Yes. sem runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 1 error on the way, and recorded the session.

How did Argusic test sem?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 55ba2f1d8fc6. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test sem?

The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does sem take to install?

14.7 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing sem?

1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.

Where is the evidence for sem?

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.

sem

Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 28 languages via tree-sitter. Built for coding agents.

Runssource: GitHub homepageRustApache-2.0commit 55ba2f1d8fc6

Rust, Apache-2.0 licensed. The project labels itself: ai agents, code intelligence, coding agents, developer tools, git, llm tools, semantic diff and tree sitter.

sem runs. An Argusic agent installed it in 14.7 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Semantic version control tool builds, all core tests pass, and the binary produces correct entity-level semantic diffs on real TypeScript/JavaScript/Python files with and without Git repos.
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

verdict: Runs
Argusic Score: 100 / 100
cost of the verifying run: $0.10 (measured)
recorded runs: 1
last tested: 2026-09-07
stars: 3,359
forks: 102
open issues: 3
watchers: 7
size: 6 MB
created: 2026-02-05
last push: 2026-09-22

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-23. 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.

Time lost to each failure while testing sem, drawn from the recorded run — Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

Flaky test persist::disk_cache::tests::precomputed_columns_match_internal_fusion intermittently fails with SqliteFailure(SystemIoFailure) when running in parallel — tempfs contention in the test harness's temp_repo_root function0.3 minutes

Install time: 15 minutes
Cold machine to finish: 24 minutes
Errors hit and fixed: 1 hit, 1 fixed with no human help
Model tokens used: 154,479
Exact commit tested: 55ba2f1d8fc6
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.

How the result was proved: runs before 2026-09-07 did not record the command used to check the result
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.

{"summary":{"fileCount":1,"added":0,"modified":1,"deleted":1,"moved":0,"renamed":0,"reordered":0,"b…
Entity-level diff works perfectly — it detected `greet` modified and `farewell` deleted as entities…
Let me compute time from start. The rustup install began at session start and the entire process to…
exec
/bin/sh -lc 'echo "Start: $(stat -c %Y /proc/1/cmdline 2>/dev/null)"; date +%s' in /work/repo
 succeeded in 0ms:
Start: 1788795229
1788796110
881 seconds elapsed, about 14.7 minutes. The installation and testing process took a while due to R…
tokens used
154,479
881 seconds elapsed, about 14.7 minutes. The installation and testing process took a while due to R…

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 1 error 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

Took 14.7 minutes to install, slower than the median of the 11 comparable projects Argusic has measured.
Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 12 ai-agents projects Argusic has installed and timed, sem was the 9th fastest to reach a running state, and 8 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	1/3	Runs	100.00	0.10	2026-09-07 15:48 UTC

Topics (from GitHub)

ai-agents code-intelligence coding-agents developer-tools git llm-tools semantic-diff tree-sitter typescript version-control

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/sem.svg)](https://argusic.com/subject/sem)

Questions

Does sem run?: Yes. sem runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test sem?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 55ba2f1d8fc6. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test sem?: The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does sem take to install?: 14.7 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 sem need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing sem?: 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does sem compare with the alternatives?: Of the 12 ai-agents projects Argusic has installed and timed, sem was the 9th fastest to reach a running state, and 8 of 12 reached one at all.
Where is the evidence for sem?: 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.

sem