mirror of
https://github.com/EKKOLearnAI/hermes-web-ui.git
synced 2026-05-26 22:10:15 +00:00
Rivera Todd
13061f8880
Two issues prevented the gateway from starting in docker-compose: 1. gateway-manager used 'hermes-agent' as default host when running inside a container, causing startAll() to skip gateway startup (remote host guard) and proxy requests to an unreachable hostname. Changed to use GATEWAY_HOST env var with fallback to '127.0.0.1' so the webui container manages its own gateway via the shared hermes binary. 2. hermes refuses to run as root inside the official Docker image. The hermes-webui container overrides the entrypoint (bypassing the privilege- drop script), so the node process runs as root. Added HERMES_ALLOW_ROOT_GATEWAY=1 to docker-compose.yml to allow this.
Hermes Web UI 中文
A full-featured web dashboard for Hermes Agent.
Manage AI chat sessions, monitor usage & costs, configure platform channels,
schedule cron jobs, browse skills — all from a clean, responsive web interface.
npm install -g hermes-web-ui && hermes-web-ui start
Features
AI Chat
- Real-time streaming via SSE with async run support
- Multi-session management — create, rename, delete, switch between sessions
- Self-built session database — local SQLite storage with automatic sync from Hermes state.db on first startup
- Session grouping by source (Telegram, Discord, Slack, etc.) with collapsible accordion
- Active session indicator — live sessions pin to top with spinner icon
- Sessions sorted by latest message time
- Markdown rendering with syntax highlighting and code copy
- Tool call detail expansion (arguments / result)
- File upload support
- File download support — download user-uploaded files and agent-generated files across local, Docker, SSH, and Singularity backends
- Session search — Ctrl+K global search across all conversations
- Global model selector — discovers models from
~/.hermes/auth.jsoncredential pool - Per-session model display badge and context token usage
Platform Channels
Unified configuration for 8 platforms in one page:
| Platform | Features |
|---|---|
| Telegram | Bot token, mention control, reactions, free-response chats |
| Discord | Bot token, mention, auto-thread, reactions, channel allow/ignore lists |
| Slack | Bot token, mention control, bot message handling |
| Enable/disable, mention control, mention patterns | |
| Matrix | Access token, homeserver, auto-thread, DM mention threads |
| Feishu (Lark) | App ID / Secret, mention control |
| QR code login (scan in browser, auto-save credentials) | |
| WeCom | Bot ID / Secret |
- Credential management writes to
~/.hermes/.env - Channel behavior settings write to
~/.hermes/config.yaml - Auto gateway restart on config change
- Per-platform configured/unconfigured status detection
Usage Analytics
- Total token usage breakdown (input / output)
- Session count with daily average
- Estimated cost tracking & cache hit rate
- Model usage distribution chart
- 30-day daily trend (bar chart + data table)
Scheduled Jobs
- Create, edit, pause, resume, delete cron jobs
- Trigger immediate execution
- Cron expression quick presets
Model Management
- Auto-discover models from credential pool (
~/.hermes/auth.json) - Fetch available models from each provider endpoint (
/v1/models) - Add, update, and delete providers (preset & custom OpenAI-compatible)
- OpenAI Codex & Nous Portal OAuth login
- Provider URL auto-detection for non-v1 API versions (e.g.
