hermes-desktop
Desktop Companion for Hermes Agent
Runs with mockssource: GitHubTypeScriptMITcommit 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 25 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Hermes Desktop builds and all 2308 tests pass on Node 22 with both TypeScript typechecks and ESLint passing clean, plus lat.md cross-references validate
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
Subject data from GitHub, linked at the top of this page. 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.
- OPENROUTER_API_KEY in global process.env contaminates resolvedSecretMap() causing config-health test to falsely pass5 minutes
- Node 18.19.1 is too old: @electron/get is ESM-only and fails with ERR_REQUIRE_ESM on postinstall2 minutes
- Lint prettier warnings from edited test file1 minute
- Install time
- 25 minutes
- Cold machine to finish
- 20 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- npm test exited 0 with 221 test files and 2308 tests passed; tsc --noEmit -p tsconfig.node.json and tsconfig.web.json produce no output (pass); eslint --max-warnings=0 . exits 0
- Model tokens used
- 325,923
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
Duration 1.90s (transform 531ms, setup 255ms, import 157ms, tests 697ms, environment 584ms) Let me also verify a final `lat check` and confirm there's nothing architectural that needs updatin… exec /bin/sh -lc 'export NVM_DIR="$HOME/.nvm"; [ -s "$NVM_DIR/nvm.sh" ] && '"\\. \""'$NVM_DIR/nvm.sh" &&… succeeded in 2593ms: Now using node v22.23.3 (npm v10.9.9) Scanned 1 .conf, 2 .css, 1 .example, 1 .gif, 28 .glb, 1 .html, 1 .icns, 1 .ico, 23 .js, 6 .json, 35… All checks passed Here's the final report: tokens used 325,923 Here's the final report:
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 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
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 25 minutes to install, slower than the median of the 44 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 45 ai projects Argusic has installed and timed, hermes-desktop was the 42nd fastest to reach a running state, and 36 of 45 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.08 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](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 25 minutes, hitting 3 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. One attempt is 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 $0.08: 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?
- 25 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?
- 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 hermes-desktop compare with the alternatives?
- Of the 45 ai projects Argusic has installed and timed, hermes-desktop was the 42nd fastest to reach a running state, and 36 of 45 reached one at all.
- Where is the evidence for hermes-desktop?
- 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.