Umbraflamma/SANCTIS-cognitive-architecture
A model-agnostic layered cognitive framework for LLMs. Improves coherence, emotional clarity, structural reasoning, and creative depth across GPT, Claude, Gemini, Grok, Mistral, and others—while reducing token waste and internal contradiction.
This project offers a specialized framework to improve how large language models (LLMs) think and respond, especially during long or complex conversations. It takes your prompts and an LLM's initial thoughts, then guides the LLM to produce more coherent, consistent, and emotionally stable responses. Knowledge workers, content creators, researchers, and anyone relying on LLMs for critical tasks would find this valuable for better, more reliable AI interactions.
Use this if you need your AI assistant or generative AI to maintain logical consistency, avoid contradictions, handle complex or emotionally charged inputs, and stay on topic through extended interactions.
Not ideal if you're looking for a simple persona-creation tool or if your AI use cases are limited to very short, straightforward questions that don't require deep reasoning or long-term memory.
Stars
11
Forks
1
Language
—
License
—
Category
Last pushed
Feb 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Umbraflamma/SANCTIS-cognitive-architecture"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
edlsh/pi-ask-user
Interactive decision-gating extension for pi — lets AI agents ask users questions with...
akougkas/wtf-p
The academic meta-prompting framework for AI agents like Claude Code, Gemini CLI, OpenCode....
leeex1/Quillan-Ronin
Attempt at A. G. I. Strive to enhance it through iterative processes, continuously refining and...
appboypov/pew-pew-plaza-packs
AI-powered project management framework based on an opinionated view on effective prompts and a...
sancovp/the_sanctuary_system
This is a repo where I, OVP, am trying to learn thru allegories...