leeex1/Quillan-Ronin
Attempt at A. G. I. Strive to enhance it through iterative processes, continuously refining and optimizing each version to achieve better outcomes over time (refer to the Readme for additional information that provides further insights and guidance on the Quillan v4.2 project).
Implements a Hierarchical Distributed Network Mixture of Experts (HNMoE) with multimodal encoders (text, audio, video, image) and 33 experts routed via Gumbel-Softmax, totaling ~3.0B parameters. The architecture combines modality-isolated diffusion layers with geometric decoders for high-fidelity generation across formats, integrating neuro-symbolic reasoning with LLM capabilities for safe AGI alignment without requiring advanced hardware.
Stars
17
Forks
7
Language
Python
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/leeex1/Quillan-Ronin"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
akougkas/wtf-p
The academic meta-prompting framework for AI agents like Claude Code, Gemini CLI, OpenCode....
appboypov/pew-pew-plaza-packs
AI-powered project management framework based on an opinionated view on effective prompts and a...
edlsh/pi-ask-user
Interactive decision-gating extension for pi — lets AI agents ask users questions with...
AKzar1el/god-prompt
The universal system prompt for AI software development. Enforces strict zero-hallucination...
m3dcodie/prompt-contract
The formal framework for Context Engineering. Move from "un-deterministic " to deterministic AI...