# How to keep track of multiple AI coding agent sessions

> Back from a break with agents still running? Keep track of multiple AI coding agent sessions with window states, spoken notices and short recaps.

Published 2026-09-25 on the Starkomand blog: https://starkomand.com/blog/resume-two-projects-with-agent-recaps/

You leave for a meeting with two agents running. One is investigating API timeouts. The other is changing a mobile navigation menu. When you come back, both terminals have moved on without you, and you need to decide which one needs you first.

That is the everyday version of a common question: how do you keep track of multiple AI coding agent sessions without rereading every terminal? I build [Starkomand](https://starkomand.com/) around that question, so this walkthrough uses it, and each section names the control in the app that handles that step. The two tasks and their output are a scripted example.

## Why terminal tabs make this hard

A terminal is a good place to run an agent and a poor place to catch up on one. The output scrolls, so the finding you need can sit far above the prompt. Tabs look alike, so two tabs named after the same CLI don't say which repository each one is in. And a finished agent looks much like a stuck one. Both are quiet, and you only learn which is which by reading.

So catching up is really three questions. Which session finished, and which is still going? Is either one waiting on me? What did each one actually do?

## Leave each agent a bounded assignment

Catching up starts before you leave. An agent with a clear stopping point is much easier to read later than one told to keep going.

Start each agent in its own repository. The **Launch folder** button in the launcher sets where new agents start; windows that are already open keep their folder. Put the API agent on the left and the website agent on the right, and give each a scope it can finish.

The API agent gets an investigation:

> Investigate why retried requests time out immediately. Trace timeout creation and reuse across attempts. Do not edit files. Report the likely cause, the relevant files, and a regression test we could use to check a fix.

The website agent gets an implementation:

> Below 720px, collapse the navigation behind the existing menu button. Close the menu after route selection and return keyboard focus to the button when the menu is dismissed. Preserve desktop navigation. Run the relevant checks and leave the result ready for browser review.

Two short jobs can share one workspace, which keeps both in a single glance. When a project grows to several windows, previews and notes, give it its own workspace. Each workspace keeps its own launch folder, layout and backdrop, and the left and right arrow keys switch between them when no window is selected.

Separate windows do not separate files. If two agents will edit the same repository, give each its own Git worktree before you start them.

## Come back and see which agent needs you

Press **Option–Command–K** from any app to bring Starkomand forward. Press it again to hide it.

Before reading a line of output, read the window headers. An agent window shows **working** while a turn runs, and **finished** with a green frame once the agent goes quiet after your prompt. The green stays until you click into the window or type, so it also marks what you have not looked at yet. A turn that ends in an error shows **failed**.

![Two agent windows side by side on the Starkomand canvas. Felix, a Claude Code session in the api-gateway repository, has a green frame and a finished badge above its timeout findings. Leo, a Codex session in the studio repository, shows a working badge while it runs the navigation tests.](https://starkomand.com/assets/blog/resume-two-projects-with-agent-recaps/states.jpg)

*Captured from the app with scripted terminal output; the repositories and file names are illustrative.*

Here the order decides itself: Felix, the API investigation, has finished, and Leo is still running the navigation tests.

Two more controls cover the time you spend away from the canvas:

- **Announce finishes and questions**, under **Settings → Voice & speech → Spoken updates**, says the agent's name and workspace when a turn finishes, and speaks up when an agent has a question, even while the canvas is hidden. It is on by default; switch it off there if you prefer silence.
- An agent that stops on a question is not finished. It is waiting for you. The **Workflows** button in the launcher shows a count when agents need you, and its **Needs you** list names them. **Command–Shift–J** jumps to the next one, across workspaces.

## Read a recap instead of the transcript

States tell you where to look. Recaps tell you what happened. With no terminal focused, hold **Space**: every window turns over to a short recap, and releasing Space turns them back.

Each recap carries a state (working, done, blocked, waiting or idle) and one to three sentences, at most 55 words, on what the session did and where it stands.

![The same two windows turned over to their recaps. Felix's recap, marked done, says the timeouts come from a deadline reused by every retry and proposes a regression test. Leo's recap, marked working, says the navigation now collapses below 720px and the tests are running.](https://starkomand.com/assets/blog/resume-two-projects-with-agent-recaps/recaps.jpg)

*The same two windows with Space held. Captured from the app; the recap text is scripted to match the example tasks.*

A recap is a model's summary, so it needs a model and some of your terminal text. You choose the writer under **Settings → Privacy → Terminal recaps → Written by**:

- **Claude** or **Codex**, run through the CLI you already have installed and signed in;
- **Custom model**, any OpenAI-compatible endpoint, including one running on your Mac, in which case recaps stay on the Mac;
- **Off**, which sends nothing anywhere.

Until you choose, Starkomand uses the Claude CLI if it finds one on your Mac, otherwise Codex, and keeps recaps off when it finds neither. The Privacy panel says which one it picked.

What goes out is one terminal's transcript, rendered to plain text and trimmed to about 4,800 characters: your latest request, the start of the session and mostly the newest output. Automatic recaps run when a turn finishes or fails, at most once every five minutes per terminal and 30 calls an hour in all; a failure pauses them for 15 minutes. Holding Space asks for a fresh recap only when a terminal has new output since its last one.

Treat a recap as a pointer, not a verdict. Felix's says it found a cause and proposed a test; read that explanation in the terminal before you act on it.

## Take one next action per project

For the API investigation, check the cause and the proposed regression test against the code. If you agree, authorize the fix in the same window, or [hand the agreed implementation to a second agent with a written brief](https://starkomand.com/blog/handoff-csv-export-claude-code-to-codex/).

For the navigation change, let the tests finish, then look at the result. Ask the agent to open the local app: agents in Starkomand can open a browser preview window on the canvas beside their terminal. Check opening, dismissal, route selection and focus return at a narrow width, and compare what you see with the original request. If you want an independent check first, [ask a second agent to review the change](https://starkomand.com/blog/review-search-race-condition-with-second-agent/).

## What stays alive when you leave

Hiding Starkomand, with **Option–Command–K** or by closing its window, stops nothing. Agents keep running while the local server runs, and spoken updates still arrive.

Quitting is a choice. **Command–Q** asks "Keep agents running after you quit?" **Keep Agents Running** closes the app and leaves the background server running your agents and terminals. **Quit Completely** stops them across every workspace. Either way, your workspaces and windows are saved and return when you reopen the app.

A saved canvas is not a running agent. Restarting the Mac ends live sessions but keeps the canvas, notes and task history. If one job must outlive the app itself, Command-click or right-click its row in the launch menu to run it as a persistent agent in Herdr, a local terminal runtime; persistent agents keep running with either quit choice.

## The Starkomand features in this walkthrough

- [One workspace per project, with its own crew, layout and backdrop](https://starkomand.com/#features)
- [Agent windows that light up as they finish](https://starkomand.com/#scene-voice-title)
- [Recaps and what stays on your Mac](https://starkomand.com/#local)
- [Browser previews beside the agent that built the page](https://starkomand.com/#features)
- [Whether agents keep running when you leave](https://starkomand.com/#faq)

For why all of this lives on a canvas rather than in tabs, read [why I put coding agents on an infinite canvas](https://starkomand.com/blog/why-i-put-coding-agents-on-an-infinite-canvas/).

Try it with two jobs you already have in progress. Give each a stopping point, [start the free 3-day trial](https://starkomand.com/), and use your next meeting to see whether you come back with one clear action per project.