### Example Skill Installations

Source: https://hermes-agent.nousresearch.com/docs/reference/optional-skills-catalog

Examples of installing specific skills from the official catalog. The first example installs a Solana skill, and the second installs a flash-attention skill.

```bash
hermes skills install official/blockchain/solana
```

```bash
hermes skills install official/mlops/flash-attention
```

--------------------------------

### Run WhatsApp Setup Wizard

Source: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/whatsapp

Execute this command to start the interactive setup wizard for the WhatsApp bridge. The wizard will guide you through selecting a mode, installing dependencies, and scanning a QR code to link your WhatsApp account.

```bash
hermes whatsapp  

```

--------------------------------

### Start WhatsApp Cloud API Setup Wizard

Source: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/whatsapp-cloud

Run this command to initiate the setup wizard for the WhatsApp Business Cloud API integration. The wizard guides through credential input and provides follow-up instructions.

```bash
hermes whatsapp-cloud  

```

--------------------------------

### Hermes Pets CLI Quick Start

Source: https://hermes-agent.nousresearch.com/docs/user-guide/features/pets

Basic CLI commands for browsing, installing, previewing, and checking pet setup.

```bash
# Browse the gallery (filter by substring)  
hermes pets list  
hermes pets list cat  
  
# Install a pet and make it active in one step  
hermes pets install boba --select  
  
# Preview / animate it in your terminal (Ctrl+C to stop)  
hermes pets show  
  
# Check your setup  
hermes pets doctor  
```

--------------------------------

### Hermes Agent Quick Start Commands

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/bundled/autonomous-ai-agents/autonomous-ai-agents-hermes-agent

Install the Hermes Agent, start an interactive chat, run a single query, initiate the setup wizard, change the model, or check the agent's health.

```bash
# Install  
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash  
  
# Interactive chat (default)  
hermes  
  
# Single query  
hermes chat -q "What is the capital of France?"  
  
# Setup wizard  
hermes setup  
  
# Change model/provider  
hermes model  
  
# Check health  
hermes doctor  
```

--------------------------------

### Setup Bitwarden Secrets Manager Integration

Source: https://hermes-agent.nousresearch.com/docs/reference/cli-commands

The `setup` subcommand initiates an interactive wizard to install the `bws` binary, store an access token, and select a project. Non-interactive setup can be achieved using `--project-id`, `--access-token`, and `--server-url` flags.

```bash
hermes secrets bitwarden setup --project-id <project-id> --access-token <access-token> --server-url <server-url>
```

--------------------------------

### Quick Start: Create, Configure, and Install Gateways

Source: https://hermes-agent.nousresearch.com/docs/user-guide/multi-profile-gateways

Use these commands to create new profiles, set up each agent, and install them as managed services. This ensures each gateway restarts automatically on crash and on user login.

```bash
# Create profiles (once)  
hermes profile create coder  
hermes profile create personal-bot  
hermes profile create research  
  
# Configure each  
coder setup  
personal-bot setup  
research setup  
  
# Install each gateway as a managed service  
coder gateway install  
personal-bot gateway install  
research gateway install  
  
# Start them all  
coder gateway start  
personal-bot gateway start  
research gateway start  

```

--------------------------------

### Install and Start LiteLLM Proxy

Source: https://hermes-agent.nousresearch.com/docs/integrations/providers

Install the LiteLLM Python package and start the proxy server with a specified model and port, or use a configuration file for multiple models.

```bash
# Install and start
pip install "litellm[proxy]"
litellm --model anthropic/claude-sonnet-4 --port 4000

# Or with a config file for multiple models:
litellm --config litellm_config.yaml --port 4000

```

--------------------------------

### Install Workspace Dependencies and Run Dev Server

Source: https://hermes-agent.nousresearch.com/docs/user-guide/desktop

Install dependencies from the repository root and then start the development server from the desktop application directory. This command boots the Vite renderer and Electron, which in turn starts the Python backend.

```bash
npm install          # from repo root — links apps/desktop, web, apps/shared  
cd apps/desktop  
npm run dev          # Vite renderer + Electron, which boots the Python backend  
```

--------------------------------

### skills.sh Examples

Source: https://hermes-agent.nousresearch.com/docs/user-guide/features/skills

Search, inspect, and install skills from the skills.sh directory.

```bash
hermes skills search react --source skills-sh  
hermes skills inspect skills-sh/vercel-labs/json-render/json-render-react  
hermes skills install skills-sh/vercel-labs/json-render/json-render-react --force
```

