@NFTCPS: Hermes 这波直接把 Agent 天花板给掀了! 全网程序员已经开始用它搭桌面神器、跑创意流水线、省 token 省到飞起——你还没跟上? 先说 hermes-desktop,CLI 小玩具直接进化成 Mac/Windows 原生桌面…
摘要
本文介绍了围绕Hermes Agent构建的五个开源工具项目,包括桌面应用、创意工作流、共享记忆层、token压缩工具和监控仪表板,旨在扩展Agent的生态系统。
查看缓存全文
缓存时间: 2026/05/13 16:23
Hermes 这波直接把 Agent 天花板给掀了! 全网程序员已经开始用它搭桌面神器、跑创意流水线、省 token 省到飞起——你还没跟上? 先说 hermes-desktop,CLI 小玩具直接进化成 Mac/Windows 原生桌面 App,一键装好就能聊,多平台消息 + 自进化循环,这才叫真正的桌面伴侣。 https://github.com/fathah/hermes-desktop… hermes-agent-idea-workflow 是给创意党准备的,脑子里一个粗糙想法,丢进去直接给你吐出 PRD + 设计文档 + 任务拆解,脑暴效率直接起飞。 https://github.com/AkoliteZA/hermes-agent-idea-workflow… plur 解决了一个老大难问题——多个 Agent 实例之间记忆不互通。它用 open engram YAML 做共享记忆层,知识跨实例永不丢,Agent 终于有集体大脑了。 https://github.com/plur-ai/plur rtk-hermes 是省钱黑科技,shell 输出自动压缩 60-90% 的 token,实战跑了 1100 万+ token 验证过的,上下文爆炸?不存在的。 https://github.com/ogallotti/rtk-hermes… hermesd 给运维党看,实时只读 TUI 仪表盘,10 大面板一眼监控 Gateway、Sessions、Tokens、Cron、Memory,Agent 在干啥一目了然。 https://github.com/mudrii/hermesd 五个方向,五个开源项目,把 Hermes 玩成了下一代 Agent 的完整生态。现在不上车,等啥呢?
fathah/hermes-desktop
Source: https://github.com/fathah/hermes-desktop
This project is in active development. Features may change, and some things might break. If you run into a problem or have an idea, open an issue. Contributions are welcome!
Languages
- English:
README.md - 简体中文:
README.zh-CN.md
Hermes Desktop is a native desktop app for installing, configuring, and chatting with Hermes Agent — a self-improving AI assistant with tool use, multi-platform messaging, and a closed learning loop.
Instead of managing the CLI by hand, the app walks through install, provider setup, and day-to-day usage in one place. It uses the official Hermes install script, stores Hermes in ~/.hermes, and gives you a GUI for chat, sessions, profiles, memory, skills, tools, scheduling, messaging gateways, and more.
Install
Download the latest build from the Releases page.
| Platform | File |
|---|---|
| macOS | .dmg |
| Linux (any) | .AppImage |
| Linux (Debian) | .deb |
| Linux (Fedora) | .rpm |
| Windows | .exe (NSIS installer) |
Windows (winget)
Once the manifest has been accepted into microsoft/winget-pkgs, you can install with:
winget install NousResearch.HermesDesktop
Until then, download the .exe from the Releases page.
Windows users: The installer is not code-signed. Windows SmartScreen will warn on first launch — click “More info” → “Run anyway”.
WSL users: If the installer stalls at
Switching to root user to install dependencies..., Playwright is waiting for a sudo password that has no TTY to read from. Grant passwordless sudo for the install, then revert when finished:echo "$USER ALL=(ALL) NOPASSWD: ALL" | sudo tee /etc/sudoers.d/hermes-install # …re-run the installer; once it finishes: sudo rm /etc/sudoers.d/hermes-installTracked in #109.
Fedora (RPM)
sudo dnf install ./hermes-desktop-<version>.rpm
Fedora users: The
.rpmis not GPG-signed. If your system enforces signature checking, append--nogpgcheckto the install command. Auto-update is not supported for.rpmbuilds (limitation ofelectron-updater); reinstall the new.rpmto update.
macOS
macOS users: The app is not code-signed or notarized. macOS will block it on first launch. To fix this, run the following after installing:
xattr -cr "/Applications/Hermes Agent.app"Or right-click the app → Open → click Open in the confirmation dialog.
