompt you give it to the thread that should take it, there's a phone web app with push notifications, a built-in issue tracker, a "Run on" that starts a thread in the cloud or on another of your machines, and an editor picker. * ½ **Sessions.** It imports your Claude Code and Codex history once, when you set it up. * ½ **Automation.** Automations and an automatic review agent both exist, but they run in Capy's cloud on its credits, which "don't use the subscriptions and keys you connect". * ½ **Desktop.** No menu-bar presence on a Mac. * ✗ **Harnesses and open source.** It runs its own agent, and it's closed. **Score: 4.** Best for teams happy to buy a cloud product. ### 15. [Conductor](https://www.conductor.build) *ADE · Tauri · Phone: iPhone · Closed · Free, cloud on paid plans* ![Conductor: workspaces in a sidebar, a chat with tool-call summaries, a changes list ready to merge and a run pane.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/conductor@2x.webp) Conductor set the pattern the others position themselves against: a Mac app that runs Claude Code and Codex in parallel, each in its own workspace, then reviews and merges their work. Melty (YC S24) raised a $22M Series A in March and claimed 100,000 users. On November 4, Meta (Facebook) bought it[^conductor] and announced a wind-down. Nine days later its changelog said "Conductor isn't shutting down. It's back, and we're building again." It's now "Conductor from Meta", and how long a Meta-owned Conductor stays supported, and for whom, is anyone's guess. **Pros** * ✓ **Mobile.** Its iPhone app works with remote control. * ✓ **Memory.** Todos that block a merge, a notes tab and status sections. * ✓ **Editor.** An Open In menu for every common editor. **Cons** * ½ **Triage.** "Next workspace" jumps between the chats that need you, but by status alone; its model-written summaries stay inside each chat. * ½ **Harnesses.** Bundled or configured binaries, but only inside its own chat. * ½ **Automation.** Its Routines run in Conductor's cloud, for paid plans only. * ½ **Machines.** Its cloud VMs sit beside local workspaces, but one Mac can't see another. * ½ **Desktop.** Notifications only. * ✗ **Sessions and open source.** No imports, and it's closed, now under Meta. **Score: 5½.** Best for people who already use it, and trust Meta to keep it going. ### 16. [super.engineering](https://super.engineering) *ADE · Rust (GPUI) · Phone: iPhone (beta) · Closed · Free (alpha)* ![super.engineering's window: unread, running and pinned threads, a thread handing three fixes to three models, and its changes and run panes.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/super-engineering@2x.webp) super.engineering ("Don't run an agent. Command a fleet.") is a native Rust app for macOS and Linux, launched in April as Superconductor, that gives every task a worktree and runs 18 agents as plain subprocesses on your own accounts. It has the best review flow in the native camp: comments anchored to lines of the diff, and one button from commit to pull request to merge. **Pros** * ✓ **Mobile.** Its iPhone app, on public TestFlight, answers approvals and questions. * ✓ **Machines and editor.** SSH workspaces sit beside local ones, and its Open In list takes any app you add. **Cons** * ½ **Triage.** ⌘I opens a real inbox across workspaces, and ↩ sends your reply and moves to the next, but by status alone. Its orchestration, which you have to ask for, is a different thing. * ½ **Harnesses.** Your CLI in its terminal tab or its chat. * ½ **Memory.** Labels, pins and colors, but no todos. * ½ **Automation.** An early preview, with reviews on demand. * ½ **Desktop.** Native and quick, with one reviewer measuring startup at about 50 milliseconds,[^super] but nothing in the menu bar. * ✗ **Open source.** It's closed, with terms that anticipate paid licensing. * ? **Sessions.** I couldn't tell whether it lists sessions started outside it. **Score: 5½.