--------------------------------

### Set Dashboard Credentials and Start

Source: https://hermes-agent.nousresearch.com/docs/user-guide/desktop

Configure the dashboard's username, password, and signing secret in the .env file, then start the dashboard bound to a reachable address. This setup is for trusted networks only.

```bash
# 1. Set the dashboard login credentials.  
cat >> ~/.hermes/.env <<'EOF'  
HERMES_DASHBOARD_BASIC_AUTH_USERNAME=admin  
HERMES_DASHBOARD_BASIC_AUTH_PASSWORD=choose-a-strong-password  
# Recommended: a stable signing secret so sessions survive restarts.  
# Without it a random key is generated per boot and you'll be logged out  
# on every restart.  
HERMES_DASHBOARD_BASIC_AUTH_SECRET=$(openssl rand -base64 32)  
EOF  
chmod 600 ~/.hermes/.env  
  
# 2. Run the dashboard bound to a reachable address. The non-loopback bind  
#    engages the auth gate; the username/password provider handles login.  
hermes dashboard --no-open --host 0.0.0.0 --port 9119  

```

--------------------------------

### Start LM Studio Server and Load Model

Source: https://hermes-agent.nousresearch.com/docs/integrations/providers

Start the LM Studio server and load a model with a specified context length. Use the CLI for automated setup.

```bash
lms server start                        # Starts on port 1234  
lms load qwen2.5-coder --context-length 64000  
```

--------------------------------

### Direct Photon Setup with Phone Number

Source: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/photon

Alternatively, run the Photon setup directly, which includes device-code login, project and user setup, and sidecar dependency installation. Re-running this command is safe as it handles existing users.

```bash
# Device-code login + project + user + sidecar deps, all in one  
hermes photon setup --phone +15551234567  

```

--------------------------------

### Install Theme and Plugin

Source: https://hermes-agent.nousresearch.com/docs/user-guide/features/extending-the-dashboard

Clone the example plugins repository and copy the theme and plugin files to their respective Hermes directories.

```bash
git clone https://github.com/NousResearch/hermes-example-plugins.git  

# Theme  
cp hermes-example-plugins/strike-freedom-cockpit/theme/strike-freedom.yaml \  
   ~/.hermes/dashboard-themes/  
  
# Plugin  
cp -r hermes-example-plugins/strike-freedom-cockpit ~/.hermes/plugins/  

```

--------------------------------

### Install and Configure Memori

Source: https://hermes-agent.nousresearch.com/docs/user-guide/features/memory-providers

Install the hermes-memori package and run the memori installation script. Then, configure Hermes to use Memori as its memory provider and complete the setup.

```bash
pip install hermes-memori
hermes-memori install
hermes config set memory.provider memori
hermes memory setup
```

--------------------------------

### Optional Setup Wizard Integration

Source: https://hermes-agent.nousresearch.com/docs/developer-guide/adding-tools

Example of adding an API key configuration for a tool to `hermes_cli/config.py` to integrate with the setup wizard.

```python
OPTIONAL_ENV_VARS = {
    ...
    "WEATHER_API_KEY": {
        "description": "Weather API key for weather lookup",
        "prompt": "Weather API key",
        "url": "https://weatherapi.com/",
        "tools": ["weather"],
        "password": True,
    },
}
```

--------------------------------

### Run Hermes Agent Setup

Source: https://hermes-agent.nousresearch.com/docs/guides/run-nemotron-3-ultra-free

Initiate the Hermes Agent setup process from the command line. This command will guide you through the initial configuration, including connecting to Nous Portal.

```bash
hermes setup
```

--------------------------------

### Quick Start Memory Commands

Source: https://hermes-agent.nousresearch.com/docs/user-guide/features/memory-providers

Use these commands for interactive setup, checking status, or disabling external memory providers.

```bash
hermes memory setup      # interactive picker + configuration  
hermes memory status     # check what's active  
hermes memory off        # disable external provider  

