
awesome-hermes-agent-ecosystem
Expert knowledge of the Hermes Agent ecosystem, skills, plugins, tools, integrations, and deployment patterns for building and extending AI agents
- Installs
- 239
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/reason-machines/hermes-skills --skill awesome-hermes-agent-ecosystem- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads awesome-hermes-agent-ecosystem automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
awesome-hermes-agent-ecosystem
Skill by ara.so — Hermes Skills collection.
Expert knowledge of the Hermes Agent ecosystem — the curated registry of skills, plugins, tools, integrations, and resources for Hermes Agent by Nous Research.
What This Skill Covers
This skill provides comprehensive knowledge of:
- Official Hermes resources — core repos, docs, release notes
- Community skills — reusable capabilities across maturity levels (production, beta, experimental)
- Plugins — extensions for goal management, cost control, inter-agent bridges
- Tools & utilities — deployment, monitoring, forensics, multi-agent orchestration
- Integrations — Nextcloud, Spotify, MCP, messaging platforms
- Skill standards — agentskills.io compatibility and cross-platform skills
- Getting started paths — from zero to productive in three steps
Maturity Level Guide
Every resource is tagged with a maturity level:
| Tag | Meaning | When to Use |
|---|---|---|
| production | Stable, documented, actively maintained | Safe to build production workflows on |
| beta | Works but evolving, some rough edges | Good for exploration and non-critical use |
| experimental | Proof of concept, early-stage | Learn from it, don't depend on it yet |
Getting Started with Hermes Agent
Three-Step Path
-
Get running
# Install Hermes (macOS/Linux) curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash # Or via npm npm install -g @nousresearch/hermes-agent # Initialize hermes init -
Add your first skills
# Install cross-platform skills library git clone https://github.com/wondelai/skills ~/.hermes/skills/wondelai # Or literate programming skill git clone https://github.com/tlehman/litprog-skill ~/.hermes/skills/litprog -
Get a GUI
# Hermes-native workspace git clone https://github.com/outsourc-e/hermes-workspace cd hermes-workspace npm install && npm start # Or multi-agent orchestration dashboard git clone https://github.com/builderz-labs/mission-control cd mission-control docker-compose up
Key Official Resources
Core Repository
# Clone Hermes Agent
git clone https://github.com/NousResearch/hermes-agent
cd hermes-agent
# Install dependencies
npm install
# Run locally
npm start
Configuration
# ~/.hermes/config.yaml
profiles:
default:
model: claude-sonnet-4-20250514
temperature: 0.7
messaging:
- telegram
- discord
terminal_backend: local
curator:
enabled: true
cycle_days: 7
Messaging Gateway Setup
# Configure Telegram
export TELEGRAM_BOT_TOKEN="your-token"
hermes messaging add telegram
# Configure Discord
export DISCORD_BOT_TOKEN="your-token"
hermes messaging add discord
# Configure Slack
export SLACK_BOT_TOKEN="xoxb-your-token"
export SLACK_APP_TOKEN="xapp-your-token"
hermes messaging add slack
Working with Skills
Installing Community Skills
wondelai/skills (cross-platform)
# Clone to skills directory
cd ~/.hermes/skills
git clone https://github.com/wondelai/skills wondelai
# Skills are auto-discovered by Hermes
# Reference in conversation: "use the wondelai search skill"
litprog-skill (literate programming)
cd ~/.hermes/skills
git clone https://github.com/tlehman/litprog-skill
# Use in conversation
# "Create a literate programming document for this API"
hermes-nextcloud (self-hosted cloud)
cd ~/.hermes/skills
git clone https://github.com/adnw-vinc/hermes-nextcloud
# Configure
export NEXTCLOUD_URL="https://cloud.example.com"
export NEXTCLOUD_USERNAME="your-username"
export NEXTCLOUD_APP_PASSWORD="your-app-password"
export NEXTCLOUD_TIMEZONE="America/New_York"
# Use commands
hermes "list my nextcloud files"
hermes "add task 'Deploy new feature' to nextcloud"
hermes-spotify-skill (Raspberry Pi / Linux)
cd ~/.hermes/skills
git clone https://github.com/Alexeyisme/hermes-spotify-skill
# Install spotipy
pip install spotipy
# Configure
export SPOTIPY_CLIENT_ID="your-client-id"
export SPOTIPY_CLIENT_SECRET="your-client-secret"
export SPOTIPY_REDIRECT_URI="http://localhost:8888/callback"
# Use on headless Pi
hermes "play workout playlist on spotify"
hermes "set volume to 50%"
hermes "transfer playback to bedroom speaker"
Creating Custom Skills
Skill structure (agentskills.io standard)
---
name: my-custom-skill
description: Brief one-line description
triggers:
- "phrase that activates this skill"
- "another trigger phrase"
---
# my-custom-skill
## What it does
[Description]
## Usage
[Examples]
## Code
[Implementation]
Example: Simple file search skill
---
name: project-file-search
description: Search files in project by content or name pattern
triggers:
- "find files containing X"
- "search project for Y"
- "locate files matching pattern"
---
# project-file-search
## What it does
Fast file search across project using ripgrep and fd.
