deliberate-reasoning-engine and Adaptive-Graph-of-Thoughts-MCP-server

Maintenance 13/25
Adoption 3/25
Maturity 24/25
Community 12/25
Maintenance 10/25
Adoption 7/25
Maturity 15/25
Community 17/25
Stars: 4
Forks: 1
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
Stars: 27
Forks: 8
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No risk flags
No Package No Dependents

About deliberate-reasoning-engine

haasonsaas/deliberate-reasoning-engine

MCP server that transforms linear AI reasoning into structured, auditable thought graphs

Implements semantic thought categorization (objectives, hypotheses, assumptions, evidence, critiques) as nodes in a directed acyclic graph with explicit dependency tracking and cascade invalidation—when an assumption is disproven, all dependent reasoning automatically becomes stale. Integrates with Claude Desktop via the Model Context Protocol, exposing tools for logging structured thoughts, retrieving the reasoning graph, and invalidating assumptions to maintain reasoning consistency.

About Adaptive-Graph-of-Thoughts-MCP-server

SaptaDey/Adaptive-Graph-of-Thoughts-MCP-server

LLM Reasoning Framework for Scientific Research

Implements an 8-stage reasoning pipeline with Neo4j graph storage and MCP protocol exposure, enabling real-time evidence integration from PubMed, Google Scholar, and Exa Search with multi-dimensional confidence scoring. Built on FastAPI with async Neo4j operations and designed for seamless Claude Desktop/VS Code integration through native MCP endpoints. Supports uncertainty quantification and dynamic hypothesis pruning to refine reasoning chains into evidence-backed scientific conclusions.

Scores updated daily from GitHub, PyPI, and npm data. How scores work