mrkeyoor.comAsk

asheshgoplani/agent-decktested 01 Oct 2026commit 035fd60

agent-deck review

Evaluate Agent Deck for supervised management of multiple coding-agent sessions.

  • Install 73 s
  • Build 95 s
68/73passed, run exited non-zero
  • 275 packages
Automationevaluationupdated 31 Oct 2026
+21stars / 7d

Choose Agent Deck if switching between coding-agent sessions and preparing separate worktrees has become a recurring chore. Start with supervised local sessions: our run on October 1, 2026, at commit 035fd60 did not establish that a working agent fleet could run unattended. Agent Deck is a terminal session manager for AI coding agents. Its documented features include session status, grouping, search, forking, Git worktrees, MCP management and a remote conductor.

Verdict

Evaluate Agent Deck for supervised management of multiple coding-agent sessions. Our October 1, 2026 run at commit 035fd60 completed installation and build, but tests timed out and the raw tail exposed missing tmux. That supports a local trial with the prerequisites installed; it does not establish unattended fleet reliability. Compare Claude Squad for agent task workspaces, or use plain tmux when manual terminal management meets your needs.

We ran it

Lab card: what happened when we ran agent-deck
Lab card from our sandbox run
Screenshot of agent-deck (discord.gg/e4xSs6NBN8)
discord.gg/e4xSs6NBN8
Install✓ · 73s275 packages
Build✓ · 95s
Tests✗ timed out · 900s68 passed · 5 failed of 73 (go test)
Repo4104 files~755,161 lines of source · 179 MB · 31 CI workflows · tests dir

Answers from our run

Does agent-deck build from source?

Dependencies installed in 73 seconds (275 packages), and the build succeeded in 95 seconds. We cloned commit 035fd60 into a clean Debian container with 3 CPUs and no project-specific setup.

Do agent-deck's tests pass?

No. The project's own test command finished in 900 seconds and reported 68 passed, 5 failed (go test).

Who should not use agent-deck?

Readers seeking a verified unattended deployment: our sandbox did not establish that outcome.

What are the alternatives to agent-deck?

Claude Squad, tmux. Evaluate Agent Deck for supervised management of multiple coding-agent sessions.

Setup3/5Under the visible rubric, usable with material qualifications: our sandbox installed in 73 seconds and built in 95 seconds, but missing tmux prevented validation of the session workflow.
Docs5/5Under the visible rubric, unusually complete within the supplied documentation scope: installation routes, session controls, worktree behavior and operational caveats are concrete. Feature correctness was not established by reading them.
Community4/5Under the visible rubric, strong activity evidence with limits: supplied metadata shows a recent push and the README provides contribution guidance. Adoption, contributor retention and actual support response times were not measured.
Maturity3/5Under the visible rubric, usable with material qualifications: the documented feature scope is broad, but our test command timed out. Stored parser summaries record 68 passing and 5 failing package results, total 73, without exhaustive unique coverage verification.

Discussed on

  1. hnAgent Deck3 points
  2. hnShow HN: Agent Deck – Terminal Dashboard to Manage Claude/Gemini/Codex Sessions3 points

Who it’s for

Developers managing coding agents across several projects who want a shared session list.
Terminal users who want worktree creation and agent-session controls in one interface.
Operators prepared to verify their agent CLI, authentication and tmux setup before adding remote supervision.

Who it’s NOT for

Readers seeking a verified unattended deployment: our sandbox did not establish that outcome.
Users expecting a successful build to prove that agent login, session creation or remote control works.
Native Windows users who cannot use WSL; the supplied README lists Windows support through WSL.
Anyone expecting Docker sessions to prevent changes to the project directory, which remains mounted read-write.

Setup reality

In our sandbox, installation returned exit code 0 after 73 seconds and the build returned exit code 0 after 95 seconds. The test command timed out after 900 seconds with exit code 124. These are the attached harness values for our October 1, 2026 run at commit 035fd60, not a new execution.

The stored parser summaries record 68 passing and 5 failing package results, with a total of 73. They do not establish exhaustive unique test coverage. The raw tail separately shows tests failing because tmux was missing from PATH. It does not establish the cause of every recorded failure or of the timeout.

The README documents a shell installer, Homebrew, Go installation and installation from source. It lists macOS, Linux and Windows through WSL. Our source build did not validate those other installation routes, an authenticated agent workload, an interactive TUI session, Docker isolation or conductor delivery.

Should you use Agent Deck?

Agent Deck is worth evaluating when you repeatedly lose track of coding-agent sessions or recreate worktrees by hand. Its README describes a single terminal interface for session status and switching, with groups, search, forks and worktree controls. Those features address a concrete coordination problem. If your existing terminal arrangement is easy to follow, there is less reason to add another manager.

Agent Deck is a terminal session manager for AI coding agents. That description comes from the repository metadata; the broader feature descriptions below come from its documentation rather than a completed agent workflow in our sandbox.