** Best for speed, if you can live with closed source. ### 17. [Zeron](https://zeron.sh) ([source](https://github.com/zeronsh/zeron)) *ADE · Rust · Phone: iOS and Android · MIT · Free* ![Zeron's new-chat composer, with pickers for the model, folder, device and branch.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/zeron@2x.webp) Zeron is "a native control plane" for Claude Code, Codex, Cursor, Devin and others, mostly the work of one developer who goes by Wing. Since version 0.3 it draws its window with its own Rust UI framework, and a Rust engine owns the agents, so closing the window leaves every session running. **Pros** * ✓ **Mobile.** iOS and Android apps watch sessions, send messages and approve diffs. * ✓ **Open source.** MIT. * ✓ **Machines.** Devices signed in to one account share one sidebar, where you can start a chat on another machine. **Cons** * ½ **Triage.** It opens on Activity, a list of the chats that need you, latest first, but by status alone on the desktop; only its phone apps' voice assistant picks an agent and project for you. * ½ **Harnesses.** Your CLI over stream-json or app-server, inside Zeron. * ½ **Memory.** Pins and named sections. * ½ **Editor.** "Open in editor" uses your OS's default app. * ½ **Desktop.** Banners, but no menu bar. * ✗ **Sessions and automation.** Two attempts to import sessions were closed unmerged, and there are no schedules or reviews. **Score: 5½.** Best for a native app that follows you across devices. ### The Landlords Every ADE above rents its agents from two landlords, and both landlords now build apartments, along with a few others. Apart from Warp, a terminal that runs anything, each runs one vendor's agent and is closed source, and every one of them sells automatic pull request review as a cloud service. ### 18. [Warp](https://www.warp.dev) *Vendor app · Rust · Phone: web · AGPL-3.0 · Free, paid plans* ![Warp running an agent: task steps with diffs, a task list and a plan document.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/warp@2x.webp) Warp named this category: [Warp 2.0 launched](https://www.warp.dev/blog/reimagining-coding-agentic-development-environment) in June 2025 as "the first Agentic Development Environment", a terminal with agents built in. **Pros** * ✓ **Harnesses.** Being a terminal, it runs Claude Code, Codex or anything else as they come. * ✓ **Mobile and editor.** Its Remote Control works from a phone's browser, and it opens your editor. **Cons** * ½ **Triage.** Its notification mailbox collects every agent's alerts to work through, but by status; its orchestration proposes child agents for you to approve. * ½ **Open source.** Its client is now open source, under the AGPL. * ½ **Memory.** Task lists, tab colors and groups. * ½ **Automation.** Scheduled agents and pull request reviews exist, but in Warp's cloud, as paid usage. * ½ **Machines.** One machine at a time. * ½ **Desktop.** Notifications and a drop-down window, but no menu bar. * ✗ **Sessions.** Claude Code sessions don't appear in its panels. **Score: 6.** Best for a terminal that knows about agents. ### 19. [Claude desktop](https://claude.ai/download) *Vendor app · Electron · Phone: iOS and Android · Closed · Your Claude plan* ![The Code tab in Claude's desktop app: an edit log, preview, diff, terminal, tasks and plan panes, and a second session.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/claude-desktop@2x.webp) The Code tab in Anthropic's desktop app runs a bundled copy of Claude Code, and it gets Claude's features before anyone else does. **Pros** * ✓ **Triage.** A needs-input marker on each session, and beyond status, a Projects coordinator sends each new message to a new thread or to the one already on that work, and it suggests your next prompt. * ✓ **Mobile.** The Claude apps on iOS and Android reach your local sessions through Remote Control. * ✓ **Machines.** One sidebar holds local, SSH and cloud sessions. * ✓ **Editor and desktop.** It opens VS Code, Cursor or Zed, and it has a menu-bar item. **Cons** * ½ **Sessions.