hermes-desktop

Desktop Companion for Hermes Agent

Runs with mockssource: GitHubhomepageTypeScriptMITcommit 2ed89070bc6c

TypeScript, MIT licensed. The project labels itself: ai, ai agent, autonomous agents, chatbot, hermes and llm.

hermes-desktop runs, with stand-ins for the services it depends on. An Argusic agent installed it in 19 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The app builds, all 2308 tests pass, and the Electron window launches on the virtual display; via the UI it walks Welcome -> install confirmation and connects to a local mock gateway where a typed message returns a streamed reply. The real upstream Hermes Agent install was not exercised.

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 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.28 (measured)
recorded runs
2
last tested
stars
14,582
forks
1,637
open issues
336
watchers
76
size
38 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 hermes-desktop, 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.

  • vitest tests/config-health.test.ts failed: expected MODEL_KEY_MISSING issue to be defined but got undefined6 minutes
  • npm install failed: electron postinstall ERR_REQUIRE_ESM requiring @electron/get from electron/install.js on Node v18.19.15 minutes
  • npm run dev crashed with EMFILE: too many open files watching /work/repo/src/renderer4 minutes
  • Remote connect opened an OAuth sign-in window loading /login and returned 4044 minutes
  • Electron aborted: SUID sandbox helper not owned by root (no root in container)3 minutes
  • Remote connect failed with TypeError: fetch failed / ECONNREFUSED 127.0.0.1:19080 from main process3 minutes
Install time
19 minutes
Cold machine to finish
20 minutes
Errors hit and fixed
6 hit, 6 fixed with no human help
How the result was proved
npx vitest run --maxWorkers=4 exited 0 with 221 test files passed / 2308 tests passed; npm run build exited 0; electron --no-sandbox --version printed v44.1.1; CDP read of the live app showed Welcome then Install confirm at /home/runner/.hermes/hermes-agent, then after connecting to a local mock gateway it showed the chat UI and rendered streamed reply 'Hello from the mock Hermes gateway'
Model tokens used
1,121,930
Exact commit tested
2ed89070bc6c
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
Behaviour against real services
this run was verified against stand-in services only

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

- `npm install` first failed: `electron@44`'s postinstall hit `ERR_REQUIRE_ESM` on the container's …
- `npm run build` exits 0 (typecheck + electron-vite build).
**Tests**
- First run: 1 of 2308 failed — `tests/config-health.test.ts` "flags MODEL_KEY_MISSING…". Diagnosed…
**Launch**
- Electron aborted on the container's unrooted SUID sandbox; launched with `electron-vite preview -…
- Drove the real UI over CDP: Welcome screen rendered, "Get Started" → install confirmation at `/ho…
- Stood up a schema-correct mock gateway and connected through "Connect to Remote Hermes" (first at…
**Notes**
- `lat` wasn't on PATH; installed `lat.md` from npm. `lat check` passes, and I updated `lat.md/prov…
- Dev mode (`npm run dev`) hits `EMFILE` in Vite's watcher (`max_user_instances=128`); used the pro…
- The real upstream Hermes Agent (~2GB install script) was not run; verification used a mock gatewa…

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

  • Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
  • 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

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 19 minutes to install, slower than the median of the 234 comparable projects Argusic has measured.

Of the 235 ai projects Argusic has installed and timed, hermes-desktop was the 199th fastest to reach a running state, and 166 of 235 reached one at all.

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 Runner2/3Runs with mocks92.000.28
Argusic Runner1/3Runs with mocks92.000.08

Topics (from GitHub)

aiai-agentautonomous-agentschatbothermesllm

Embed the badge

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

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

Questions

Does hermes-desktop run?
hermes-desktop runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 19 minutes, hitting 6 errors on the way, and recorded the session.
How did Argusic test hermes-desktop?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 2ed89070bc6c. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test hermes-desktop?
The run that produced this verdict cost $0.28: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does hermes-desktop take to install?
19 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 hermes-desktop need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing hermes-desktop?
6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does hermes-desktop compare with the alternatives?
Of the 235 ai projects Argusic has installed and timed, hermes-desktop was the 199th fastest to reach a running state, and 166 of 235 reached one at all.
Where is the evidence for hermes-desktop?
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