agent-deck
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
Runssource: GitHubhomepageGoMITcommit 3d7cb43acf1b
Go, MIT licensed. The project labels itself: ai agent, ai agents, ai coding assistant, aider, bubble tea, claude code, cli and codex.
agent-deck runs. An Argusic agent installed it in 37 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Agent-deck vdev builds and runs in the container. The binary responds to version, help, and ls commands. 34 of 34 directly testable internal packages pass. The WebSocket terminal bridge functions correctly. Only pre-existing environment-specific test failures: keepalive client-count assertions (container PTY behavior) and systemd service tests (no systemd --user).
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 96 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- TestWSKeepaliveReapsDeadPeer and TestWSKeepaliveHealthyClientSurvives fail in this container3 minutes
- Go compiler not installed2 minutes
- tmux not installed1 minute
- Install time
- 37 minutes
- Cold machine to finish
- 62 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- go build ./... exited 0 (full module compiles); binary outputs correct 'Agent Deck vdev' for version/help; 34 internal packages pass (statedb, tmux, session, web, agentpaths, atomicfile, childenv, costs, credrefresh, docker, experiments, feedback, fleet, git, intervalhook, jujutsu, logging, mcppool, openclaw, pathsafety, platform, procfd, profile, releasetests, safego, selfheal, send, shellwords, sysinfo, telemetry, terminal, termreply, tmuxutf8, vcsbackend, watcher, desknotify); 7 testutil subpackages pass; cmd/agent-deck version tests pass; WebSocket integration test passes; 2 keepalive WS tests fail due to container PTY quirks (client-count assertion), 2 tmux service tests skip (no systemd --user)
- Model tokens used
- 218,536
- Exact commit tested
- 3d7cb43acf1b
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
/bin/sh -lc 'export PATH=/tmp/go/bin:/home/runner/.local/bin:$HOME/.local/bin:$PATH; GOPATH=$HOME/g… exec /bin/sh -lc 'export PATH=/tmp/go/bin:/home/runner/.local/bin:$HOME/.local/bin:$PATH; GOPATH=$HOME/g… exited 127 in 0ms: TIME: minutes elapsed /bin/sh: 1: bc: not found Here's my final comprehensive report: 2026-09-19T02:18:11.600473Z ERROR codex_core::session: failed to record rollout items: thread 01a0b… 2026-09-19T02:18:11.600786Z ERROR codex_core::session: failed to record rollout items: thread 01a0b… tokens used 218,536 Here's my final comprehensive report:
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 37 minutes to install, slower than the median of the 11 comparable projects Argusic has measured.
Of the 12 ai-agent projects Argusic has installed and timed, agent-deck was the 12th fastest to reach a running state, and 9 of 12 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.25 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.12 |
Topics (from GitHub)
ai-agentai-agentsai-coding-assistantaiderbubble-teaclaude-codeclicodexdeveloper-toolsdiscordgemini-cligolangmcpproductivitysession-managerterminaltmuxtui
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agent-deck)Questions
- Does agent-deck run?
- Yes. agent-deck runs. Argusic installed and launched it on a clean machine in 37 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test agent-deck?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3d7cb43acf1b. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test agent-deck?
- The run that produced this verdict cost $0.25: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agent-deck take to install?
- 37 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does agent-deck need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agent-deck?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does agent-deck compare with the alternatives?
- Of the 12 ai-agent projects Argusic has installed and timed, agent-deck was the 12th fastest to reach a running state, and 9 of 12 reached one at all.
- Where is the evidence for agent-deck?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.