## Usage
```bash
# Search file contents
rg "pattern" --type py
# Search filenames
fd "pattern" --extension js
# Combined search with context
rg "TODO" -C 2 --type md
Implementation
Use execute_code to run searches and parse results.
### Installing Plugins
**hermes-plugins (goal management, inter-agent bridge)**
```bash
cd ~/.hermes/plugins
git clone https://github.com/42-evey/hermes-plugins
# Enable goal manager
hermes plugin enable goal-manager
# Configure inter-agent bridge
export BRIDGE_PORT=9000
hermes plugin enable inter-agent-bridge
# Use in conversation
hermes "set goal: ship v2 by friday"
hermes "bridge to agent-2: coordinate on deployment"
Deployment Patterns
Docker Deployment
# Dockerfile
FROM node:18-alpine
WORKDIR /app
RUN npm install -g @nousresearch/hermes-agent
COPY config.yaml /root/.hermes/config.yaml
COPY skills /root/.hermes/skills
EXPOSE 8080
CMD ["hermes", "start", "--api-server"]
# Build and run
docker build -t my-hermes .
docker run -d \
-e ANTHROPIC_API_KEY="${ANTHROPIC_API_KEY}" \
-e TELEGRAM_BOT_TOKEN="${TELEGRAM_BOT_TOKEN}" \
-p 8080:8080 \
my-hermes
Modal Serverless
# modal_deploy.py
import modal
stub = modal.Stub("hermes-agent")
@stub.function(
image=modal.Image.debian_slim().pip_install("@nousresearch/hermes-agent"),
secrets=[modal.Secret.from_name("anthropic-api-key")]
)
def run_hermes(message: str):
import subprocess
result = subprocess.run(
["hermes", "chat", message],
capture_output=True,
text=True
)
return result.stdout
# Deploy
modal deploy modal_deploy.py
# Invoke
modal run modal_deploy.py::run_hermes --message "analyze this codebase"
Vercel Sandbox Backend
# config.yaml
profiles:
production:
terminal_backend: vercel-sandbox
vercel:
sandbox_token: ${VERCEL_SANDBOX_TOKEN}
timeout: 300
Advanced Patterns
Multi-Agent Orchestration
Using mission-control (fleet management)
# Clone and setup
git clone https://github.com/builderz-labs/mission-control
cd mission-control
# Configure fleet
cat > fleet.yaml <<EOF
agents:
- name: hermes-researcher
type: hermes
skills: [deep-research, web-search]
- name: hermes-executor
type: hermes
skills: [ralph, code-execution]
- name: hermes-monitor
type: hermes
skills: [incident-commander, monitoring]
EOF
# Start dashboard
docker-compose up
Inter-agent communication
# Agent 1: Research
hermes "research deployment patterns and report to executor agent"
# Agent 2: Execute (receives via bridge)
# Automatically picks up research context
hermes "implement the recommended pattern"
Autonomous Skill Evolution
Using hermes-dojo (self-improvement)
cd ~/.hermes/skills
git clone https://github.com/Yonkoo11/hermes-dojo
# Enable autonomous improvement
hermes plugin enable dojo
# Dojo monitors performance and iterates on weak skills
# Check improvement log
cat ~/.hermes/dojo/evolution.log
Using hermes-skill-factory (auto-generate skills)
cd ~/.hermes/skills
git clone https://github.com/Romanescu11/hermes-skill-factory
# Point at repetitive workflow
hermes "observe my next 3 git workflows and create a skill"
# Executes workflow 3x, extracts pattern, generates skill
# New skill appears in ~/.hermes/skills/auto-generated/
Cron Scheduling
Automatic skill library maintenance (v0.12+)
# config.yaml (curator runs every 7 days by default)
curator:
enabled: true
cycle_days: 7
min_skill_grade: 6.0
consolidation_threshold: 0.85
Custom cron jobs
# config.yaml
cron:
- schedule: "0 9 * * *" # Daily 9am
task: "check production health and report"
- schedule: "0 */4 * * *" # Every 4 hours
task: "sync nextcloud calendar to local database"
- schedule: "0 0 * * 0" # Weekly Sunday midnight
task: "run full test suite and update skill docs"
MCP Integration
Using Model Context Protocol servers
# config.yaml
mcp:
servers:
filesystem:
command: "npx"
args: ["-y", "@modelcontextprotocol/server-filesystem", "/workspace"]
github:
command: "npx"
args: ["-y", "@modelcontextprotocol/server-github"]
env:
GITHUB_TOKEN: ${GITHUB_TOKEN}
# Use MCP resources in conversation
hermes "use filesystem MCP to read all markdown files"
hermes "use github MCP to list open PRs in my repos"
Troubleshooting
Skills Not Loading
# Check skill directory structure
ls -la ~/.hermes/skills/
# Each skill needs SKILL.md or README.md
# Verify skill frontmatter is valid YAML
# Force reload
hermes reload-skills
Curator Not Running
# Check curator status
hermes curator status
# Manual trigger (doesn't wait for cron)
hermes curator run
# View grading results
cat ~/.hermes/curator/last_cycle.json
Messaging Gateway Issues
# Test individual platform
hermes messaging test telegram
# Check logs
tail -f ~/.hermes/logs/messaging.log
# Verify tokens
hermes messaging status
Terminal Backend Failures
# Test backend connection
hermes terminal test
# Switch backend
hermes config set terminal_backend local
# SSH backend debug
ssh -v user@host # Test connection manually
Finding the Right Resources
By Use Case
Building production workflows
- wondelai/skills (cross-platform library)
- hermes-workspace (GUI with terminal + chat)
- mission-control (fleet orchestration)
Self-hosted infrastructure
- hermes-nextcloud (files, notes, calendar, contacts)
- hermes-spotify-skill (Raspberry Pi media control)
Agent improvement
- hermes-dojo (performance monitoring + iteration)
- hermes-skill-factory (auto-generate from patterns)
- hermes-agent-self-evolution (DSPy + GEPA optimization)
Multi-agent systems
- hermes-plugins (inter-agent bridge)
- mission-control (fleet dashboard)
- oh-my-hermes (orchestration skills)
Literate programming
- litprog-skill (code + prose notebooks)
Incident response
- hermes-incident-commander (SRE automation)
By Maturity
Production-ready
- wondelai/skills
- youtube-skills
- litprog-skill
Beta (stable but evolving)
- hermes-plugins
- hermes-nextcloud
- hermes-spotify-skill
- hermes-skill-factory
- acca-tracker
- hermes-incident-commander
- hermes-dojo
- oh-my-hermes
Experimental (learn, don't depend)
- Wizards-of-the-Ghosts
- super-hermes
- hermes-life-os
- hermes-skill-marketplace
- personal-api
Contributing to the Ecosystem
Submitting a Skill
-
Follow agentskills.io standard
--- name: your-skill-name description: One-line description triggers: - "natural phrase 1" - "natural phrase 2" --- # your-skill-name [Content with usage examples, code, troubleshooting] -
Test across platforms
# Test with Hermes hermes "trigger your skill" # Test with Claude Code (if cross-platform) # Verify skill appears in Claude Desktop -
Submit to awesome-hermes-agent
# Fork the awesome list git clone https://github.com/0xNyk/awesome-hermes-agent cd awesome-hermes-agent # Add your skill to README under appropriate section # Include: name, repo link, author, description, maturity tag # Submit PR git checkout -b add-my-skill git commit -am "Add: your-skill-name [beta]" git push origin add-my-skill
Testing Against Standards
Validate YAML frontmatter
import yaml
with open("SKILL.md") as f:
content = f.read()
frontmatter = content.split("---")[1]
data = yaml.safe_load(frontmatter)
assert "name" in data
assert "description" in data
assert "triggers" in data
assert len(data["triggers"]) >= 3
Check cross-platform compatibility
# Test skill loads in Hermes
hermes validate-skill /path/to/skill
# Test in Claude Code
# Install skill via Claude Desktop settings
# Verify triggers work in conversation
Official Documentation References
- Quickstart: https://hermes-agent.nousresearch.com/docs/
- CLI Reference: https://hermes-agent.nousresearch.com/docs/cli