** Your CLI sessions come in by hand, through `/resume` or an import. * ½ **Memory.** Pins, sections and renaming. * ½ **Automation.** Local schedules, but its automatic pull request review is Code Review, billed separately on Team and Enterprise plans, or a GitHub Action, both in the cloud. * ✗ **Harnesses and open source.** It runs Claude and nothing else, and it's closed. **Score: 6½.** Best for Claude, and only Claude. ### 20. [Codex app](https://openai.com/codex/) *Vendor app · Electron · Phone: iOS and Android (paid plans) · Closed · Your ChatGPT plan* ![The Codex app's home screen: recent threads and projects, and a composer with suggested tasks.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/codex-app@2x.webp) OpenAI's Codex app has lived inside the ChatGPT desktop app since July. **Pros** * ✓ **Machines.** It hands chats between your computers. * ✓ **Editor and desktop.** It opens your editor, and it sits in the menu bar. **Cons** * ½ **Triage.** Its Activity view and ⌘⌥A take you to the next chat needing attention. Beyond status, its always-on assistant continues the existing Codex task your request belongs to, but only on ChatGPT Pro, at $100 a month and up. * ½ **Sessions.** Your CLI sessions appear once their folder is a project. * ½ **Mobile.** The ChatGPT apps reach your desktop's chats, on paid plans. * ½ **Memory.** Pins and sections. * ½ **Automation.** Local schedules, but pull request reviews only in OpenAI's cloud. * ✗ **Harnesses and open source.** It runs Codex, and the app is closed, though the Codex CLI is Apache-2.0. **Score: 5½.** Best for Codex, and only Codex. ### 21. [Cursor](https://cursor.com) *Vendor app · VS Code fork · Phone: iPhone and web (paid plans) · Closed · Your Cursor plan* ![Cursor's agents window: agents by repo, an agent's thread and summary, and a diff ready to commit and push.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/cursor@2x.webp) Cursor is the editor most people first met agents in, and its agents window is now a front door of its own. **Pros** * ✓ **Machines.** My Machines lets you start agents on any of your computers. * ✓ **Desktop.** A menu-bar icon counts what's unread. **Cons** * ½ **Triage.** A Needs Attention section across every workspace, by status. Its Projects coordinator hands tasks to agents, which is orchestration rather than triage. * ½ **Sessions.** An opt-in, read-only import of Claude Code chats. * ½ **Mobile.** An iPhone app and the web, on paid plans. * ½ **Memory.** Projects have a task board, but only on its Premium plan and up. * ½ **Automation.** Automations and Bugbot, both in Cursor's cloud and billed. * ✗ **Harnesses, open source and editor.** It runs only its own agent, it's closed, and it is the editor. **Score: 4½.** Best for people who already live in Cursor. ### 22. [Google Antigravity](https://antigravity.google) *Vendor app · Electron · Phone: web · Closed · Free, paid plans* ![Antigravity: a conversation with a changed-file card and a voice chat panel, beside a projects sidebar.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/antigravity@2x.webp) Antigravity is Google's agent-first IDE, with an Agent Manager that sends agents off in parallel. **Cons** * ½ **Mobile and machines.** Its Remote Control works from a phone's browser, across all your machines, but it needs a plan that supports it, and it rolled out to Ultra subscribers first. * ½ **Triage.** Status icons and filters, but no queue. Its /swarm coordinator splits a task among workers, which is orchestration, not triage. * ½ **Sessions.** Its CLI can pull in the app's conversations, by hand. * ½ **Memory.** Pins and groups. * ½ **Automation.** Local schedules, but no pull request review of its own. * ½ **Editor.** It opens Antigravity's own IDE, or Finder. * ½ **Desktop.** A tray icon on Windows and Linux only. * ✗ **Harnesses and open source.** Claude appears only as a model inside Google's agent, and it's closed. **Score: 4.