Hermes Workspace AI Agent UI

Hermes Workspace AI Agent 用户界面

Skill by ara.so — Hermes Skills collection.

Hermes Workspace is a native web interface for Hermes Agent that provides chat, terminal, memory browser, skills catalog, MCP integration, multi-agent orchestration, and a complete control plane for autonomous AI workflows. Unlike chat wrappers, it's a full workspace with file browsing, persistent sessions, role-based agent dispatch, and swarm mode for managing multiple Hermes Agent workers.

由ara.so开发的Skill — Hermes Skills集合。

Hermes Workspace 是 Hermes Agent 的原生Web界面，提供聊天、终端、记忆浏览器、技能目录、MCP集成、多Agent编排，以及用于自主AI工作流的完整控制平面。与聊天包装器不同，它是一个具备文件浏览、持久会话、基于角色的Agent调度，以及用于管理多个Hermes Agent工作节点的Swarm模式的完整工作区。

What It Does

功能特性

Chat Interface: Real-time SSE streaming, tool call rendering, multi-session support, markdown + syntax highlighting
Memory Browser: Search, edit, and manage agent memory with live markdown editor
Skills Catalog: Browse 2,000+ skills with origin badges, filters, source paths
MCP Integration: Full Model Context Protocol catalog, marketplace, and source management
Terminal & Files: Monaco-powered file browser and cross-platform PTY terminal
Multi-Agent Dashboard: Manage multiple Hermes Agent instances with profile presets (Sage/Trader/Builder/Scribe/Ops)
Swarm Mode: Persistent tmux-backed agent workers with role-based dispatch and Kanban task board
Conductor: Mission decomposition and dispatch with fallback to native swarm orchestration
PWA Support: Install as native app, access over Tailscale

聊天界面：实时SSE流传输、工具调用渲染、多会话支持、Markdown语法高亮
记忆浏览器：使用实时Markdown编辑器搜索、编辑和管理Agent记忆
技能目录：浏览2000+个技能，带有来源标识、筛选器和源路径
MCP集成：完整的Model Context Protocol目录、市场和源管理
终端与文件：基于Monaco的文件浏览器和跨平台PTY终端
多Agent仪表板：使用配置文件预设（Sage/Trader/Builder/Scribe/Ops）管理多个Hermes Agent实例
Swarm模式：基于tmux的持久Agent工作节点，支持基于角色的调度和看板任务板
Conductor：任务分解与调度，可回退到原生Swarm编排
PWA支持：可安装为原生应用，通过Tailscale访问

Installation

安装

Docker Compose (Recommended for Self-Hosting)

Docker Compose (推荐自托管)

bash

undefined

bash

undefined

Clone repository

git clone https://github.com/outsourc-e/hermes-workspace.git cd hermes-workspace

Start with docker-compose

docker-compose up -d

Access at http://localhost:3000

undefined

undefined

One-Line Install (macOS/Linux)

一键安装 (macOS/Linux)

bash

curl -fsSL https://raw.githubusercontent.com/outsourc-e/hermes-workspace/main/install.sh | bash

bash

curl -fsSL https://raw.githubusercontent.com/outsourc-e/hermes-workspace/main/install.sh | bash

Terminal 1: Start Hermes Agent gateway

hermes gateway run

Terminal 2: Start workspace

cd ~/hermes-workspace && pnpm dev

undefined

cd ~/hermes-workspace && pnpm dev

undefined

Manual Installation

手动安装

bash

undefined

bash

undefined

Prerequisites: Node.js 22+, pnpm

git clone https://github.com/outsourc-e/hermes-workspace.git cd hermes-workspace

Install dependencies

pnpm install

Configure environment

cp .env.example .env

Edit .env with your settings

echo 'HERMES_API_URL=http://127.0.0.1:8642' >> .env echo 'HERMES_DASHBOARD_URL=http://127.0.0.1:9119' >> .env

Start development server

pnpm dev

undefined

pnpm dev

undefined

Attach to Existing Hermes Agent

连接到已有的Hermes Agent

If you already have a Hermes Agent gateway running:

bash

git clone https://github.com/outsourc-e/hermes-workspace.git
cd hermes-workspace
pnpm install
cp .env.example .env

如果您已经运行了Hermes Agent网关：

bash

git clone https://github.com/outsourc-e/hermes-workspace.git
cd hermes-workspace
pnpm install
cp .env.example .env

