"Hybrid Memory Models Combining Relational, Graph, and RAG Approaches" matching MCP servers:

Enables sending one identical brief to multiple LLMs in parallel and returning every answer verbatim, unmerged, unranked, and unsynthesized.

Enables searching, comparing, and inspecting AI models by pricing, context window, and capabilities via the models.dev catalog.

Classifies development task complexity (LIGHT/MEDIUM/HEAVY) and recommends the most cost-efficient AI model per provider, enabling optimized model selection for coding tasks.

A powerful Model Context Protocol server that creates intelligent graph representations of your codebase with comprehensive semantic analysis capabilities, supporting 11 languages and 26 MCP methods.

A graph-based MCP server that provides AI coding agents with persistent memory to store patterns, track complex relationships, and retrieve knowledge across sessions. It leverages graph structures to handle temporal queries and relational paths that traditional vector stores often miss.

An MCP server that gives your agent a persistent project brain: vision, architecture decisions, conventions, roadmaps, and automatic session handoff.

Provides a dynamic SQLite-backed code knowledge graph for AI assistants, with MCP tools to inspect symbols, find dependency paths, and analyze code structure across multiple languages.

MCP server that lists available GitHub Models and compares responses from multiple models for the same prompt.

An MCP server that wraps the @apitomy/data-models library for querying, validating, and editing OpenAPI and AsyncAPI documents.

MCP server for context-aware codebase exploration using FastContext model, combining LLM-guided search with fuzzy matching to find relevant code snippets.

An MCP server that helps interact with and compare different GitHub Models, enabling listing, filtering, and comparing model responses.

Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.

A lean, local knowledge graph that joins a repo's code to its aSPARK delivery artifacts, enabling agents to trace user stories to code and assess impact of changes, served over MCP.

An enhanced fork of the official MCP memory server that enables persistent knowledge graph storage with automatic timestamps, tags, importance levels, date range search, comprehensive statistics, and multi-format export (JSON, CSV, GraphML).

Provides a decision memory layer for codebases, enabling AI agents to search, retrieve, and record business decisions with metadata filters and full-text search.

MCP server that turns coding workflows into explicit execution graphs (DAG) with deterministic command execution, human-in-the-loop gates, and tamper-proof run history for Claude Code.

Enables AI coding agents to store and query procedural knowledge as RDF triples, returning localized guidance, ranked next steps, and fastest successful paths while recording transition outcomes and task rollouts. Supports self-evolving graph maintenance through proposed mutations, held-out validation gating, negative memory of rejected proposals, and idempotent evidence imports.

Provides tools for AI-powered graph analysis, including relationship extraction, adjacency matrix creation, and network centrality calculations. It enables users to perform complex structural analysis and generate interactive D3.js visualizations from structured data.

Auto-captured, auto-recalled, path-scoped memory for AI coding agents and teams.

MCP server for managing project memory in AGENTS.md. Allows agents to record and remove durable facts using save/forget tools.