Neuro-Symbolic AI with Knowledge Graph | Logic Language for LLM 🌱🐋🌍

Adaptive Reasoning Engine for Efficient and Context-Aware Intelligence

Open WebUI Logic Tree Multi-Model LLM Project - Advanced AI reasoning with Sakana AI's AB-MCTS and sophisticated multi-model collaboration

Turn stories, strategies, or systems into insight. Auto-generate Dialectical Wheels (DWs) from any text to reveal blind spots, surface polarities, and trace dynamic paths toward synthesis. DWs are semantic maps that expose tension, transformation, and coherence within a system—whether narrative, ethical, organizational, or technological.

A stateful AI agent framework powered by the Cognitive Lattice to solve complex tasks with persistent memory and reliable tool orchestration.

A Python-based logical reasoning system combining rule-based engines with Large Language Models (LLMs) for business automation. Supports deduction and hypothesis testing, partial fact completion, and automated fact retrieval via documents or chat. Features include explainable reasoning, workflow integration, and customizable knowledge bases.

Recursive reasoning engine for AI agents and vector databases. Powered by MIT's RLM.

An intelligent financial advisor chatbot powered by LLaMA-3, built with LangGraph for structured reasoning, RAG from The Intelligent Investor PDF, and real-time data from Yahoo Finance and DuckDuckGo. The system dynamically orchestrates tools, handles fallbacks, and maintains conversation memory.

AI that tries to show its work. Transparent, private, and easy to run yourself

🧠 Open-source AI reasoning research platform — persistent reasoning graphs, multi-agent swarms, Graph-of-Thoughts, and MemGPT-style memory. Built with Claude Opus 4.6 by Anthropic. Explore, verify, and fork AI thinking in real-time.

Episteme is a persistent epistemic reasoning system with non-monotonic logic, explicit conflict detection, belief revision, and quantitative belief lifecycle management layered on top of symbolic inference.

A collection of meticulously crafted system prompts designed to transform general-purpose LLMs into specialized, value-aligned reasoning engines.

ABES: Adaptive Belief Ecology System. A headless cognitive memory engine for autonomous AI. Beliefs act as living organisms that decay, conflict, and mutate over time, managed by a 15 phase scheduler and an optional RL tuning layer.

Integrated cognitive agent system combining hierarchical management, memory systems, and cognitive processing

A blueprint for a synthetic mind. This AI strategist doesn't just reason; it proactively gathers real-time data and simulates future outcomes. Its cognitive architecture features a parallel Cognitive Loop with metacognition and focused attention, all defined in a symbolic, LLM-to-LLM protocol.

CXS is a deterministic continuity standard for long-range, multi-session, and long-chat LLM reasoning. It enables GPT, Claude, Grok, Gemini, and local models to share state through a human-readable Continuity Passport with strict-mode rules, drift detection/repair, and full chain-of-custody. Validated across 250+ continuity tests.

AVRT™ — The first ethical voice middleware firewall for AI, built to score reasoning with SPIEL™ and THT™. SHA‑256 hashing + blockchain-ready proof system. Created by Jason Proper. © 2025 BGBH Threads LLC.

Active development branch of the G2 Researcher — patched, debugged, and upgraded baseline with improved stability, logging, and dry-run support. Main workspace for ongoing evolution.

A cognitive AI agent that overcomes the limitations of LLMs. Project Atma features advanced reasoning, planning, and long-term memory capabilities, all with a transparent, state-based architecture. Your AI-powered problem solver.

Verity is a forensic verification AI that analyzes contradictory evidence across multiple formats (video, audio, documents, images) to reconstruct verified timelines and detect inconsistencies. Built with Gemini 3's advanced reasoning capabilities and transparent thinking mode.

An experimental cognitive architecture built on an LLM, designed for advanced reasoning and dynamic tool creation.

Multi-agent reasoning system with loop awareness, human-in-the-loop arbitration, and long-term reasoning memory.

Hoshimiya Script / StarPolaris OS — internal multi-layer AI architecture for LLMs. Self-contained behavioral OS (Type-G Trinity).

Local LLM + RAG knowledge assistant with structured ingestion, typed metadata, and reproducible indexing (Python).

Symbiotic Prompting & Ontological Routing Engine. A fractal, biomimetic cognitive architecture. We don't teach LLMs what to say; we give them a distributed, self-routing ecosystem to choose how to think.

Flutter AI application

SUBIT‑64 is a semantic architecture for interpretable cognitive agents. It defines a four‑layer pipeline — Interpreter → Reasoning → Topology → Persona — enabling structured cognition, stable behavior, and transparent multi‑agent coordination. Model‑agnostic. Modular. Canonical.

AI Venture Architect powered by Gemini 3 Pro. Uses deep reasoning (Thinking Config) and Lateral Thinking frameworks to generate, visualize, and rank startup ideas.

Self-evolving recursive AI reasoning system — φ-governed tool use, multi-agent code review, workflow orchestration, and persistent spiral memory, built on E8 Lie group geometry and golden ratio mathematics

The central hub for Mina Ecosystem. A multi-agent reasoning system focusing on critical thinking and loop awareness.