Features
- Guided first-run install for Hermes Agent with progress tracking and dependency resolution
- Local or remote backend — run Hermes locally on
127.0.0.1:8642, or connect the desktop app to a remote Hermes API server with URL + API key - Multi-provider support — OpenRouter, Anthropic, OpenAI, Google (Gemini), xAI (Grok), Nous Portal, Qwen, MiniMax, Hugging Face, Groq, and local OpenAI-compatible endpoints (LM Studio, Ollama, vLLM, llama.cpp)
- Streaming chat UI with SSE streaming, tool progress indicators, markdown rendering, and syntax highlighting
- Token usage tracking — live prompt/completion token counts and cost display in the chat footer, plus a
/usageslash command - 22 slash commands —
/new,/clear,/fast,/web,/image,/browse,/code,/shell,/usage,/help,/tools,/skills,/model,/memory,/persona,/version,/compact,/compress,/undo,/retry,/debug,/status, and more - Session management — full-text search (SQLite FTS5), date-grouped history, resume and search across conversations
- Profile switching — create, delete, and switch between separate Hermes environments with isolated config
- 14 toolsets — web, browser, terminal, file, code execution, vision, image gen, TTS, skills, memory, session search, clarify, delegation, MoA, and task planning
- Memory system — view/edit memory entries, user profile memory, capacity tracking, and discoverable memory providers (Honcho, Hindsight, Mem0, RetainDB, Supermemory, ByteRover)
- Persona editor — edit and reset your agent’s SOUL.md personality
- Saved models — CRUD management for model configurations across providers
- Scheduled tasks — cron job builder (minutes, hourly, daily, weekly, custom cron) with 15 delivery targets
- 16 messaging gateways — Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Mattermost, Email (IMAP/SMTP), SMS (Twilio/Vonage), iMessage (BlueBubbles), DingTalk, Feishu/Lark, WeCom, WeChat (iLink Bot), Webhooks, Home Assistant
- Hermes Office (Claw3d) — visual 3D interface with dev server and adapter management
- Backup, import & debug dump — full data backup/restore and system diagnostics from Settings
- Log viewer — view gateway and agent logs directly from the Settings screen
- Auto-updater — check for and install updates via electron-updater
- i18n ready — internationalization framework with English locale covering all screens, ready for community translations
- Test suite — SSE parser, IPC handlers, preload API surface, installer utilities, and constants validation with Vitest
Preview
| Office |
Chat |
| Profiles |
Tools |
| Settings |
Skills |
How It Works
On first launch, the app:
- Asks whether you want to run Hermes locally or connect to a remote Hermes API server.
- Local mode: checks whether Hermes is already installed in
~/.hermes; if not, runs the official Hermes installer with dependency resolution (Git, uv, Python 3.11+). - Remote mode: prompts for the remote API URL and API key, validates the connection, and skips local install.
- Prompts for an API provider or local model endpoint.
- Saves provider config and API keys through Hermes config files.
- Launches the main workspace once setup is complete.
In local mode, chat requests go through http://127.0.0.1:8642 with SSE streaming. In remote mode, the app talks to your configured remote URL with the same streaming protocol. The desktop app parses the stream in real time, rendering tool progress, markdown content, and token usage as it arrives.
Screens
| Screen | Description |
|---|---|
| Chat | Streaming conversation UI with slash commands, tool progress, and token tracking |
| Sessions | Browse, search, and resume past conversations |
| Agents | Create, delete, and switch between Hermes profiles |
| Skills | Browse, install, and manage bundled and installed skills |
| Models | Manage saved model configurations per provider |
| Memory | View/edit memory entries, user profile, and configure memory providers |
| Soul | Edit the active profile’s persona (SOUL.md) |
| Tools | Enable or disable individual toolsets |
| Schedules | Create and manage cron jobs with delivery targets |
| Gateway | Configure and control messaging platform integrations |
| Office | Claw3d visual interface setup and management |
| Settings | Provider config, credential pools, backup/import, log viewer, network settings, theme |
Supported Providers
LLM Providers
| Provider | Notes |
|---|---|
| OpenRouter | 200+ models via single API (recommended) |
| Anthropic | Direct Claude access |
| OpenAI | Direct GPT access |
| Google (Gemini) | Google AI Studio |
| xAI (Grok) | Grok models |
| Nous Portal | Free tier available |
| Qwen | QwenAI models |
| MiniMax | Global and China endpoints |
| Hugging Face | 20+ open models via HF Inference |
| Groq | Fast inference (voice/STT) |
| Local/Custom | Any OpenAI-compatible endpoint |
Local presets are included for LM Studio, Ollama, vLLM, and llama.cpp.
Messaging Platforms
Telegram, Discord, Slack, WhatsApp, Signal, Matrix/Element, Mattermost, Email (IMAP/SMTP), SMS (Twilio & Vonage), iMessage (BlueBubbles), DingTalk, Feishu/Lark, WeCom, WeChat (iLink Bot), Webhooks, and Home Assistant.
Tool Integrations
Exa Search, Parallel API, Tavily, Firecrawl, FAL.ai (image generation), Honcho, Browserbase, Weights & Biases, and Tinker.
