Built on Node.js runtime, providing cognitive tools for AI systems including thinking modes, memory management, and reasoning analysis
Implemented in TypeScript for type-safe cognitive processing, offering structured thinking tools and memory systems for AI applications
ThoughtMCP
Production-Ready AI Cognitive Architecture with Human-Like Memory and Reasoning
ThoughtMCP provides AI systems with persistent memory, parallel reasoning, and metacognitive capabilities through the Model Context Protocol (MCP).
Key Features
Five-Sector Memory: Episodic, Semantic, Procedural, Emotional, and Reflective memory types
Glass Box Observability: Real-time visualization of internal reasoning streams (Thought Console)
Cognitive Personalization: Configurable skepticism levels and thinking styles via User Profile
Visual Intelligence: 3D memory graph with Semantic Zooming and Level-of-Detail (LOD)
Parallel Reasoning: Four concurrent streams (Analytical, Creative, Critical, Synthetic)
Framework Selection: Eight systematic thinking frameworks with >80% selection accuracy
Metacognition: Confidence calibration, bias detection, emotion analysis
Production Ready: 75%+ test coverage, sub-200ms retrieval, PostgreSQL persistence
Quick Start
MCP Tools
Category | Tools | Description |
Memory |
| Persistent five-sector memory |
Reasoning |
| Multi-stream reasoning |
Metacognitive |
| Self-monitoring and quality check |
MCP Configuration
Web UI (Beta)
ThoughtMCP includes a web-based interface for visualizing memories and reasoning processes. The UI is currently in beta and under active development.
⚠️ Beta Notice: The UI is experimental and may have breaking changes between releases. Not recommended for production use yet.
Documentation
Guide | Description |
Getting started and basic usage | |
Tool schemas and examples | |
System design | |
Development workflow | |
Production deployment |
See docs/ for complete documentation.
Contributing
See CONTRIBUTING.md for guidelines.
License
MIT License - see LICENSE for details