threadport
Portable, verifiable work state for coding agents
Runssource: GitHubhomepageTypeScriptApache-2.0commit 249363bfbb87
TypeScript, Apache-2.0 licensed. The project labels itself: ai agents, coding agents, context engineering, developer tools, local first, mcp and session handoff.
threadport runs. An Argusic agent installed it in 5.2 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
ThreadPort 0.2.1 built from source, all 523 unit tests pass, the CLI validates schemas, renders capsules, reports diagnostics, and lists targets without errors.
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.
- Node 18 is installed but the project requires Node >=242 minutes
- Test control-plane.test.ts uses hardcoded expiry date '2026-09-30' which is past current date (2026-10-31), causing receipt status to be 'expired' instead of 'pending'1.5 minutes
- Install time
- 5 minutes
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- npm test: 83 test files passed, 523 tests passed, 3 skipped (exit 0). CLI verify: 'node dist/src/cli.js validate examples/capsule-v1.json' returned 'valid'. CLI doctor: reported ThreadPort 0.2.1 with no errors. CLI render: produced correct Markdown output. CLI --help: listed all commands.
- Model tokens used
- 38,598
- Exact commit tested
- 249363bfbb87
- 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.
"claude-jsonl-v1",
"codex-jsonl-v1"
],
"errors": []
}
=== Finished ===
Everything is working. Let me compile the final result.
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 5.2, "…
tokens used
38,598
Everything is working. Let me compile the final result.
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 5.2, "…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.
- Installed in 5.2 minutes, faster than the median of the 109 comparable projects Argusic has measured.
- Recovered from all 2 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 Apache-2.0, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 110 ai-agents projects Argusic has installed and timed, threadport was the 48th fastest to reach a running state, and 81 of 110 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.
- A quick evaluation: it was running 5.2 minutes after the clone.
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)
ai-agentscoding-agentscontext-engineeringdeveloper-toolslocal-firstmcpsession-handoff
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/threadport)Questions
- Does threadport run?
- Yes. threadport runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test threadport?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 249363bfbb87. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test threadport?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does threadport take to install?
- 5.2 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 threadport need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing threadport?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does threadport compare with the alternatives?
- Of the 110 ai-agents projects Argusic has installed and timed, threadport was the 48th fastest to reach a running state, and 81 of 110 reached one at all.
- Where is the evidence for threadport?
- 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.