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).

44
/ 100
Emerging

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.

No Package No Dependents
Maintenance 13 / 25
Adoption 6 / 25
Maturity 9 / 25
Community 16 / 25

How are scores calculated?

Stars

17

Forks

7

Language

Python

License

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.