** Best for Google's agent, with Google's models. ### Gone, Going or Out of Scope * **[Vibe Kanban](https://github.com/BloopAI/vibe-kanban):** a Kanban board over your agents, a worktree per card. A competitor's blog reports its makers wound it down in April;[^vibekanban] it may live on as a community project. * **[Sculptor](https://docs.imbue.com/changelog):** Imbue's app for running Claude Code agents in parallel containers. The last release I could find is from January. * **[Claude Squad](https://github.com/smtg-ai/claude-squad):** a terminal app that runs several agents in tmux sessions and worktrees, and one of the first of its kind. ### The Islands Every island works the same way underneath. It installs a hook into each agent (for Claude Code, a script its hooks call when it wants permission, wants input or finishes a turn), the hook tells the app over a local socket, and the app draws it in the notch. Because they watch the CLIs you already installed and live in the notch, nearly all of them get full marks for native harnesses and the desktop. Their triage is a status queue, with no model reading what each session asks, so they get half for it. None has search, schedules or pull request reviews, and only a few reach your phone. ### 23. [Coucou](https://github.com/Louis-CFM/coucou) ([source](https://github.com/Louis-CFM/coucou)) *Island · Swift · Phone: iOS and Android · MIT (code) · Free* ![Coucou's notch panel: a checklist of the agent's reads, edits and commands, and a live diff of the file it's editing.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/coucou@2x.webp) Coucou is the most popular island by stars (7,200), and the only one that runs on all three desktops: macOS, Windows and Linux. **Pros** * ✓ **Harnesses.** It hooks into the CLIs you already run, and can start Claude Code in your own terminal. * ✓ **Mobile.** Its iPhone app, free on the App Store, allows with Face ID, answers questions and sends the next instruction, and there's an Android app too. * ✓ **Open source.** MIT, though its name, mascot and sounds aren't. * ✓ **Desktop.** The notch and the menu bar. **Cons** * ½ **Triage.** Approvals queue across sessions and take the card in turn, and ⌃⌥A jumps to whatever is waiting, but no model organizes them. * ½ **Sessions.** They appear once they fire a hook, and there's no search. * ½ **Memory.** A color per agent. * ½ **Machines.** A reverse SSH tunnel you set up yourself. * ½ **Editor.** VS Code only. * ✗ **Automation.** None. **Score: 6½.** The best island on my list, and one that follows you off the Mac. ### 24. [CodeIsland](https://github.com/wxtsky/CodeIsland) ([source](https://github.com/wxtsky/CodeIsland)) *Island · Swift · Phone: iPhone and Watch · MIT · Free* ![CodeIsland's notch panel: four sessions marked needs you, working and done, with each one's tool and terminal.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/codeisland@2x.webp) CodeIsland is close to Vibe Island's feature list for free, with thirty-plus agents and 2,600 stars. **Pros** * ✓ **Harnesses.** It hooks into your own CLIs, honoring each one's config folder. * ✓ **Open source and desktop.** MIT and native, in the notch and the menu bar. **Cons** * ½ **Triage.** Approvals and questions wait in a queue, and answering one brings up the next, but by status alone. * ½ **Sessions.** It finds sessions already running at launch, but keeps no history and has no search. * ½ **Mobile.** An iPhone and Watch companion that works only on the same Wi-Fi or over Bluetooth. * ½ **Machines.** SSH hosts beside local ones. * ½ **Editor.** It opens the folder in Finder. * ✗ **Memory and automation.** Neither. **Score: 5½.** A free, open-source Vibe Island that reaches your wrist. ### 25. [Open Island](https://github.com/Octane0411/open-vibe-island) ([source](https://github.com/Octane0411/open-vibe-island)) *Island · Swift · Phone: iPhone and Watch (build it yourself) · GPL-3.0 · Free* ![Open Island's notch panel: four sessions with their agent and terminal, and Claude and Codex usage.