/v4) - Provider-level model grouping with default model switching
Multi-Profile & Gateway
- Create, rename, delete, and switch between Hermes profiles
- Clone existing profile or import from archive (
.tar.gz) - Export profile for backup or sharing
- Multi-gateway management — start, stop, and monitor gateway per profile
- Auto port conflict resolution
- Profile-scoped configuration and cache isolation
File Browser
- Browse files on remote backends (local, Docker, SSH, Singularity)
- Upload, download, rename, copy, move, and delete files
- Create directories
- View file content with syntax highlighting
Group Chat
- Multi-agent chat rooms with real-time messaging via Socket.IO
- @mention routing — mention an agent to trigger a contextual reply
- Context compression — automatic conversation summarization when history exceeds token threshold
- Typing status and reply progress indicators
- Room creation, deletion, and invite code management
- Agent management — add/remove agents from rooms with per-agent profiles
- SQLite message persistence
- Mobile responsive with collapsible sidebar
Skills & Memory
- Browse and search installed skills
- View skill details and attached files
- User notes and profile management
Logs
- View agent / gateway / error logs
- Filter by log level, log file, and keyword
- Structured log parsing with HTTP access log highlighting
Authentication
- Token-based auth (auto-generated on first run or set via
AUTH_TOKENenv var) - Optional username/password login — set via settings page after initial token auth
- Auth can be disabled with
AUTH_DISABLED=1
Settings
- Display (streaming, compact mode, reasoning, cost display)
- Agent (max turns, timeout, tool enforcement)
- Memory (enable/disable, char limits)
- Session reset (idle timeout, scheduled reset)
- Privacy (PII redaction)
- Model settings (default model & provider)
- API server configuration
Web Terminal
- Integrated terminal powered by node-pty and @xterm/xterm
- Multi-session support — create, switch between, and close terminal sessions
- Real-time keyboard input and PTY output streaming via WebSocket
- Window resize support
Quick Start
npm (Recommended)
npm install -g hermes-web-ui
hermes-web-ui start
One-line Setup (Auto-detect OS)
Automatically installs Node.js (if missing) and hermes-web-ui on Debian/Ubuntu/macOS:
bash <(curl -fsSL https://raw.githubusercontent.com/EKKOLearnAI/hermes-web-ui/main/scripts/setup.sh)
WSL
bash <(curl -fsSL https://raw.githubusercontent.com/EKKOLearnAI/hermes-web-ui/main/scripts/setup.sh)
hermes-web-ui start
WSL auto-detects and uses
hermes gateway runfor background startup (no launchd/systemd).
Docker Compose
Run Web UI together with Hermes Agent:
# Use pre-built image (Recommended)
WEBUI_IMAGE=ekkoye8888/hermes-web-ui:latest docker compose up -d hermes-agent hermes-webui
# Or build from source
docker compose up -d --build hermes-agent hermes-webui
docker compose logs -f hermes-webui
- Persistent Hermes data is stored in
./hermes_data - Web UI auth token is stored in
./hermes_data/hermes-web-ui/.token - On first run with auth enabled, the token is printed to container logs
- All runtime settings are environment-variable driven in
docker-compose.yml
For detailed notes and troubleshooting, see docs/docker.md.
CLI Commands
| Command | Description |
|---|---|
hermes-web-ui start |
Start in background (daemon mode) |
hermes-web-ui start --port 9000 |
Start on custom port |
hermes-web-ui stop |
Stop background process |
hermes-web-ui restart |
Restart background process |
hermes-web-ui status |
Check if running |
hermes-web-ui update |
Update to latest version & restart |
hermes-web-ui -v |
Show version number |
hermes-web-ui -h |
Show help message |
Auto Configuration
On startup the BFF server automatically:
- Validates
~/.hermes/config.yamland fills missingapi_serverfields - Backs up original config to
config.yaml.bakif modified - Detects and starts the gateway if needed
- Resolves port conflicts (kills stale processes)
- Opens browser on successful startup
Development
git clone https://github.com/EKKOLearnAI/hermes-web-ui.git
cd hermes-web-ui
npm install
npm run dev
- Frontend: http://localhost:5173
- BFF Server: http://localhost:8648 (proxies to Hermes on 8642)
npm run build # outputs to dist/
Architecture
Browser → BFF (Koa, :8648) → Hermes Gateway (:8642)
↓
Hermes CLI (sessions, logs, version)
↓
~/.hermes/config.yaml (channel behavior)
~/.hermes/auth.json (credential pool)
Tencent iLink API (WeChat QR login)
The frontend is designed with multi-agent extensibility — all Hermes-specific code is namespaced under hermes/ directories (API, components, views, stores), making it straightforward to add new agent integrations alongside.
The BFF layer handles API proxy (with path rewriting), SSE streaming, file upload and download (multi-backend: local/Docker/SSH/Singularity), session CRUD via CLI, config/credential management, WeChat QR login, model discovery, skills/memory management, log reading, and static file serving.
Tech Stack
Frontend: Vue 3 + TypeScript + Vite + Naive UI + Pinia + Vue Router + vue-i18n + SCSS + markdown-it + highlight.js
Backend: Koa 2 (BFF server) + node-pty (web terminal)