Our run built successfully but could not validate tmux workflows

Our run took place on October 1, 2026, at commit 035fd60 (full SHA: 035fd602eda5e3ed7e95edb63b6418fbe285f74d). The recorded sandbox had 3 CPUs, 8 GB of memory and the golang:1.24-bookworm image. The installation tail records a download of Go 1.25.13, so the image label alone does not identify the toolchain used throughout the run.

In our sandbox, installation returned exit code 0 after 73 seconds and the build returned exit code 0 after 95 seconds. The test command timed out after 900 seconds with exit code 124. The build tail contains vet-exit:0; neither that line nor a zero command exit establishes that an agent session was launched successfully.

Our harness stores each command's outcome, elapsed time, exit code, timeout flag and available output tail, alongside parsed test results. The testing-methodology page explains this reporting approach and its limits. Its supplied October 31 description is provenance context, not evidence that this older run used every detail of today's procedure.

The attached stored parser summaries record 68 passing and 5 failing package results, with a total of 73. These are package-result summaries, not counts of individual test cases or verified exhaustive unique coverage. The raw record also lists 4 packages without tests; we have not added those to the attached total or reconstructed a different aggregate.

The raw tail shows TestListAgentDeckCodexSessionIDsOnSocket failing because tmux was unavailable. It also shows missing-tmux errors in control-client, startup-timeout, status-expiry and orphan-client tests. These named failures are separate observations from the aggregate parser summary. They establish an environment limitation in our sandbox, not that every affected feature is broken on a correctly provisioned machine. The tail does not explain every failing package or why the entire command reached its timeout.

We did not validate agent authentication, interactive session switching, a coding workload, account separation, remote conductor delivery or Docker isolation. No audit result is attached, and scan coverage is unknown. This run supports an installation and build observation, not a security assessment or an unattended-operation recommendation.

Worktrees and conductors need different checks

The README at the measured commit documents forks that inherit conversation history through supported tools' native fork mechanisms. It also documents Git worktrees with separate branches. These are useful starting points for trying competing changes, but branch separation does not establish that credentials or external services are isolated.

The same README says .worktreeinclude can copy files that both match its patterns and are ignored by Git. Review those patterns before creating agent workspaces, especially when they include environment files or secrets directories. Its Docker section says the project directory is bind-mounted read-write, so a containerized agent can still edit that code.

A conductor adds a different responsibility: the documentation describes a persistent supervising session and remote channels, with watchers able to wake it from outside events. Our run did not exercise that path. Evaluate local session creation and switching first, then test the particular channel, credentials and watcher behavior you intend to operate. The available evidence does not justify carrying forward the earlier page's watcher-queue diagnosis or treating its old account and tmux issue reports as verified current defects.

Compare a session manager with a terminal multiplexer

Claude Squad manages multiple coding agents in separate Git workspaces. Its README also documents change review and checkout controls. Compare it with Agent Deck when task workspaces and reviewing agent changes are your main needs. The supplied extracts do not establish that either product is more reliable or that Claude Squad lacks remote features.

Tmux creates and controls multiple terminals from one screen and can keep them running after detachment. Choose plain tmux when you want to arrange and revisit terminals yourself. It also underlies the session approach documented for Agent Deck, so it is both a simpler manual option and part of the environment you need to verify, rather than an interchangeable agent supervisor.

How to read the scores

These are editorial assessments, not benchmark results. The scale is 1 for substantial obstacles, 2 for notable gaps, 3 for usable with material qualifications, 4 for strong supporting evidence with remaining limits, and 5 for unusually complete evidence within the assessed scope.

Setup ease is 3: installation and build completed, but missing tmux prevented the sandbox from establishing a working session path. Documentation is 5 for the supplied material's specific installation routes, controls, configuration behavior and operational caveats; that score does not certify every documented feature. Community is 4 for visible project activity and contribution guidance, not measured adoption or support response time. Maturity is 3 because the documented scope is broad while our test command remained unfinished and operational behavior was not validated.

For your first evaluation, install tmux and one supported agent CLI, confirm the agent's own login, and create a disposable session in a repository you can safely change. Verify switching, restarting and worktree behavior before adding conductor automation. That check resolves the main gap our sandbox left open.

Alternatives

ProjectWhat it isPick it when
Claude Squad gh↗A terminal app for multiple coding agents in separate Git workspaces.Compare it when separate task workspaces and reviewing changes before applying them are your main requirements. Its supplied README supports those roles, but does not establish a reliability advantage over Agent Deck.
tmux gh↗A terminal multiplexer with detachable sessions that continue running in the background.Use it directly when you can manage terminal sessions yourself. It is also part of Agent Deck's documented session environment, so this is a manual alternative and an underlying component.

What people are saying

  1. [github-trending] asheshgoplani/agent-deck

Sources

  1. Agent Deck README
  2. GitHub repository metadata
  3. Agent Deck v1.15.0 release
  4. Issue 2060: Codex account environment
  5. Issue 2061: unbounded tmux terminal features
  6. Issue 2062: dead-letter operations gap

More automation reviews