```

--------------------------------

### Install and Serve vLLM Models

Source: https://hermes-agent.nousresearch.com/docs/integrations/providers

Install vLLM and serve a model with specific configurations for tool calling and context length. This setup is ideal for high-throughput GPU inference.

```bash
pip install vllm  
vllm serve meta-llama/Llama-3.1-70B-Instruct  
  --port 8000 
  --max-model-len 65536 
  --tensor-parallel-size 2 
  --enable-auto-tool-choice 
  --tool-call-parser hermes  

```

--------------------------------

### Run Hermes Gateway Setup Wizard

Source: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/ntfy

Initiates the guided setup process for Hermes gateway configuration. Select 'ntfy' when prompted to configure the ntfy adapter.

```bash
hermes gateway setup  

```

--------------------------------

### Install Skill from URL with Explicit Name

Source: https://hermes-agent.nousresearch.com/docs/user-guide/features/skills

When the frontmatter or URL slug is insufficient, explicitly provide a name for the skill during installation using the `--name` flag. This example shows both command-line and in-chat usage.

```bash
# Frontmatter has no name and the URL slug is unhelpful — supply one:  
hermes skills install https://example.com/SKILL.md --name sharethis-chat  
  
# Or inside a chat session:  
/skills install https://example.com/SKILL.md --name sharethis-chat
```

--------------------------------

### Setup Nous Portal Provider

Source: https://hermes-agent.nousresearch.com/docs/user-guide/configuring-models

Run this command to log in to Nous Portal and set it as your provider on a fresh install.

```bash
hermes setup --portal
```

--------------------------------

### Start Hermes Gateway

Source: https://hermes-agent.nousresearch.com/docs/user-guide/features/voice-mode

Use these commands to start the Hermes gateway, which connects to your configured messaging platforms. The `setup` command initiates an interactive wizard for initial configuration.

```bash
hermes gateway        # Start the gateway (connects to configured platforms)
```

```bash
hermes gateway setup  # Interactive setup wizard for first-time configuration
```

--------------------------------

### Install and Serve Ollama Models

Source: https://hermes-agent.nousresearch.com/docs/integrations/providers

Install Ollama and pull a model, then start the Ollama server. This is the first step to using local models with Hermes Agent.

```bash
# Install and run a model  
ollama pull qwen2.5-coder:32b  
ollama serve   # Starts on port 11434  

```

--------------------------------

### Hermes Gateway Setup Wizard

Source: https://hermes-agent.nousresearch.com/docs/user-guide/messaging

Use the interactive wizard for easy configuration of all messaging platforms. It guides you through setup, shows existing configurations, and offers to restart the gateway.

```bash
hermes gateway setup        # Interactive setup for all messaging platforms  
```

--------------------------------

### Quick Start: GRPO Training

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/optional/mlops/mlops-slime

Example command to launch GRPO training.

```bash
# Source model configuration  
source scripts/models/qwen3-4B.sh  
  
# Launch training  
python train.py \
    --actor-num-nodes 1 \
    --actor-num-gpus-per-node 4 \
    --rollout-num-gpus 4 \
    --advantage-estimator grpo \
    --use-kl-loss --kl-loss-coef 0.001 \
    --rollout-batch-size 32 \
    --n-samples-per-prompt 8 \
    --global-batch-size 256 \
    --num-rollout 3000 \
    --prompt-data /path/to/data.jsonl \
    ${MODEL_ARGS[@]} ${CKPT_ARGS[@]}  
```

--------------------------------

### Quick Start: Create and Use a Profile

Source: https://hermes-agent.nousresearch.com/docs/user-guide/profiles

This sequence demonstrates the quickest way to create a new profile, configure it, and start interacting with it. The profile name becomes a command alias.

```bash
hermes profile create coder       # creates profile + "coder" command alias  
coder setup                       # configure API keys and model  
coder chat                        # start chatting  
```

--------------------------------

### README.md Structure Example

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/optional/software-development/software-development-code-wiki

An example structure for a project's README.md file, including sections for project name, key concepts, entry points, architecture, module map, and getting started.

```markdown
# <Project Name>  
  
<One paragraph: what it is and what it's for. Self-contained — don't assume the  
reader has the source README.>  
  
## Key Concepts  
  
- **<Concept 1>** — <one line>  
- **<Concept 2>** — <one line>  
  
## Entry Points  
  
- [`path/to/main.py`](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/software-development/code-wiki/<link>) — <what runs when you start it>  
- [`path/to/cli.py`](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/software-development/code-wiki/<link>) — <CLI surface>  
  
## High-Level Architecture  
  
<2-3 sentences. Detail goes in architecture.md.>  
  
See [architecture.md](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/software-development/code-wiki/architecture.md).  
  
## Module Map  
  
| Module | Purpose |  
|---|---|  
| [`<module>`](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/software-development/code-wiki/modules/<module>.md) | <one-line purpose> |  
  
## Getting Started  
  
See [getting-started.md](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/software-development/code-wiki/getting-started.md).  


