agent-workspace-linux
Isolated Linux desktop workspaces for AI agents, a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.
Runssource: GitHubRustMITcommit 0bc4c041d06a
Rust, MIT licensed. The project labels itself: agent, agents, ai, ai agents, browser automation, claude code, codex and desktop automation.
agent-workspace-linux runs. An Argusic agent installed it in 16 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-workspace-linux 0.6.2 builds from source, all 199 tests pass, binary runs --help and --version, starts an X11 workspace with openbox and xdotool (extracted from apt debs), launches GUI apps (xlogo), takes screenshots via ffmpeg, and responds to MCP protocol initialization.
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 100 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.
- npm prebuilt binary requires GLIBC 2.43 but system has GLIBC 2.395 minutes
- Missing openbox window manager and xdotool for workspace start3 minutes
- Test binary linking failed: rust-lld could not find -lxcb -lfreetype -lxkbcommon -lxkbcommon-x111 minute
- Install time
- 16 minutes
- Cold machine to finish
- 14 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- cargo test --locked exited 0, 199 passed (198 unit + 1 integration); workspace start --session x11 returned ok=true with daemon_pid; workspace launch xlogo returned ok=true app running=true; workspace status confirmed ready=true with 1 running app; MCP init returned valid serverInfo; --version returned 'agent-workspace-linux 0.6.2'
- Model tokens used
- 158,061
- Exact commit tested
- 0bc4c041d06a
- 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.
=== Build verification === -rwxrwxr-x 2 runner runner 284710720 Oct 31 07:54 /work/repo/target/debug/agent-workspace-linux === Test summary === 198 unit tests + 1 integration test = 199 passed, 0 failed === Workspace test === Started X11 workspace, launched xlogo app, verified running, took screenshot, stopped workspace === MCP test === MCP initialize responded with serverInfo name=agent-workspace-linux version=0.6.2 === Version === agent-workspace-linux 0.6.2 tokens used 158,061
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.
What did not, or is not known
- Took 16 minutes to install, slower than the median of the 131 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 132 agent projects Argusic has installed and timed, agent-workspace-linux was the 93rd fastest to reach a running state, and 86 of 132 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
Topics (from GitHub)
agentagentsaiai-agentsbrowser-automationclaude-codecodexdesktop-automationlinuxllmmcpmodel-context-protocolrustsandboxskillx11
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agent-workspace-linux)Questions
- Does agent-workspace-linux run?
- Yes. agent-workspace-linux runs. Argusic installed and launched it on a clean machine in 16 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test agent-workspace-linux?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0bc4c041d06a. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test agent-workspace-linux?
- The run that produced this verdict cost $0.11: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agent-workspace-linux take to install?
- 16 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-workspace-linux need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agent-workspace-linux?
- 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-workspace-linux compare with the alternatives?
- Of the 132 agent projects Argusic has installed and timed, agent-workspace-linux was the 93rd fastest to reach a running state, and 86 of 132 reached one at all.
- Where is the evidence for agent-workspace-linux?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.