Point to existing gateway

echo 'HERMES_API_URL=http://127.0.0.1:8642' >> .env echo 'HERMES_DASHBOARD_URL=http://127.0.0.1:9119' >> .env

If gateway requires auth

echo 'HERMES_API_TOKEN=your_api_server_key' >> .env

pnpm dev

undefined

echo 'HERMES_API_TOKEN=your_api_server_key' >> .env

pnpm dev

undefined

Configuration

配置

Environment Variables

环境变量

bash

undefined

bash

undefined

Required: OpenAI-compatible backend URL

HERMES_API_URL=http://127.0.0.1:8642

Optional: Dashboard API for enhanced features

HERMES_DASHBOARD_URL=http://127.0.0.1:9119

Optional: Gateway authentication token

HERMES_API_TOKEN=your_api_server_key

Optional: UI password protection

HERMES_PASSWORD=your_password

Optional: Provider API keys (only if using these providers)

OPENAI_API_KEY=sk-... OPENROUTER_API_KEY=sk-or-v1-... GOOGLE_API_KEY=AIza... ANTHROPIC_API_KEY=sk-ant-...

Optional: Custom port

PORT=3000

undefined

PORT=3000

undefined

Gateway Requirements

网关要求

For full functionality, the Hermes Agent gateway needs:

bash

undefined

要实现完整功能，Hermes Agent网关需要：

bash

undefined

In ~/.hermes/.env or gateway config

API_SERVER_ENABLED=true API_SERVER_HOST=0.0.0.0 API_SERVER_PORT=8642

Optional: Enable authentication

API_SERVER_KEY=your_secret_key


Start gateway and dashboard:

```bash
hermes gateway run        # Port 8642
hermes dashboard          # Port 9119

API_SERVER_KEY=your_secret_key


启动网关和仪表板：

```bash
hermes gateway run        # Port 8642
hermes dashboard          # Port 9119

Remote Access (Tailscale/VPN)

远程访问 (Tailscale/VPN)

For access from remote devices:

bash

undefined

如需从远程设备访问：

bash

undefined

Use Tailscale/LAN IP instead of localhost

echo 'HERMES_API_URL=http://100.x.y.z:8642' >> .env echo 'HERMES_DASHBOARD_URL=http://100.x.y.z:9119' >> .env

Gateway must bind to 0.0.0.0

echo 'API_SERVER_HOST=0.0.0.0' >> ~/.hermes/.env

undefined

echo 'API_SERVER_HOST=0.0.0.0' >> ~/.hermes/.env

undefined

Usage Patterns

使用模式

Connecting to Local Models

连接到本地模型

Ollama

bash

undefined

bash

undefined

Start Ollama with CORS enabled

OLLAMA_ORIGINS=* ollama serve

Start workspace pointing to Ollama

HERMES_API_URL=http://127.0.0.1:11434 pnpm dev

undefined

HERMES_API_URL=http://127.0.0.1:11434 pnpm dev

undefined

LM Studio

bash

undefined

bash

undefined

Start LM Studio server on port 1234

In workspace:

HERMES_API_URL=http://127.0.0.1:1234/v1 pnpm dev

undefined

HERMES_API_URL=http://127.0.0.1:1234/v1 pnpm dev

undefined

Atomic Chat

bash

undefined

bash

undefined

Start Atomic Chat desktop app

In workspace:

HERMES_API_URL=http://127.0.0.1:1337/v1 pnpm dev

undefined

HERMES_API_URL=http://127.0.0.1:1337/v1 pnpm dev

undefined

Swarm Mode Setup

Swarm模式设置

Enable multi-agent orchestration:

bash

undefined

启用多Agent编排：

bash

undefined

Start multiple agent workers

cd ~/hermes-workspace pnpm swarm:start

View swarm docs

cat docs/swarm/README.md

Configure roles in workspace UI:

Settings → Swarm → Configure Roles

- builder: Code implementation

- reviewer: PR review and validation

- docs: Documentation

- research: Investigation

- ops: Operations and deployment

- triage: Issue classification

- qa: Quality assurance

- lab: Experiments

undefined

undefined

API Integration

API集成

For programmatic access:

typescript

// Next.js API route example
import { NextRequest, NextResponse } from 'next/server';

export async function POST(req: NextRequest) {
  const { message, sessionId } = await req.json();
  
  const response = await fetch(`${process.env.HERMES_API_URL}/v1/chat/completions`, {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'Authorization': `Bearer ${process.env.HERMES_API_TOKEN || ''}`
    },
    body: JSON.stringify({
      model: 'hermes-3',
      messages: [{ role: 'user', content: message }],
      stream: true
    })
  });
  
  return new NextResponse(response.body);
}

如需程序化访问：

typescript

// Next.js API route example
import { NextRequest, NextResponse } from 'next/server';

export async function POST(req: NextRequest) {
  const { message, sessionId } = await req.json();
  
  const response = await fetch(`${process.env.HERMES_API_URL}/v1/chat/completions`, {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'Authorization': `Bearer ${process.env.HERMES_API_TOKEN || ''}`
    },
    body: JSON.stringify({
      model: 'hermes-3',
      messages: [{ role: 'user', content: message }],
      stream: true
    })
  });
  
  return new NextResponse(response.body);
}

Custom Theme Configuration

自定义主题配置

Create or modify themes in

src/styles/themes

:

typescript

// src/styles/themes/custom.ts
export const customTheme = {
  name: 'custom',
  colors: {
    background: '#0a0a0a',
    foreground: '#ffffff',
    primary: '#6366f1',
    secondary: '#8b5cf6',
    accent: '#ec4899',
    muted: '#374151',
    border: '#1f2937'
  },
  fonts: {
    sans: 'Inter, system-ui, sans-serif',
    mono: 'JetBrains Mono, monospace'
  }
};

在

src/styles/themes

中创建或修改主题：

typescript

// src/styles/themes/custom.ts
export const customTheme = {
  name: 'custom',
  colors: {
    background: '#0a0a0a',
    foreground: '#ffffff',
    primary: '#6366f1',
    secondary: '#8b5cf6',
    accent: '#ec4899',
    muted: '#374151',
    border: '#1f2937'
  },
  fonts: {
    sans: 'Inter, system-ui, sans-serif',
    mono: 'JetBrains Mono, monospace'
  }
};

Docker Deployment

Docker部署

yaml

undefined

yaml

undefined

docker-compose.yml

version: '3.8'

services: hermes-workspace: build: . ports: - "3000:3000" environment: - HERMES_API_URL=http://hermes-gateway:8642 - HERMES_DASHBOARD_URL=http://hermes-gateway:9119 - HERMES_API_TOKEN=${HERMES_API_TOKEN} depends_on: - hermes-gateway volumes: - ./data:/app/data

hermes-gateway: image: nousresearch/hermes-agent:latest ports: - "8642:8642" - "9119:9119" environment: - API_SERVER_ENABLED=true - API_SERVER_HOST=0.0.0.0 - API_SERVER_KEY=${HERMES_API_TOKEN} - OPENAI_API_KEY=${OPENAI_API_KEY} volumes: - ./hermes-data:/root/.hermes

undefined

version: '3.8'

services: hermes-workspace: build: . ports: - "3000:3000" environment: - HERMES_API_URL=http://hermes-gateway:8642 - HERMES_DASHBOARD_URL=http://hermes-gateway:9119 - HERMES_API_TOKEN=${HERMES_API_TOKEN} depends_on: - hermes-gateway volumes: - ./data:/app/data

hermes-gateway: image: nousresearch/hermes-agent:latest ports: - "8642:8642" - "9119:9119" environment: - API_SERVER_ENABLED=true - API_SERVER_HOST=0.0.0.0 - API_SERVER_KEY=${HERMES_API_TOKEN} - OPENAI_API_KEY=${OPENAI_API_KEY} volumes: - ./hermes-data:/root/.hermes

undefined

Conductor Mission Dispatch

Conductor任务调度

typescript

// Dispatching a mission programmatically
const dispatchMission = async (mission: string) => {
  const response = await fetch('/api/conductor/dispatch', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
      mission,
      mode: 'auto', // or 'native-swarm'
      decompose: true
    })
  });
  
  const result = await response.json();
  return result;
};

// Example usage
await dispatchMission('Review and merge PR #42, update docs');

typescript

// Dispatching a mission programmatically
const dispatchMission = async (mission: string) => {
  const response = await fetch('/api/conductor/dispatch', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
      mission,
      mode: 'auto', // or 'native-swarm'
      decompose: true
    })
  });
  
  const result = await response.json();
  return result;
};

// Example usage
await dispatchMission('Review and merge PR #42, update docs');