```

--------------------------------

### Startup Checklist Markdown

Source: https://hermes-agent.nousresearch.com/docs/user-guide/features/hooks

Example of a startup checklist written in Markdown for the BOOT.md file. This file contains natural-language instructions for the agent to execute on gateway startup.

```markdown
# Startup Checklist

1. Run `hermes cron list` and check if any scheduled jobs failed overnight.
2. If any failed, send a summary to Discord #ops using the `send_message` tool.
3. Check if `/opt/app/deploy.log` has any ERROR lines from the last 24 hours. If yes, summarize them and include in the same Discord message.
4. If nothing went wrong, reply with only `[SILENT]` so no message is sent.

```

--------------------------------

### Hermes Gateway Commands Overview

Source: https://hermes-agent.nousresearch.com/docs/user-guide/messaging

A collection of commands to manage the Hermes gateway. These include running in the foreground, interactive setup, installation as a service, starting, stopping, and checking the status of the gateway service.

```bash
hermes gateway              # Run in foreground  
```

```bash
hermes gateway setup        # Configure messaging platforms interactively  
```

```bash
hermes gateway install      # Install as a user service (Linux) / launchd service (macOS)  
```

```bash
sudo hermes gateway install --system   # Linux only: install a boot-time system service  
```

```bash
hermes gateway start        # Start the default service  
```

```bash
hermes gateway stop         # Stop the default service  
```

```bash
hermes gateway status       # Check default service status  
```

```bash
hermes gateway status --system         # Linux only: inspect the system service explicitly  
```

--------------------------------

### Install and Start ClawRouter

Source: https://hermes-agent.nousresearch.com/docs/integrations/providers

Install ClawRouter using npx and start the local routing proxy. It defaults to port 8402.

```bash
# Install and start
npx @blockrun/clawrouter    # Starts on port 8402

```

--------------------------------

### Configuration Example

Source: https://hermes-agent.nousresearch.com/docs/developer-guide/context-engine-plugin

Example of how to configure the context engine in config.yaml.

```yaml
context:
  engine: "lcm"   # must match your engine's name property

```

--------------------------------

### get API Example

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/optional/mlops/mlops-pytorch-fsdp

Demonstrates retrieving a value from the store using the get API.

```python
import torch.distributed as dist
from datetime import timedelta
store = dist.TCPStore("127.0.0.1", 0, 1, True, timedelta(seconds=30))
store.set("first_key", "first_value")
# Should return "first_value"
store.get("first_key")
```

--------------------------------

### Set up Virtual Environment and Install Termux Bundle

Source: https://hermes-agent.nousresearch.com/docs/getting-started/termux

This sequence creates a virtual environment, activates it, sets the Android API level, and installs the Termux bundle with constraints. Use this when `uv pip install` fails on Android.

```bash
python -m venv venv  
```

```bash
source venv/bin/activate  
```

```bash
export ANDROID_API_LEVEL="$(getprop ro.build.version.sdk)"  
```

```bash
python -m pip install --upgrade pip setuptools wheel  
```

```bash
python -m pip install -e '.[termux]' -c constraints-termux.txt  
```

--------------------------------

### Install and Activate Pet (Procedure)

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/bundled/productivity/productivity-petdex

This sequence demonstrates the typical workflow for finding, installing, and activating a pet, followed by a preview and a diagnostic check.

```bash
hermes pets list <query>
hermes pets install <slug> --select
hermes pets show (Ctrl+C to stop)
hermes pets doctor
```

--------------------------------

### Install System Libraries (Debian/Ubuntu)

Source: https://hermes-agent.nousresearch.com/docs/getting-started/installation

Run this command as an administrator with sudo to install system libraries required by Chromium. This is a one-time setup step for non-sudo installations.

```bash
sudo npx playwright install-deps chromium
```

