Zer0Q/MKEvo-cognitive-runtime
A cognitive runtime architecture for LLM continuity, memory, identity, and safe pseudo-conscious agents.
Implements a **Consciousness State Controller** that governs seven operational modes (narrative, analytic, critical-metacognitive, etc.) rather than letting the LLM choose its own behavior, combined with structured memory (episodic, semantic, identity, procedural) and constitutional review pipelines. Built on Global Workspace Theory and Attention Schema Theory, it uses token-level self-simulation ("protention") to preview outputs before generation, enabling offline-capable cognitive loops on local hardware like NVIDIA DGX.
Stars
3
Forks
—
Language
—
License
GPL-3.0
Category
Last pushed
Dec 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Zer0Q/MKEvo-cognitive-runtime"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Fozikio/cortex-engine
Cognitive engine for AI agents — semantic memory, observations, embeddings, dream consolidation....
brain-tree-dev/brain-tree-os
Open source brain viewer and project management for AI agents. Give your AI a brain.
NateBJones-Projects/OB1
Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat...
vstorm-co/summarization-pydantic-ai
Context Management processor for Pydantic AI agents, providing LLM-powered summarization or...
inputlayer/inputlayer
Streaming reasoning layer for AI. Incremental rules engine with vector search, graph traversal,...