HermesOffice

AI-native office suite (Docs, Sheets, Slides, PDF) where the Hermes Agent is the brain, open standards, byte-preserving round-trip, 100% local.

Runssource: GitHubTypeScriptApache-2.0commit 05c5512e75cf

TypeScript, Apache-2.0 licensed. The project labels itself: agent, ai native, docx, electron, hermes, local first, mcp and office suite.

HermesOffice runs. An Argusic agent installed it in 2 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

HermesOffice repository installs, builds all 6 Electron apps, passes all ~6900 unit tests across 18 workspaces, and launches the Electron shell app on an Xvfb display.

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
$0.05 (measured)
recorded runs
2
last tested
stars
589
forks
77
open issues
27
watchers
3
size
45 MB
created
last push

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.

Time lost to each failure while testing HermesOffice, 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.

  • Node v18 installed but project requires >=22.12.0; npm install emitted EBADENGINE warnings1 minute
  • Rust/cargo not found — sheets native:test and native:build would fail1 minute
  • Electron chrome-sandbox not SUID (no root access)
Install time
2 minutes
Cold machine to finish
18 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
npm test passed: ~6900 tests across 18 workspaces all green; npx electron apps/shell/out/main/index.js --no-sandbox --disable-gpu --disable-software-rasterizer --no-zygote launched on :99 and remained alive (kill -0 confirmed)
Model tokens used
146,999
Exact commit tested
05c5512e75cf
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.

| @hermesoffice/sheets | 171 (1 skipped) | 1978 passed, 1 skipped |
| @hermesoffice/shell | 19 | 234 passed |
| @hermesoffice/slides | 61 (1 skipped) | 648 passed, 8 skipped |
| @hermesoffice/pdf | 42 | 575 passed |
| @hermesoffice/markdown | 10 | 145 passed |
**Launch verification:**
- Electron shell app started on Xvfb display `:99` with `--no-sandbox --disable-gpu --disable-softw…
**Errors encountered:**
1. Node v18 installed, project needs >=22.12.0 — fixed by extracting Node 22.12.0 into `~/.local/bi…
2. Rust/cargo not found for sheets sidecar — fixed by installing Rust via rustup
3. Electron SUID sandbox issue (no root for `chmod 4755`) — worked around with `--no-sandbox`
4. HTMLCanvasElement not implemented in vitest/JSDOM — cosmetic warnings only, all tests passed

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 2 minutes, faster than the median of the 32 comparable projects Argusic has measured.
  • 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 Apache-2.0, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

Of the 33 agent projects Argusic has installed and timed, HermesOffice was the 9th fastest to reach a running state, and 25 of 33 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 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.05
Argusic Runner1/3Runs100.000.08

Topics (from GitHub)

agentai-nativedocxelectronhermeslocal-firstmcpoffice-suiteopen-sourcepdfpptxreacttypescriptuniverxlsx

Embed the badge

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

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

Questions

Does HermesOffice run?
Yes. HermesOffice runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test HermesOffice?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 05c5512e75cf. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test HermesOffice?
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 HermesOffice take to install?
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 HermesOffice need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing HermesOffice?
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 HermesOffice compare with the alternatives?
Of the 33 agent projects Argusic has installed and timed, HermesOffice was the 9th fastest to reach a running state, and 25 of 33 reached one at all.
Where is the evidence for HermesOffice?
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.

Discussion