Key Commands

关键命令

Development

开发

bash

undefined

bash

undefined

Start development server

pnpm dev

Build for production

pnpm build

Start production server

pnpm start

Run tests

pnpm test

Lint code

pnpm lint

Type check

pnpm type-check

undefined

pnpm type-check

undefined

Swarm Management

Swarm管理

bash

undefined

bash

undefined

Start swarm workers

pnpm swarm:start

Stop swarm workers

pnpm swarm:stop

View swarm status

pnpm swarm:status

Attach to worker terminal

pnpm swarm:attach <worker-name>

undefined

pnpm swarm:attach <worker-name>

undefined

Docker

bash

undefined

bash

undefined

Build image

docker build -t hermes-workspace .

Run container

docker run -p 3000:3000
-e HERMES_API_URL=http://gateway:8642
-e HERMES_DASHBOARD_URL=http://gateway:9119
hermes-workspace

Docker Compose

docker-compose up -d docker-compose logs -f docker-compose down

undefined

docker-compose up -d docker-compose logs -f docker-compose down

undefined

Troubleshooting

故障排除

Connection Issues

连接问题

bash

undefined

bash

undefined

Verify gateway is running

curl http://127.0.0.1:8642/health

Expected: {"status":"ok"}

Verify dashboard is running

curl http://127.0.0.1:9119/api/status

Expected: dashboard metadata JSON

Check gateway logs

hermes gateway run --verbose

Check workspace logs

pnpm dev

Look for connection probe results

undefined

undefined

Authentication Failures

认证失败

bash

undefined

bash

undefined

Ensure API_SERVER_KEY matches HERMES_API_TOKEN

In gateway config (~/.hermes/.env):

API_SERVER_KEY=your_secret

In workspace .env:

HERMES_API_TOKEN=your_secret

Or disable auth entirely:

Remove API_SERVER_KEY from gateway

Remove HERMES_API_TOKEN from workspace

undefined

undefined

Features Not Appearing

功能未显示

bash

undefined

bash

undefined

Check capability detection in browser console:

Settings → Connection → Test Connection

Verify dashboard is running for enhanced features:

ps aux | grep "hermes dashboard"

Check HERMES_DASHBOARD_URL is set correctly:

echo $HERMES_DASHBOARD_URL

Restart both services:

pkill -f "hermes gateway" pkill -f "hermes dashboard" hermes gateway run & hermes dashboard &

undefined

pkill -f "hermes gateway" pkill -f "hermes dashboard" hermes gateway run & hermes dashboard &

undefined

Swarm Workers Not Starting

Swarm工作节点未启动

bash

undefined

bash

undefined

Check tmux sessions

tmux ls

Verify worker processes

ps aux | grep hermes

Check worker logs

tail -f ~/.hermes/logs/worker-*.log

Reset swarm state

pnpm swarm:stop rm -rf ~/.hermes/swarm-state pnpm swarm:start

undefined

pnpm swarm:stop rm -rf ~/.hermes/swarm-state pnpm swarm:start

undefined

Memory/Performance Issues

内存/性能问题

bash

undefined

bash

undefined

Increase Node.js memory

NODE_OPTIONS="--max-old-space-size=4096" pnpm dev

Clear workspace cache

rm -rf .next pnpm build

Check Docker resource limits

docker stats

Increase in Docker Desktop settings if needed

undefined

undefined

Remote Access Not Working

远程访问无法工作

bash

undefined

bash

undefined

Verify gateway binds to 0.0.0.0

grep API_SERVER_HOST ~/.hermes/.env

Should be: API_SERVER_HOST=0.0.0.0

Test from remote device

curl http://<tailscale-ip>:8642/health

Check firewall rules

sudo ufw status sudo ufw allow 8642/tcp sudo ufw allow 9119/tcp

Verify Tailscale connectivity

tailscale status ping <tailscale-ip>

undefined

tailscale status ping <tailscale-ip>

undefined

Build Errors

构建错误

bash

undefined

bash

undefined

Clear all caches and reinstall

rm -rf node_modules .next pnpm-lock.yaml pnpm install pnpm build

Verify Node.js version

node --version

Must be 22.0.0 or higher

Check for TypeScript errors

pnpm type-check

undefined

pnpm type-check

undefined

Advanced Configuration

高级配置

Custom Skills Integration

自定义技能集成

bash

undefined

bash

undefined

Add custom skills directory

export HERMES_SKILLS_PATH=/path/to/custom/skills

Skills should follow format:

