The app had a single cyan accent, so every emphasis in the chat chain was a shade of the same hue. An approval waiting on the user, a tool that had already run, a streaming response and an outright error all looked equally urgent — the hue carried no information at all. The colours are now split by meaning rather than by shade, and the rule is documented at the top of variables.scss so it survives future edits: cyan the system itself brand, primary buttons, selection, user bubbles amber needs you approval cards, context about to fill lime the machine works tool execution, assistant output, streaming red something failed errors only — deliberately not a palette member Red staying out is the load-bearing part: when failure reuses the accent family the urgency signal disappears entirely. `--warning` moves from yellow (hue 85) to amber (hue 68) and `--success` from a muted green to fluorescent lime (hue 128). Because both are global tokens, every page using them changes hue in the same pass; the Arco `--green-*` / `--orange-*` bridges are updated with them so solid controls follow instead of staying behind. Six translucent companions (`--success-soft`, `--warning-line`, …) were added for fills and borders. On the chat surface: the approval card goes amber with a slow pulse on its icon — the only moving part in the chain, marking the one thing that is genuinely waiting. Tool-change cards and assistant bubbles take a 2px lime left edge meaning "already ran"; user bubbles get a cyan right edge so the two sides read apart without labels. The context meter is green under 60%, amber to 80%, red above; those thresholds already existed and only the colours were wrong. Rendering-layer only. No store logic, no /chat-run payload, no markup or event wiring.
hermes-ui
Self-hosted web dashboard for Hermes Agent — chat, session history, skills, MCP servers, model management, IM channels, file management, and usage analytics in one browser UI.
This project is under active rebuild. Feature work is being staged phase by phase; see
docs/phases/README.mdfor the current plan.
Prerequisites
hermes-ui runs as a plain Node.js server. It does not bundle a runtime.
- Node.js
>=23 - Python with
hermes-agentinstalled
Install hermes-agent, then either put hermes on your PATH or point HERMES_BIN at the
executable:
export HERMES_BIN=/path/to/hermes
If the CLI cannot be found, the UI shows an install hint instead of failing silently.
Getting Started
npm ci --ignore-scripts
npm run build
npm start
Then open http://localhost:8648 and log in with the default credentials printed on first start.
For development with hot reload:
npm run dev
The client runs on http://localhost:8649 and the Koa server on port 8647.
Layout
packages/client Vue 3 client: views, components, Pinia stores, i18n, API helpers
packages/server Koa API, Socket.IO chat runtime, SQLite stores, Hermes integration
packages/skills Built-in skills injected into the Hermes skills directory
tests Vitest unit/integration tests and Playwright browser tests
scripts Build and repository harness scripts
docs Architecture, harness docs, and the phased build plan
Docker
docker compose up -d
The image is based on nousresearch/hermes-agent, so Python and the Hermes CLI are already
present in the container.
Configuration
| Variable | Purpose |
|---|---|
HERMES_BIN |
Path to the hermes executable. Falls back to hermes on PATH. |
HERMES_HOME |
Hermes profile directory. Used to isolate profiles. |
HERMES_WEB_UI_HOME |
Web UI state directory. Defaults to ~/.hermes-web-ui. |
HERMES_WEBUI_STATE_DIR |
Alternate override for the Web UI state directory. |
PORT |
Server port. |
The HERMES_WEB_UI_* prefixes and the ~/.hermes-web-ui data directory are kept from the
0.6.x line on purpose, so existing deployments and data directories keep working.
Commands
| Command | Description |
|---|---|
npm run dev |
Run client and server with hot reload. |
npm run build |
Type-check and build client and server bundles. |
npm start |
Serve the production build. |
npm run test |
Run Vitest tests. |
npm run test:coverage |
Run Vitest with coverage. |
npm run test:e2e |
Run Playwright browser tests. |
npm run harness:check |
Validate repository docs, workflows, and package scripts. |
npm run openapi:generate |
Regenerate docs/openapi.json. |
License
BSL-1.1. See LICENSE.