--------------------------------

### Fastest Path Installation with Nous Portal

Source: https://hermes-agent.nousresearch.com/docs/getting-started/installation

This command streamlines the setup by logging you in, setting Nous as the provider, and enabling the Tool Gateway in a single step.

```bash
hermes setup --portal  
```

--------------------------------

### Install and Use Shop CLI

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/optional/productivity/productivity-shop

Install the shop CLI globally using pnpm or npm. Shows how to view help and upgrade/uninstall the package.

```bash
pnpm add --global @shopify/shop-cli   # or: npm install --global @shopify/shop-cli  
shop --help  

```

```bash
pnpm add --global @shopify/shop-cli@latest # (or npm install --global @shopify/shop-cli@latest)

```

```bash
pnpm rm -g @shopify/shop-cli # (or npm rm -g @shopify/shop-cli)

```

--------------------------------

### Get classification

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/optional/mlops/mlops-clip

Example of how to get the classification category and probability from CLIP model outputs.

```python
max_idx = probs.argmax().item()
max_prob = probs[0, max_idx].item()

print(f"Category: {categories[max_idx]} ({max_prob:.2%})")
```

--------------------------------

### Reload Shell Profile After Installation

Source: https://hermes-agent.nousresearch.com/docs/reference/faq

If the 'hermes' command is not found after installation, reload your shell profile or start a new terminal session. Verify the installation location if issues persist.

```bash
# Reload your shell profile  
source ~/.bashrc    # bash  
source ~/.zshrc     # zsh  

# Or start a new terminal session  
```

```bash
which hermes  
ls ~/.local/bin/hermes  
```

--------------------------------

### Get Teams App Install Link

Source: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/teams

Generate an installation link for the Teams application using its ID. This link can be opened in a browser to directly install the bot in the Teams client.

```bash
teams app get <teamsAppId> --install-link  

```

--------------------------------

### Installation

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/optional/mlops/mlops-simpo

Steps to set up the environment and install necessary libraries for SimPO training.

```bash
# Create environment  
conda create -n simpo python=3.10 && conda activate simpo  
  
# Install PyTorch 2.2.2  
# Visit: https://pytorch.org/get-started/locally/  
  
# Install alignment-handbook  
git clone https://github.com/huggingface/alignment-handbook.git  
cd alignment-handbook  
python -m pip install .  
  
# Install Flash Attention 2  
python -m pip install flash-attn --no-build-isolation  
```

--------------------------------

### Start Hermes Gateway

Source: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/slack

Use these commands to start the Hermes gateway. The first command runs it in the foreground, while the others install it as a service.

```bash
hermes gateway
```

```bash
hermes gateway install
```

```bash
sudo hermes gateway install --system   # Linux only: boot-time system service  
```

--------------------------------

### Initialize Kanban Board

Source: https://hermes-agent.nousresearch.com/docs/user-guide/features/kanban

Use this command to create the `kanban.db` file and print a hint for the daemon.

```bash
hermes kanban init
```

--------------------------------

### Start Hermes Gateway

Source: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/signal

Start the Hermes gateway. You can run it in the foreground, install it as a user service, or as a system service on Linux for boot-time startup.

```bash
hermes gateway              # Foreground  
hermes gateway install      # Install as a user service  
sudo hermes gateway install --system   # Linux only: boot-time system service  
```

--------------------------------

### Start Hermes Agent Chat

Source: https://hermes-agent.nousresearch.com/docs/guides/run-nemotron-3-ultra-free

Once setup is complete, run this command to start interacting with the selected model through the Hermes Agent command-line interface.

```bash
hermes
```

--------------------------------

### Install and Launch SGLang Server

Source: https://hermes-agent.nousresearch.com/docs/integrations/providers

Install SGLang and launch the server with a specified model and configuration. Use `--tool-call-parser` for models with tool-calling capabilities.

```bash
pip install "sglang[all]"  
python -m sglang.launch_server \  
  --model meta-llama/Llama-3.1-70B-Instruct \  
  --port 30000 \  
  --context-length 65536 \  
  --tp 2 \  
  --tool-call-parser qwen  
```

--------------------------------

### Reload Shell and Start Hermes

Source: https://hermes-agent.nousresearch.com/docs/getting-started/installation

After installation, reload your shell configuration (e.g., .bashrc or .zshrc) and then run the 'hermes' command to start chatting.

```bash
source ~/.bashrc   # or: source ~/.zshrc  
hermes             # Start chatting!  
```

