hermes-ecosystem

🗺️ Hermes Atlas — the community map of every tool, skill, and integration for Hermes Agent by Nous Research. Live at hermesatlas.com

ksimbackHTMLgit

View on GitHub

What the docs cover

How it works

Environment variables (Vercel)

Overview

Review hermes-ecosystem through its repository signals, setup path, and structured documentation.

Key Features

Built around html tooling
Carries strong trust indicators from repository metadata

Best For

Agent Tool research

Use Cases

Ai Agents

Keep exploring from this skill

Use these paths to move from a single repository into the broader category, platform, and workflow hubs that users usually compare next.

Related Skills

🛠 agent-toolclaude-codecodex

163K

skills

Skills for Real Engineers. Straight from my .claude directory.

Mmattpocockabout 2 months ago

npx skills@latest add mattpocock/skills

🛠 agent-toolmcp

151.5K

langflow

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

Llangflow-aiabout 2 months ago

View on GitHub

🛠 agent-toolclaude-code

137.1K

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

Aanthropicsabout 2 months ago

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows -- all through natural language commands. Use it in your terminal, IDE, or tag @claude on Github.

**Learn more in the [official documentation](https://code.claude.com/docs/en/overview)**.

<img src="./demo.gif" />

## Get started
> [!NOTE]
> Installation via npm is deprecated. Use one of the recommended methods below.

For more installation options, uninstall steps, and troubleshooting, see the [setup documentation](https://code.claude.com/docs/en/setup).

1. Install Claude Code:

    **MacOS/Linux (Recommended):**

Install

npm install

Repository

Stars

1,116

Forks

Running locally

git clone https://github.com/ksimback/hermes-ecosystem.git
cd hermes-ecosystem

# Install deps (only needed for the API endpoints + chunk builder)
npm install

# To rebuild the chatbot's knowledge base after editing research/ files:
OPENROUTER_API_KEY=sk-or-... node scripts/build-chunks.js

# To test the RAG pipeline locally:
OPENROUTER_API_KEY=sk-or-... node scripts/test-rag.js

# To preview the static site, just open index.html in a browser
# (the API endpoints only work when deployed to Vercel)

┌─────────────────────────────────────────────────────────────┐
│  hermesatlas.com (Vercel static + serverless)               │
│                                                              │
│  ┌─────────────┐  ┌──────────────┐  ┌──────────────────┐    │
│  │ index.html  │  │ /api/stars   │  │ /api/chat        │    │
│  │ (the map)   │  │ (live data)  │  │ (RAG chatbot)    │    │
│  └─────────────┘  └──────┬───────┘  └────────┬─────────┘    │
│                          │                    │              │
│                          ▼                    ▼              │
│                   ┌──────────┐         ┌────────────┐       │
│                   │  Redis   │         │ OpenRouter │       │
│                   │  Cloud   │         │  (Gemma 4) │       │
│                   └────┬─────┘         └────────────┘       │
│                        │                                     │
│                        ▼                                     │
│                  ┌──────────┐                                │
│                  │ GitHub   │                                │
│                  │ GraphQL  │                                │
│                  └──────────┘                                │
└─────────────────────────────────────────────────────────────┘

Stack:

Frontend: Vanilla HTML/CSS/JavaScript (no framework, no build step)
Hosting: Vercel (static + serverless functions)
Cache: Redis Cloud (1hr TTL on star counts, daily history snapshots)
LLM: OpenRouter with fallback chain (Gemma 4 31B → Gemma 4 26B → Gemini 3 Flash)
Embeddings: OpenAI text-embedding-3-small (computed once at build time, cached as static JSON)
Retrieval: Hybrid BM25 + cosine similarity, MMR re-ranking, conversation-aware query rewriting

Variable	Purpose	Required
`GITHUB_TOKEN`	Fine-grained PAT, public repos read-only	For 5000/hr rate limit (60/hr without)
`OPENROUTER_API_KEY`	LLM API key for chat	Yes
`REDIS_URL`	Redis Cloud connection string	Yes (for cache + history)
`OPENROUTER_MODEL`	Override primary LLM model	No (default: `google/gemma-4-31b-it:free`)
`OPENROUTER_FALLBACK_MODELS`	Comma-separated fallback chain	No