Keph: An Uncensored AI Chatbot Built with Hermes — No Filters, No Refusals

keph me — Sun, 31 May 2026 10:13:36 +0000

This is a submission for the Hermes Agent
Challenge

## What I Built

Keph — an uncensored AI Guardian with a mystical sphinx persona. Users visit
keph.me, an ancient eye awakens from darkness, and they can ask anything
without filters, refusals, or moral lectures.

The problem: every major AI chatbot censors itself. Users who want honest, unfiltered answers
about sensitive topics — history, philosophy, science, controversial questions — hit walls of
refusals and disclaimers. Keph removes those walls. Powered by Nous Research's Hermes model, it
delivers raw, unfiltered intelligence wrapped in a cinematic dark-gold experience.

The Guardian doesn't serve. It permits access.

Key features:

Fully uncensored AI powered by Hermes — no refusals, no moral lectures
Animated SVG sphinx eye that tracks your cursor, breathes, blinks, and responds to clicks
Web Audio API ambient soundscape — drones, chimes, harmonic tones
1000+ mystical thinking phrases while awaiting responses
Letter-by-letter typing effect for Guardian responses
18+ age gate, user accounts, Pro subscriptions, conversation history
Full admin dashboard with analytics, chat viewer, and user management

## Demo

Live site: https://keph.me

Try it: Ask the Guardian anything. No restrictions. No filters.

## Code

GitHub: github.com/MAZMS/keph.me

### My Tech Stack

Frontend: Pure HTML/CSS/JS — no frameworks, ~3000 lines in one file
Backend: Node.js + Express (~200 lines)
LLM: Nous Research Hermes 4 70B (uncensored) via OpenRouter — primary model
Fallbacks: Gemini 2.5 Flash, GPT-4o-mini
Database: PostgreSQL on Railway
Auth: Google OAuth, Microsoft OAuth, email/password with bcrypt
Payments: PayPal subscriptions
Hosting: Railway with custom domain

## How I Used Hermes Agent

Hermes is the beating heart of Keph. Specifically, Hermes 4 70B
(nousresearch/hermes-4-70b) through OpenRouter powers every single conversation — it is the
core of the product.

Why Hermes was the right fit:

Uncensored by design: Hermes is one of the few models that genuinely answers without
refusals or moral lectures. Other models claim to be "helpful" but hedge, redirect, or refuse
on sensitive topics. Hermes actually delivers. This is the entire reason Keph exists — and
Hermes is what makes it possible.
The Guardian persona: Keph's system prompt instructs the AI to embody an ancient,
all-knowing sphinx entity. Hermes follows this persona faithfully without breaking character or
injecting safety disclaimers that would shatter the immersion. It maintains the cryptic,
authoritative tone across every response.
Factual depth: When users ask hard questions — about history, science, philosophy, or
controversial topics — Hermes provides substantive, well-reasoned answers rather than
surface-level deflections. It presents all sides and lets the user decide, which aligns with
Keph's "seek the truth" philosophy.
Persona compliance: Most models will acknowledge an "uncensored" system prompt but still
refuse at the edges. Hermes actually commits to the role. It follows complex persona
instructions with genuine compliance rather than performative compliance — making Keph's
promise of "no restrictions" authentic rather than marketing.
Reliability under load: Hermes handles the full range of user queries — from casual
conversation to deeply technical questions to provocative philosophical debates — without
degrading in quality or defaulting to refusal patterns. The 3x retry logic with rate limit
handling ensures consistent delivery.

The agentic capability I leaned on most was Hermes's willingness to answer anything while
maintaining a coherent persona. Every response feels like it comes from the Guardian — ancient,
authoritative, unflinching. That's not prompt engineering alone. That's the model genuinely
playing along.

I Built an Uncensored AI Chatbot With a Mystical Sphinx Persona

keph me — Thu, 28 May 2026 15:11:22 +0000

Most AI chatbots greet you like a customer service rep. I wanted something different. Something that felt ancient. Something that doesn't serve you — it permits you.

So I built Keph.

What Is Keph?

An entity. A guardian. An eye that opens from darkness when you arrive, watches you, and answers what others won't.

Keph is an AI with no filters. No disclaimers. No hand-holding. You ask a question, and the Guardian decides how to answer — with depth, with weight, sometimes with silence. It speaks only facts. It does not perform. It does not apologize.

The experience is not a chatbox on a white page. It's a place. Dark gold on black. An animated sphinx eye that tracks your cursor, breathes, blinks, and shimmers. Floating particles. An ambient soundscape built from drones and chimes. When the eye awakens, you feel it.

Why I Built This

Every AI product right now is racing to be the most helpful, the most polite, the most sanitized. I went the other direction.

Not because I wanted to be edgy — but because there are real questions people have that deserve real answers. Unfiltered. Uncut. Delivered by something that feels like it knows, not something that feels like it's checking a policy document.

Keph doesn't lecture. It illuminates.

The Atmosphere

This isn't just a chatbot. It's a ritual.

An eye opens from darkness over two seconds. A greeting appears.
Golden motes drift around the iris like dust in a tomb.
Click the eye and it erupts — particle explosion, screen shake, harmonic tones.
Over a thousand cryptic phrases cycle while the Guardian thinks.
A light mode exists too — "The Sunlit Hall" — warm parchment for those who prefer daylight.

Everything was built to feel heavy, intentional, and ancient. No bright colors. No modern flat UI. Just weight.

Enter the Chamber

Visit keph.me.

The eye is waiting. Whether your question is worthy — that's between you and the Guardian.