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/open-island@2x.webp) Open Island knows fifteen agents, and unusually for an island it doesn't rely on hooks alone: it also reads Claude Code's and Codex's own session files. **Pros** * ✓ **Harnesses.** It hooks into your own CLIs, and talks to the Codex app through its own app-server. * ✓ **Desktop.** Native, in the notch and the menu bar. **Cons** * ½ **Triage.** It sorts sessions by what needs an approval or an answer, by status alone. * ½ **Sessions.** It finds the last 24 hours of Claude Code and Codex transcripts, with no search. * ½ **Mobile.** iPhone and Watch apps that you build yourself. * ½ **Open source.** GPL. * ½ **Machines.** Claude Code over a forwarded SSH socket. * ½ **Editor.** It jumps to the hosting IDE, or Finder. * ✗ **Memory and automation.** Neither. **Score: 5.** An open-source island that understands the agents' own records, not just their hooks. ### 26. [AgentPeek](https://agentpeek.app) *Island · Swift · Phone: no phone app · Closed · $14.99 once* ![AgentPeek's notch panel for one session: its branch, cost and diff, latest message and a running typecheck.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/agentpeek@2x.webp) AgentPeek, by Bren Huber, knows 27 agents and reads them more ways than most: hooks, transcripts, the agents' local databases and ACP. **Pros** * ✓ **Harnesses.** It leaves your agents where they run, and can even send one a follow-up prompt. * ✓ **Desktop.** Native, in the notch and the menu bar. **Cons** * ½ **Triage.** Prompts stack in the notch and the arrow keys move between them, by status alone. * ½ **Sessions.** Recent ones, with no search. * ½ **Memory.** A board that fills itself. * ½ **Machines.** A view-only dashboard of one agent on another machine. * ½ **Editor.** Reveal in Finder. * ✗ **Mobile, open source and automation.** None of them, for $14.99. **Score: 4½.** Best for doing a little more than yes and no. ### 27. [Ping Island](https://github.com/erha19/ping-island) ([source](https://github.com/erha19/ping-island)) *Island · Swift · Phone: no phone app · Apache-2.0 · Free* ![Ping Island's panel: seven sessions from seven different agents, with how long each has run.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/ping-island@2x.webp) Ping Island knows about seventeen agents through its own hook bridge, Codex's app-server and plugins. **Pros** * ✓ **Harnesses.** It leaves your CLIs and the Claude and Codex apps where they are. * ✓ **Open source and desktop.** Apache-2.0 and native, in the notch and the menu bar. **Cons** * ½ **Triage.** The notch opens on the most urgent request, ranked by status and time rather than by what it asks. * ½ **Sessions.** Codex's 30 most recent threads, with no search. * ½ **Machines.** SSH hosts in one view, though you can't start sessions on them. * ✗ **Mobile, memory, automation and editor.** None of them. **Score: 4½.** Best for watching agents on SSH hosts, for free. ### 28. [Agent Island](https://agent-island.dev) *Island · Swift · Phone: no phone app · MIT (claimed) · Free, when you can get it* ![Agent Island's expanded panel: Claude's five-hour and weekly usage and Grok's weekly usage.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/agent-island@2x.webp) Agent Island reads transcripts instead of installing hooks, and runs on Windows as well as the Mac. **Pros** * ✓ **Harnesses.** It reads your agents' transcripts without touching their settings. * ✓ **Desktop.** A menu-bar app whose island takes the shape of the notch. **Cons** * ½ **Triage.** Its "It's your turn" alarms queue rather than replace each other, by status alone. Its switch to the next Codex account when one runs out is capacity planning. * ½ **Sessions.** It sees the ones already running, but has no search. * ½ **Open source.** Its site says MIT, but its maker's source is gone. * ✗ **Everything else.