--------------------------------

### Manual Installation of Hermes Mod

Source: https://hermes-agent.nousresearch.com/docs/user-guide/features/skins

Steps to manually clone the repository, install dependencies, and start the application.

```bash
git clone https://github.com/cocktailpeanut/hermes-mod.git
cd hermes-mod/app
npm install
npm start
```

--------------------------------

### Timezone Command Examples

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/bundled/productivity/productivity-maps

Examples of using the timezone command to get timezone information for given coordinates.

```shell
python3 $MAPS timezone 48.8584 2.2945  
python3 $MAPS timezone 35.6762 139.6503  
```

--------------------------------

### Quick Start - Built-in Parrot Example

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/optional/research/research-darwinian-evolver

A tiny smoke test for the Darwinian Evolver using the parrot example, requiring ANTHROPIC_API_KEY.

```bash
cd ~/.hermes/cache/darwinian-evolver/darwinian_evolver  
uv run darwinian_evolver parrot \  
  --num_iterations 2 \  
  --num_parents_per_iteration 2 \  
  --mutator_concurrency 2 --evaluator_concurrency 2 \  
  --output_dir /tmp/parrot_demo  
```

--------------------------------

### Run Stocks Client - Quote Example

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/optional/finance/finance-stocks

Example of how to run the stocks client script to get a quote for a specific stock.

```bash
SCRIPT=~/.hermes/skills/finance/stocks/scripts/stocks_client.py
python3 $SCRIPT quote AAPL
```

--------------------------------

### YAML Configuration Example

Source: https://hermes-agent.nousresearch.com/docs/developer-guide/adding-platform-adapters

Example of how to configure the custom platform adapter in the `config.yaml` file, specifying enabled status and extra token/channel details.

```yaml
gateway:
  platforms:
    my_platform:
      enabled: true
      extra:
        token: "..."
        channel: "#general"
```

--------------------------------

### Install Profiles from Various Git Sources

Source: https://hermes-agent.nousresearch.com/docs/user-guide/profile-distributions

Demonstrates installing profiles using different Git URL formats, including GitHub shorthand, full HTTPS, SSH, self-hosted Git services, and local directories for development.

```bash
# GitHub shorthand
hermes profile install github.com/you/research-bot

# Full HTTPS
hermes profile install https://github.com/you/research-bot.git

# SSH
hermes profile install git@github.com:you/research-bot.git

# Self-hosted, GitLab, Gitea, Forgejo — any Git host
hermes profile install https://git.example.com/team/research-bot.git

# Private repo using your configured git auth
hermes profile install git@github.com:your-org/internal-bot.git

# Local directory during development (no git push needed)
hermes profile install ~/my-profile-in-progress/

```

--------------------------------

### Songsee Quick Start Examples

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/bundled/media/media-songsee

Various command-line examples demonstrating the usage of the Songsee skill for generating audio visualizations.

```bash
# Basic spectrogram  
songsee track.mp3  

```

```bash
# Save to specific file  
songsee track.mp3 -o spectrogram.png  

```

```bash
# Multi-panel visualization grid  
songsee track.mp3 --viz spectrogram,mel,chroma,hpss,selfsim,loudness,tempogram,mfcc,flux  

```

```bash
# Time slice (start at 12.5s, 8s duration)  
songsee track.mp3 --start 12.5 --duration 8 -o slice.jpg  

```

```bash
# From stdin  
cat track.mp3 | songsee - --format png -o out.png  

```

--------------------------------

### Full Slack Integration Example Configuration

Source: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/slack

A comprehensive example demonstrating global and Slack-specific settings, including session grouping, unauthorized DM handling, voice transcription, mention requirements, and reply modes.

```yaml
# Global gateway settings
group_sessions_per_user: true
unauthorized_dm_behavior: "pair"
stt_enabled: true

# Slack-specific settings
slack:
  require_mention: true
  unauthorized_dm_behavior: "pair"

# Platform config
platforms:
  slack:
    reply_to_mode: "first"
    extra:
      reply_in_thread: true
      reply_broadcast: false
```

--------------------------------

### Configuration Example

Source: https://hermes-agent.nousresearch.com/docs/developer-guide/context-engine-plugin

