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

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

RAG Knowledge Graph - MCP server providing AI-powered tools and automation by MEOK AI Labs

Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.

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.

Local repo-intelligence MCP for coding agents: indexes source, symbols, call graphs, git/GitHub history, and source-bound repo memories into local database.

Provides a personal hybrid running and strength training coach that integrates with Intervals.icu, offering 28-day plans, activity reconciliation, and delivery of scheduled workouts to calendars via MCP.

Enables AI agents to synthesize and update hierarchical episodic and semantic user profile memory graphs through MCP, using deterministic zero-dependency Python processing with JSON Schema validation.

A local MCP server that gives AI assistants persistent long-term memory using a biological neural architecture with cortex, synapses, and hippocampus.

Embedded, local-first agent memory: facts extracted into a per-namespace SQLite file (vec0 + FTS5) with hybrid retrieval and point-in-time (time-travel) queries. ADD-only history over stdio — no server process, no cloud dependency.

Local-first agent memory & knowledge service: hybrid retrieval (vector + BM25/RRF) + memory governance (decay, dedup, freshness), REST + MCP dual protocol, fully offline without LLM. Python.

Provides a unified MCP interface over Uniswap V2, V3, and V4 across multiple chains via The Graph, enabling agents to query token prices, top pools, pairs, and recent swaps with clean JSON output.

Local-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware and secret-safe.

Provides AI agents with persistent, long-term memory via OKF-formatted markdown and SQLite indexing, enabling stateful storage, retrieval, and search across sessions.

MCP server for querying AAVE V2/V3 lending protocol and governance data via The Graph subgraphs. Exposes 14 tools and 5 guided prompts that any AI agent (Claude, Cursor, Copilot, etc.) can use to query lending markets, user positions, health factors, liquidations, flash loans, rate history, and AAVE governance — across 7 chains (Ethereum, Base, Arbitrum, Polygon, Optimism, Avalanche, Fantom) via

"primitive" RAG-like web search model context protocol server that runs locally. ✨ no APIs ✨

RAG Knowledge - MCP server providing AI-powered tools and automation by MEOK AI Labs

Semantic and exact retrieval over 22M Taiwan court judgments with built-in citation guardrails — bundles carry a read-whitelist so downstream models cannot cite judgments whose reasoning was never read. Also provides exact lookup of administrative interpretations with lifecycle status (repealed / superseded / unverified).

A persistent, project-scoped memory layer for AI coding agents, providing 39 tools for capturing, searching, deduplicating, relating, and maintaining memory records across long-running coding sessions.

Enables AI assistants to remember and retrieve user information across conversations using vector search technology. Built on Cloudflare infrastructure with isolated user namespaces for secure, persistent memory storage.

Persistent long-term memory for AI agents — semantic recall across Claude, Cursor, ChatGPT & MCP.