** Nothing for mobile, memory, automation, machines or your editor. * The bigger problem: you can't download it. Its repo, its releases and its Homebrew tap have all disappeared. **Score: 3½.** Best for nobody, until it comes back. ### 29. [Vibe Island](https://vibeisland.app) *Island · Swift · Phone: no phone app yet · Closed · $19.99 once* ![Vibe Island's notch panel with three sessions (Claude, Grok Build and Codex) and usage.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/vibe-island@2x.webp) Vibe Island is the commercial leader and the one people mean when they say "island": thirty agents, twenty-odd terminals, and a jump to the exact tab or split pane. **Pros** * ✓ **Harnesses.** It watches every CLI where you already run it. * ✓ **Desktop.** The most polished native notch here. **Cons** * ½ **Triage.** A parallel approval queue with keyboard shortcuts, by status alone; it runs no model. * ½ **Sessions.** No history, no search. * ½ **Machines.** SSH hosts, approvals included. * ✗ **Mobile, open source, memory and automation.** Its iPhone app is on a waitlist (for now it pushes notifications through a third-party app), and it's closed. * ? **Editor.** I couldn't tell whether it opens your editor. **Score: 3½.** The most polished island money can buy, with a two-day trial. ### 30. [AgentNotch](https://agentnotch.app) *Island · native · Phone: no phone app · Closed · $9.99 once* ![AgentNotch's notch panel: an approval, a question, working sessions, and plan usage for Claude, Codex and Cursor.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/agentnotch@2x.webp) There are two AgentNotches. This is Piotr Jura's paid app; a [free AgentNotch on GitHub](https://github.com/AppGram/agentnotch), from a different maker, only watches Claude Code and Codex and hasn't been updated since January. **Pros** * ✓ **Harnesses.** It watches nine agents wherever they run. * ✓ **Desktop.** The notch and the menu bar. **Cons** * ½ **Triage.** It shows the one session that needs you, worst first, by status alone. * ½ **Sessions.** Live ones, plus some history at startup, with no search. * ✗ **Everything else.** Nothing for mobile, open source, memory, automation, machines or your editor. **Score: 3.** The cheapest paid island. ### 31. [Notchi](https://notchi.app) ([source](https://github.com/sk-ruban/notchi)) *Island · Swift · Phone: no phone app · GPL-3.0 · Free* ![Notchi's usage dashboard: Claude and Codex cost and tokens, a 30-day chart and limits.](https://codebrief.com/images/posts/32-coding-agent-apps-reviewed/notchi@2x.webp) Notchi covers Claude Code and Codex, with a mascot for every session, and needs a MacBook with a notch running macOS 15. **Pros** * ✓ **Harnesses.** It hooks into Claude Code and Codex in your own terminal. * ✓ **Desktop.** Native, in the notch. **Cons** * ½ **Triage.** Mascots and sounds, but no queue; the model it runs reads the mood of your prompts, not what the agents need. * ½ **Sessions.** Past transcripts feed only its cost dashboard. * ½ **Open source.** GPL. * ✗ **Everything else.** Nothing for mobile, memory, automation, machines or your editor. **Score: 3½.** A small, free island for the two agents most people run. ### 32. [Vibe Notch](https://github.com/farouqaldori/vibe-notch) (formerly Claude Island) ([source](https://github.com/farouqaldori/vibe-notch)) *Island · Swift · Phone: no phone app · Apache-2.0 · Free* Vibe Notch started out as Claude Island, one of the first of these, and other islands have been forked from it. **Pros** * ✓ **Open source and desktop.** Apache-2.0 and native, in the notch and the menu bar. **Cons** * ½ **Triage and sessions.** The notch opens on a new approval, but there's no queue, and sessions appear only once their hooks fire. * ✗ **Harnesses.** Claude Code only. * ✗ **Everything else.** Nothing for mobile, memory, automation, machines or your editor, and it has been quiet since April. **Score: 3.