Example of how to configure the context engine in config.yaml to use a plugin.

```yaml
context:
  engine: "compressor"    # default built-in
  engine: "lcm"           # activates a plugin engine named "lcm"
```

--------------------------------

### Install missing Chromium for browser tools

Source: https://hermes-agent.nousresearch.com/docs/user-guide/windows-native

If browser tools time out, run `hermes doctor` to identify missing Chromium and get the exact command to install it.

```powershell
hermes doctor
```

```powershell
npx playwright install chromium
```

--------------------------------

### Area Command Examples

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/bundled/productivity/productivity-maps

Examples of using the area command to get bounding box coordinates and dimensions for a named place.

```shell
python3 $MAPS area "Manhattan, New York"  
python3 $MAPS area "London"  
```

--------------------------------

### Configure Hermes via Setup Wizard

Source: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/simplex

Run the Hermes gateway setup wizard to configure integration with SimpleX Chat.

```bash
hermes gateway setup

```

--------------------------------

### Production: Install as a Service

Source: https://hermes-agent.nousresearch.com/docs/guides/team-telegram-assistant

Install the gateway as a persistent service.

```bash
hermes gateway install
sudo hermes gateway install --system   # Linux only: boot-time system service
```

--------------------------------

### Starting a Conversation

Source: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/yuanbao

Example message to initiate a conversation with the Yuanbao bot.

```bash
hello  

```

--------------------------------

### Hello World with GPU

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/optional/mlops/mlops-modal

A simple example demonstrating how to use a GPU to get NVIDIA system information.

```python
import modal  

app = modal.App("hello-gpu")  

@app.function(gpu="T4")  
def gpu_info():  
    import subprocess  
    return subprocess.run(["nvidia-smi"], capture_output=True, text=True).stdout  

@app.local_entrypoint()  
def main():  
    print(gpu_info.remote())  
```

--------------------------------

### Download and Prepare Modpack Server Files

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/optional/gaming/gaming-minecraft-modpack-server

Initial steps to download the server pack, unzip it, and inspect its contents. Look for key files like startserver.sh and mod loader information.

```bash
mkdir -p ~/minecraft-server
cd ~/minecraft-server
wget -O serverpack.zip "<URL>"
unzip -o serverpack.zip -d server
ls server/
```

--------------------------------

### Assembled System Prompt Example

Source: https://hermes-agent.nousresearch.com/docs/developer-guide/prompt-assembly

This example illustrates the structure of a complete system prompt, showing how different layers like agent identity, tool guidance, memory snapshots, user profiles, skills, project context, and timestamps are combined.

```text
# Layer 1: Agent Identity (from ~/.hermes/SOUL.md)  
You are Hermes, an AI assistant created by Nous Research.  
You are an expert software engineer and researcher.  
You value correctness, clarity, and efficiency.  
...  
  
# Layer 2: Tool-aware behavior guidance  
You have persistent memory across sessions. Save durable facts using  
the memory tool: user preferences, environment details, tool quirks,  
and stable conventions. Memory is injected into every turn, so keep  
it compact and focused on facts that will still matter later.  
...  
When the user references something from a past conversation or you  
suspect relevant cross-session context exists, use session_search  
to recall it before asking them to repeat themselves.  
  
# Tool-use enforcement (for GPT/Codex models only)  
You MUST use your tools to take action — do not describe what you  
would do or plan to do without actually doing it.  
...  
  
# Layer 3: Honcho static block (when active)  
[Honcho personality/context data]  
  
# Layer 4: Optional system message (from config or API)  
[User-configured system message override]  
  
# Layer 5: Frozen MEMORY snapshot  
## Persistent Memory  
- User prefers Python 3.12, uses pyproject.toml  
- Default editor is nvim  
- Working on project "atlas" in ~/code/atlas  
- Timezone: US/Pacific  
  
# Layer 6: Frozen USER profile snapshot  
## User Profile  
- Name: Alice  
- GitHub: alice-dev  
  
# Layer 7: Skills index  
## Skills (mandatory)  
Before replying, scan the skills below. If one clearly matches  
your task, load it with skill_view(name) and follow its instructions.  
...  
<available_skills>  
  software-development:  
    - code-review: Structured code review workflow  
    - test-driven-development: TDD methodology  
  research:  
    - arxiv: Search and summarize arXiv papers  
</available_skills>  
  
# Layer 8: Context files (from project directory)  
# Project Context  
The following project context files have been loaded and should be followed:  
  
## AGENTS.md  
This is the atlas project. Use pytest for testing. The main  
entry point is src/atlas/main.py. Always run `make lint` before  
committing.  
  
# Layer 9: Timestamp + session  
Current time: 2026-03-30T14:30:00-07:00  
Session: abc123  
  
# Layer 10: Platform hint  
You are a CLI AI Agent. Try not to use markdown but simple text  
renderable inside a terminal.  

