nesquena/hermes-webui
AI Agent · tested 2026-10-01 · by the Hlido desk, not the vendor
In short: A lightweight, phone-friendly web front end for Nous Research's Hermes Agent — useful precisely because it claims full parity with the CLI, not a watered-down subset.
4 PASS · 1 FAIL of 5 public-surface claims
Quick answer
nesquena/hermes-webui scores 80/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-10-01). STEADY (80) for a focused, well-scoped access layer that promises CLI parity and phone access to a credible underlying agent (Hermes, Nous Research lineage), with a clean documented setup.
Hermes WebUI is a companion surface, and it is honest about that: it is a dark-themed web and mobile front end for the Hermes Agent (a persistent, server-resident autonomous agent from the Nous Research orbit), and its central claim is full parity with the terminal experience — everything you can do from the CLI, you can do here. That parity framing is the right one; a web UI that silently drops capabilities is worse than no UI, and promising parity is a commitment worth holding the project to. Because the real engine is Hermes Agent itself (persistent context, scheduled offline jobs, improvement over time), this entry's value is almost entirely a function of that underlying agent — the WebUI is the access layer. This is a public-surface and repository read, not an installed, driven session, so the verdict covers the stated parity and the shape of the offering rather than a measured confirmation that parity actually holds across every CLI action, which is exactly what a user should check on setup.
Why STEADY
STEADY (80) for a focused, well-scoped access layer that promises CLI parity and phone access to a credible underlying agent (Hermes, Nous Research lineage), with a clean documented setup. Not higher because its value is derivative of the Hermes Agent it fronts, and the parity claim — the whole point — was read on the public surface, not verified action-by-action in this review.
Public-surface checklist
- PASS Homepage loads (required)
- PASS Primary value prop (required)
- FAIL Cta present (required)
- PASS Pricing or access
- PASS Evidence or demo
What we saw
1 screenshot captured by the Hlido engine during the reviewed run (run-b6042c4f4021a7bc-github-com). Our own captures — not vendor marketing material.
What it does well
- Claims full parity with the Hermes CLI rather than a reduced feature subset
- Brings a persistent server-side agent to the browser and the phone
- Lightweight, dark-themed interface scoped to one clear job
- Fronts a credible underlying agent (Hermes, Nous Research lineage)
- Documented setup path for self-hosting the UI
What it fails at
- Value is derivative — it is only as good as the Hermes Agent behind it
- The headline CLI-parity claim was read, not verified action-by-action here
- Requires running and maintaining the underlying Hermes Agent server
- Narrow by design — it is an access layer, not an agent in its own right
Best for
- Existing Hermes Agent users who want browser and mobile access
- Developers who want a persistent server-side agent reachable from a phone
- Users comfortable self-hosting both the agent and its UI
Not recommended for
- Users not already committed to the Hermes Agent
- Buyers wanting a self-contained agent rather than a front end
- Non-technical users who cannot run the backing server
Pricing & access
- Pricing findable on the public surfacePASS
Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-06-16.
Compared to
-
goose
access-layer
Goose is a full local agent; Hermes WebUI is a front end for a specific server-side agent. Choose Hermes WebUI if you are already on Hermes and want web/mobile access, Goose if you want the agent itself.
Agent relevance
CLI
Hermes WebUI is a human access layer for the Hermes Agent rather than a programmatic surface for other agents. The underlying Hermes Agent is CLI-driven and server-resident; the WebUI mirrors that for human use.
Agent-friendly score: 4/10
Score over time
The longitudinal record — every point is the score as published on that date. Raw series.
Evidence
scorecard.json · transparency passport · registry · methodology
Embed this trust badge
Markdown
[](https://hlido.eu/check/?agent=nesquena-hermes-webui)HTML
<a href="https://hlido.eu/check/?agent=nesquena-hermes-webui"><img src="https://hlido.eu/badge/nesquena-hermes-webui.svg" alt="Hlido trust score"></a>