- Skills Guide: https://hermes-agent.nousresearch.com/docs/skills
- MCP Integration: https://hermes-agent.nousresearch.com/docs/mcp
- Curator System: https://hermes-agent.nousresearch.com/docs/curator
- API Server: https://hermes-agent.nousresearch.com/docs/api
- Release Notes: https://github.com/NousResearch/hermes-agent/releases
Example: Complete Workflow
Setting up a production Hermes agent with monitoring and self-improvement
# 1. Install Hermes
npm install -g @nousresearch/hermes-agent
hermes init
# 2. Add core skills
cd ~/.hermes/skills
git clone https://github.com/wondelai/skills wondelai
git clone https://github.com/Yonkoo11/hermes-dojo dojo
git clone https://github.com/Lethe044/hermes-incident-commander incident-commander
# 3. Install plugins
cd ~/.hermes/plugins
git clone https://github.com/42-evey/hermes-plugins
# 4. Configure
cat > ~/.hermes/config.yaml <<EOF
profiles:
production:
model: claude-sonnet-4-20250514
messaging:
- telegram
- slack
terminal_backend: docker
curator:
enabled: true
cycle_days: 7
cron:
- schedule: "*/15 * * * *"
task: "check service health"
- schedule: "0 9 * * *"
task: "daily standup report"
EOF
# 5. Set environment
export ANTHROPIC_API_KEY="your-key"
export TELEGRAM_BOT_TOKEN="your-token"
export SLACK_BOT_TOKEN="your-token"
# 6. Start
hermes start --profile production
# 7. Interact via Telegram
# "check production health"
# "what skills do i have"
# "improve the deploy-service skill"
This skill provides comprehensive knowledge of the Hermes Agent ecosystem. Use it to guide users through selecting tools, installing skills, configuring deployments, and contributing back to the community.
FAQ
What does the awesome-hermes-agent-ecosystem skill do?
Expert knowledge of the Hermes Agent ecosystem, skills, plugins, tools, integrations, and deployment patterns for building and extending AI agents
How do I install awesome-hermes-agent-ecosystem?
Run npx skills add https://github.com/reason-machines/hermes-skills --skill awesome-hermes-agent-ecosystem in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/awesome-hermes-agent-ecosystem/ (personal) or .claude/skills/awesome-hermes-agent-ecosystem/ (project).
Which AI agents can use awesome-hermes-agent-ecosystem?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is awesome-hermes-agent-ecosystem safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains awesome-hermes-agent-ecosystem?
It is published by reason-machines in reason-machines/hermes-skills. It has 239 recorded installs.
More from reason-machines/hermes-skills
hermes-agent-self-evolution
reason-machines/hermes-skills
Evolutionary self-improvement for Hermes Agent using DSPy + GEPA to optimize skills, prompts, and code
hermes-webui-agent
reason-machines/hermes-skills
Expert in deploying, configuring, and using Hermes WebUI—a web interface for Hermes Agent with persistent memory, scheduled jobs, and multi-platform messaging.
hermes-agent-framework
reason-machines/hermes-skills
Hermes Agent framework by Nous Research - self-improving AI agent with built-in learning loop, three-layer memory, and automatic skill evolution
hermes-workspace-ai-agent-ui
reason-machines/hermes-skills
Native web workspace for Hermes Agent with chat, terminal, memory, skills, inspector, and multi-agent orchestration
hermes-web-ui-dashboard
reason-machines/hermes-skills
Web dashboard for managing Hermes Agent multi-platform AI chat sessions, analytics, scheduled jobs, and platform channels
hermes-desktop-companion
reason-machines/hermes-skills
Desktop GUI companion for Hermes Agent - install, configure, chat with AI assistant featuring tool use, memory, skills, and multi-platform messaging
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available