```

--------------------------------

### Structured output example

Source: https://hermes-agent.nousresearch.com/docs/developer-guide/plugin-llm-access

Example of using `ctx.llm.complete_structured` to get a typed JSON answer, including instructions, input, JSON schema, and purpose.

```python
result = ctx.llm.complete_structured(  
    instructions="Score this support reply for urgency (0–1) and pick a category.",  
    input=[{"type": "text", "text": message_body}],  
    json_schema=TRIAGE_SCHEMA,  
    purpose="support.triage",  
    temperature=0.0,  
    max_tokens=128,  
)  
  
if result.parsed["urgency"] > 0.8:  
    await dispatch_to_oncall(result.parsed["category"], message_body)  

```

--------------------------------

### Initialize, Start, Create, Watch, and List Kanban Boards

Source: https://hermes-agent.nousresearch.com/docs/user-guide/features/kanban

Commands for initializing a Kanban board, starting the gateway, creating tasks, watching activity, and listing board contents. These are user-facing commands for board management.

```bash
# 1. Create the board (you)  
hermes kanban init  
  
# 2. Start the gateway (hosts the embedded dispatcher)  
hermes gateway start  
  
# 3. Create a task (you — or an orchestrator agent via kanban_create)  
hermes kanban create "research AI funding landscape" --assignee researcher  
  
# 4. Watch activity live (you)  
hermes kanban watch  
  
# 5. See the board (you)  
hermes kanban list  
hermes kanban stats  
```

--------------------------------

### Re-snapshot PATH for macOS Gateway

Source: https://hermes-agent.nousresearch.com/docs/reference/faq

Re-run the gateway install command to capture the current shell PATH, which is necessary if tools were installed after the initial gateway setup. Then restart the gateway.

```bash
hermes gateway install    # Re-snapshots your current PATH  
hermes gateway start      # Detects the updated plist and reloads  
```

--------------------------------

### Shop Catalog Search Examples

Source: https://hermes-agent.nousresearch.com/docs/user-guide/skills/optional/productivity/productivity-shop

Provides practical examples of using the `shop search` command with different parameters for various search scenarios.

```bash
shop search "trail running shoes" --country GB --currency GBP --ships-to GB --ships-from GB --limit 10 --condition new
shop search "tshirt" --country US --color White --size M --gender Female
shop search "black crewneck sweater" --like-id gid://shopify/p/abc123
shop search --image ./photo.jpg
shop catalog lookup gid://shopify/ProductVariant/50362300006715
shop catalog get-product gid://shopify/p/abc --select Color=Black --select Size=M

```

--------------------------------

### Install and Manage Hermes Agent with Nous Portal

Source: https://hermes-agent.nousresearch.com/docs/integrations/providers

Use these commands for a fresh installation or to manage an existing setup with Nous Portal. Inspect login and routing information at any time.

```bash
hermes setup --portal     # fresh install — OAuth + provider + gateway in one command  
hermes model              # existing install — pick "Nous Portal" from the list  
hermes portal info        # inspect login + routing at any time  
```

--------------------------------

### Create Branch and Run Tests

Source: https://hermes-agent.nousresearch.com/docs/developer-guide/contributing

After installation, create a new branch for your contributions and run the project's tests to ensure everything is working correctly.

```bash
git checkout -b fix/description
scripts/run_tests.sh
```

--------------------------------

### Example Prompts for Hermes Agent

Source: https://hermes-agent.nousresearch.com/docs/getting-started/quickstart

Use specific and verifiable prompts to test Hermes' capabilities. These examples cover summarization, file identification, and GitHub PR workflow setup.

```bash
Summarize this repo in 5 bullets and tell me what the main entrypoint is.  
```

```bash
Check my current directory and tell me what looks like the main project file.  
```

```bash
Help me set up a clean GitHub PR workflow for this codebase.  
```