nesquena /hermes-webui
Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!
★ 19,531⑂ 2,836👁 60⑃ 6,738● 2,318▤ 1,852
+13
Daily
+157
Weekly
+652
Monthly
19,531
stars
2,836
forks
60
watchers
6,738
prs
2,318
issues
1,852
releases
README
Hermes Web UI
Hermes Agent is a sophisticated autonomous agent that lives on your server, accessed via a terminal or messaging apps, that remembers what it learns and gets more capable the longer it runs.
Hermes WebUI is a lightweight, dark-themed web app interface in your browser for Hermes Agent.
Full parity with the CLI experience - everything you can do from a terminal, you can do from this UI. No build step, no framework, no bundler. Just Python and vanilla JS.
Layout: three-panel. Left sidebar for sessions and navigation, center for chat,
right for workspace file browsing. Model, profile, and workspace controls live in
the composer footer — always visible while composing. A circular context ring
shows token usage at a glance. All settings and session tools are in the
Hermes Control Center (launcher at the sidebar bottom).
Setup Hermes so you can access it natively on every device:
Light mode with full profile support
Customize your settings, configure a password
Workspace file browser with inline preview
Session projects, tags, and tool call cards
This gives you nearly 1:1 parity with Hermes CLI from a convenient web UI which you can access securely through an SSH tunnel from your Hermes setup. Single command to start this up, and a single command to SSH tunnel for access on your computer. Every single part of the web UI uses your existing Hermes agent and existing models, without requiring any additional setup.
---
Contents
- Why Hermes — what it is and how it compares
- Quick start — clone + bootstrap.py / start.sh / ctl.sh
- Features — chat, sessions, workspace, voice, profiles, security, themes, panels, mobile
- Configuration & access — auto-discovery, overrides, remote/Tailscale/phone, manual launch
- Nix flake/module — declarative install and service
- Docker — single- and multi-container deploys
- Running tests
- Architecture — backend/frontend layout, state dir
- Docs — the full documentation index
- Contributors
---
Why Hermes
Most AI tools reset every session. They don't know who you are, what you worked on, or what
conventions your project follows. You re-explain yourself every time.
Hermes retains context across sessions, runs scheduled jobs while you're offline, and gets
smarter about your environment the longer it runs. It uses your existing Hermes agent setup,
your existing models, and requires no additional configuration to start.
What makes it different from other agentic tools:
- Persistent memory — user profile, agent notes, and a skills system that saves reusable
procedures; Hermes learns your environment and does not have to relearn it
- Self-hosted scheduling — cron jobs that fire while you're offline and deliver results to
Telegram, Discord, Slack, Signal, email, and more
- 10+ messaging platforms — the same agent available in the terminal is reachable from your phone
- Self-improvingTop issues
#1925RFC: Make WebUI a thin observability/control client over Hermes Agent runtime28 comments · 2026-05-08#5619Web UI config discrepancy with multi-profiles21 comments · 2026-07-05#3400Redesign live-to-final assistant replies for running agent sessions20 comments · 2026-06-02#6876Hermes agent is not responding18 comments · 2026-08-09#7310WebUI stalls under load: /api/session full-transcript reconciliation takes 4-7s and stacks threads on a single-threaded server17 comments · 2026-08-26#6880Bug: server-initiated re-entry can bypass turn serialization across compression lineage14 comments · 2026-08-09#2761WebUI mid-conversation: "No LLM provider configured" bricks the session until a fork; assistant response sometimes vanishes into an "Auto-compressing..." card; model silently reverts to gpt-5.4-mini13 comments · 2026-05-22#6351High RAM usage over time: SESSIONS LRU cache + StreamChannel buffers accumulate ~1.7 GB on long runs11 comments · 2026-07-20
Discussions
#8199Should background manual compression switch the active conversation back?1 comments · 2026-10-13#8197image uploads make sessions heavy.0 comments · 2026-10-13#8018How do I actually get the ElevenLabs TTS engine to play? Listen button is silent while the server path is verified working1 comments · 2026-10-04#7951Compatibility policy could be clearer.0 comments · 2026-10-01#7609When to expect the next stable release0 comments · 2026-09-16#7411A plea to change this project's name0 comments · 2026-09-03#7403Bot support0 comments · 2026-09-02#7392Notifications for PWA?1 comments · 2026-09-01
Latest release
v0.52.678 v0.52.678 2026-11-15Known issues - Context meter after a reload or model switch (8975). For some sessions on custom or self-hosted endpoints, the context meter can show the default window (256K) instead of the model's real window after a page reload or a model switch. It corrects itself on the next turn. Compression and chats are unaffected. Context-management plugins that read WebUI's context window see the same default until then. - Credentials can pair with the wrong URL on Agent builds after hermes-agent 151775 when a providers: entry named like a built-in provider has its own URL and model.base_url dif