/custom/skills/

├── skill-name/

│ ├── SKILL.md

│ └── metadata.json

undefined

undefined

Persistent Sessions

持久会话

bash

undefined

bash

undefined

Sessions stored in ~/.hermes/sessions/

Backup sessions:

tar -czf sessions-backup.tar.gz ~/.hermes/sessions/

Restore sessions:

tar -xzf sessions-backup.tar.gz -C ~/

undefined

tar -xzf sessions-backup.tar.gz -C ~/

undefined

Custom API Routes

自定义API路由

typescript

// app/api/custom/route.ts
import { NextRequest } from 'next/server';

export async function POST(req: NextRequest) {
  // Custom endpoint logic
  const data = await req.json();
  
  // Forward to gateway with custom headers
  const response = await fetch(`${process.env.HERMES_API_URL}/custom`, {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'X-Custom-Header': 'value'
    },
    body: JSON.stringify(data)
  });
  
  return response;
}

typescript

// app/api/custom/route.ts
import { NextRequest } from 'next/server';

export async function POST(req: NextRequest) {
  // Custom endpoint logic
  const data = await req.json();
  
  // Forward to gateway with custom headers
  const response = await fetch(`${process.env.HERMES_API_URL}/custom`, {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'X-Custom-Header': 'value'
    },
    body: JSON.stringify(data)
  });
  
  return response;
}

Resources

资源

GitHub: https://github.com/outsourc-e/hermes-workspace
Documentation: https://hermes-workspace.com
Hermes Agent: https://github.com/NousResearch/hermes-agent
Swarm Docs:
```
docs/swarm/README.md
```
in repository
Issues: https://github.com/outsourc-e/hermes-workspace/issues

GitHub: https://github.com/outsourc-e/hermes-workspace
文档: https://hermes-workspace.com
Hermes Agent: https://github.com/NousResearch/hermes-agent
Swarm文档: 仓库中的
```
docs/swarm/README.md
```
问题反馈: https://github.com/outsourc-e/hermes-workspace/issues

hermes-workspace-ai-agent-ui

Original

Translation

Hermes Workspace AI Agent UI

Hermes Workspace AI Agent 用户界面

What It Does

功能特性

Installation

安装

Docker Compose (Recommended for Self-Hosting)

Docker Compose (推荐自托管)

Clone repository

Clone repository

Start with docker-compose

Start with docker-compose

Access at http://localhost:3000

Access at http://localhost:3000

One-Line Install (macOS/Linux)

一键安装 (macOS/Linux)

Terminal 1: Start Hermes Agent gateway

Terminal 1: Start Hermes Agent gateway

Terminal 2: Start workspace

Terminal 2: Start workspace

Manual Installation

手动安装

Prerequisites: Node.js 22+, pnpm

Prerequisites: Node.js 22+, pnpm

Install dependencies

Install dependencies

Configure environment

Configure environment

Edit .env with your settings

Edit .env with your settings

Start development server

Start development server

Attach to Existing Hermes Agent

连接到已有的Hermes Agent

Point to existing gateway

Point to existing gateway

If gateway requires auth

If gateway requires auth

Configuration

配置

Environment Variables

环境变量

Required: OpenAI-compatible backend URL

Required: OpenAI-compatible backend URL

Optional: Dashboard API for enhanced features

Optional: Dashboard API for enhanced features

Optional: Gateway authentication token

Optional: Gateway authentication token

Optional: UI password protection

Optional: UI password protection

Optional: Provider API keys (only if using these providers)

Optional: Provider API keys (only if using these providers)

Optional: Custom port

Optional: Custom port

Gateway Requirements

网关要求

In ~/.hermes/.env or gateway config

In ~/.hermes/.env or gateway config

Optional: Enable authentication

Optional: Enable authentication

Remote Access (Tailscale/VPN)

远程访问 (Tailscale/VPN)

Use Tailscale/LAN IP instead of localhost

Use Tailscale/LAN IP instead of localhost

Gateway must bind to 0.0.0.0

Gateway must bind to 0.0.0.0

Usage Patterns

使用模式

Connecting to Local Models

连接到本地模型

Ollama

Ollama

Start Ollama with CORS enabled

Start Ollama with CORS enabled

Start workspace pointing to Ollama

Start workspace pointing to Ollama

LM Studio