Development
Prerequisites
- Node.js and npm
- A Unix-like shell environment for the Hermes installer
- Network access for downloading Hermes during first-run install
Install dependencies
npm install
Start the app in development
npm run dev
Run checks
npm run lint
npm run typecheck
Run tests
npm run test
npm run test:watch
Build the desktop app
npm run build
Platform packaging:
npm run build:mac
npm run build:win
npm run build:linux
npm run build:rpm # Fedora/RHEL .rpm only
First-Time Setup
When the app opens for the first time, it will either detect an existing Hermes installation or offer to install it for you.
Supported setup paths in the UI:
OpenRouterAnthropicOpenAILocal LLMvia an OpenAI-compatible base URL
Local presets are included for:
- LM Studio
- Ollama
- vLLM
- llama.cpp
Hermes files are managed in:
~/.hermes~/.hermes/.env~/.hermes/config.yaml~/.hermes/hermes-agent~/.hermes/profiles/— named profile directories~/.hermes/state.db— session history database~/.hermes/cron/jobs.json— scheduled tasks
Tech Stack
- Electron 39 — cross-platform desktop shell
- React 19 — UI framework
- TypeScript 5.9 — type safety across main and renderer processes
- Tailwind CSS 4 — utility-first styling
- Vite 7 + electron-vite — fast dev server and build tooling
- better-sqlite3 — local session storage with FTS5 full-text search
- i18next — internationalization framework
- Vitest — test runner
Notes
- The desktop app depends on the upstream Hermes Agent project for agent behavior and tool execution.
- The built-in installer runs the official Hermes install script with
--skip-setup, then completes provider configuration in the GUI. - Local model providers do not require an API key, but the compatible server must already be running.
- Alternative npm registry routes are supported for environments with restricted network access.
Contributing
Contributions are welcome! Check out the Contributing Guide to get started. If you’re not sure where to begin, take a look at the open issues. Found a bug or have a feature request? File an issue.
Related Project
For the core agent, docs, and CLI workflows, see the main Hermes Agent repository:
- https://github.com/NousResearch/hermes-agent
相似文章
@FakeMaidenMaker: Hermes Agent 终于有了桌面应用啦! 想用 Hermes Agent,都要打开 terminal 配 provider、装 skill、改 cron 都得敲命令,光看 ~/.hermes 那堆 yaml 和 env 文件就头大。…
Hermes Desktop 是 Hermes Agent 的桌面 GUI 伴侣,提供图形化安装、配置和聊天功能,支持 11 个 LLM provider 和 16 个消息平台,简化了 CLI 操作。
@GitTrend0x: Hermes 谁用谁舒服!超级应用研发! 强化 fork 版、阿里云记忆插件、Felo 营销技能包、Awesome 社区圣经、轻量 Web UI…… 全网程序员把 Hermes 玩成了下一代 Agent 深度 hack 神器 + 云端集体…
Hermes Agent及其生态工具集在开发者社区中引发关注,包括强化fork版、阿里云记忆插件、Felo技能包、社区圣经和轻量Web UI,展示了AI Agent的深度定制和云端协作能力。
@hisevenih: Hermes Agent 终于出官方桌面版了。 这次是官方版本,Mac OS、Windows、Linux 都能装。我刚下下来试了一圈,整体体验还挺顺手,至少不用再折腾一堆环境配置了。 Hermes支持从 OpenClaw 迁移,所以对老用…
Hermes Agent 发布官方桌面版,支持 Mac、Windows、Linux,提供多平台集成和持久记忆等功能。
@NFTCPS: Hermes 生态要炸了,你还没上车? Nous Research 的 Hermes Agent 这波社区爆发真的猛。一堆开发者开始往上堆插件、堆适配器、堆记忆系统,感觉整个生态正在从"一个模型"变成"一套完整的 Agent 操作系统"。…
Nous Research 的 Hermes Agent 生态正在快速扩展,开发者社区贡献了大量插件、适配器和记忆系统(如 HermesHub 技能市场、企业适配器、本地记忆插件等),使 Hermes 从单一模型演变为完整的 Agent 操作系统。
@VincentLogic: 发现个挺有意思的 AI 助手客户端! Hermes Agent,界面做得挺清爽的中文桌面应用。功能集成得挺全: - 对话、会话管理 - 多模型支持 - 技能、工具集成 - 定时任务、网关配置 从界面看能帮你:搜索网页、设置提醒、总结邮件、…
Hermes Agent 是一款基于 Electron 开发的跨平台 AI 助手桌面客户端,支持多模型切换、技能集成与定时任务等功能,旨在为用户提供统一的 AI 效率工作台。