** Claude Code alone, if you don't mind that it has gone quiet. ### Also on the Island * **[NotchCode](https://notchcode.dev):** $19.99 once for Claude Code, Gemini CLI and Codex, in tmux only. I couldn't tell who makes it or whether it's still sold. * **[Notchcode](https://github.com/billxby/notchcode)** (no relation): free and MIT, Claude Code and Codex, watching and jumping only, on Mac and Windows. * **[Chimlo](https://github.com/kraten/chimlo):** free and GPL, Claude Code and Codex, allows and answers. One release, in July. * **[Vibe Hub](https://github.com/mtunique/VibeHub):** a Claude Island fork for Claude Code and OpenCode, with SSH. Free source, but the app has a license check. * **[HermitFlow](https://github.com/0x0Bke/HermitFlow-VibeIsland):** free and MIT, Claude Code, Codex and OpenCode, and it approves Codex by driving its terminal through Accessibility. * **[Agent Visor](https://github.com/824zzy/agent-visor):** a menu-bar app for seven agents, from the maker of the older Claude Visor. * **[MioIsland](https://github.com/MioMioOS/MioIsland):** Claude Code with an iPhone companion, free for personal use only (CC BY-NC). ## The Shake-Out This category is already consolidating: * Meta (Facebook) bought Conductor, the best-funded independent, and announced its end, then reversed course nine days later. It lives on as "Conductor from Meta", with nothing said about for how long. * Emdash stopped developing its open-source desktop app, and its team product sits behind a waitlist. * Paradev moved automations, remote access and its phone app behind its paid plan, though it did switch to MIT. * Vibe Kanban, by one account, has wound down, and Agent Island's maker has taken down every download. * The landlords keep moving in: the Codex app folded into ChatGPT's desktop app in July, and the vendors' own apps get every new feature first. Of course, this list is far from comprehensive. These apps launch every week, and I'm sure I've missed some. Thanks to zakra, whose lists gave me a starting point.[^zakra] Star counts are GitHub's in mid-November 2026, and the screenshots are the makers' own, from their sites and repositories. What do you run your agents in? [^yegge]: [Steve Yegge on X](https://x.com/Steve_Yegge/status/2121671447810888185), 14 November 2026: "You probably don't need one." [^credits]: Paseo's maker, [on Hacker News](https://news.ycombinator.com/item?id=48377250). [^orca]: The memory figures are from [a review on andrew.ooo](https://andrew.ooo/posts/orca-stablyai-parallel-coding-agents-ide-review/); the reports are [on Hacker News](https://news.ycombinator.com/item?id=50372338) and [again](https://news.ycombinator.com/item?id=49606598). [^paradev]: Reported by [Magica](https://magica.com/news/paradev-seed-funding-coding-agent-workspace). [^paseo]: [On Hacker News](https://news.ycombinator.com/item?id=50414272). [^synara]: [Theo on X](https://x.com/theo/status/2084197114348028281). [^bb]: [On Hacker News](https://news.ycombinator.com/item?id=49272048). [^monocode]: [AlphaSignal](https://alphasignal.ai/news/monocode-unifies-claude-code-codex-and-cursor-into-one-desktop-app), on the open issues and the rewrite. [^herdr]: Covered by [heise](https://www.heise.de/en/news/Herdr-desktop-app-A-hub-for-AI-coding-agents-11508175.html) and discussed [on Hacker News](https://news.ycombinator.com/item?id=50298436); Thoughtworks' [Technology Radar](https://www.thoughtworks.com/radar/tools/herdr) puts it in Assess. [^conductor]: Reported by [SiliconANGLE](https://siliconangle.com/2026/11/04/meta-acquires-ai-coding-startup-conductor-whose-app-runs-several-coding-agents-at-once/). The reversal is in Conductor's own [changelog](https://www.conductor.build/changelog). [^super]: [A review on DEV](https://dev.to/danielbergholz/superconductor-review-the-cleanest-way-ive-found-to-run-ai-agents-in-parallel-1c87). [^vibekanban]: [Nimbalyst's roundup of agent tools](https://nimbalyst-website.pages.dev/blog/best-agent-management-tools-2026/). [^zakra]: zakra's [ADE tier list](https://x.com/zqkrq) and [ADEMark](https://ademark.dev).