Memory & Knowledge MCP Servers for Windsurf (legacy)

Self-hosted hybrid memory & retrieval for AI apps: semantic + BM25 + temporal + graph recall over Qdrant/Memgraph, RRF fusion, 8-stage

Source-grounded memory layer for AI agents — cites its sources, says "I don't know" when it lacks evidence, and corrects superseded facts

Memory health monitor for OpenClaw — diagnose, guard, and remediate your agent's memory

A python-based MCP server for your local org mode files

MCP based Pocket Agent in vector db ( chroma) as storage

MCP server for reading LlamaIndex documents stored in Qdrant vector database

A generic RAG MCP server with pluggable embedding providers and vector stores

Local semantic search for markdown notes — MCP server

Persistent memory for Claude — MCP server with hierarchical memory, semantic search, and customizable persona

Spatial bidirectional persistent memory MCP server for LLMs - vector-based semantic memory as a navigable landscape

A dynamic, agent/LLM-friendly SQLite memory bank for MCP servers with semantic search capabilities.

Knowledge-graph memory server using Supabase with pgvector for semantic search.

MCP server for managing task contexts.

Vendor-agnostic cognitive persistence layer for AI agents.

Vidurai — Local-First AI Memory Layer for LLMs. Give Claude, ChatGPT, and Copilot persistent context without cloud sync.

Wadachi (轍) — persistent memory + semantic search MCP server for AI agents. Formerly Engram.

Persistent graph-backed conversational memory for AI agents.

Self-Evolving RAG for AI Agents — A cross-app persistent memory system where agents autonomously write, retrieve, and evolve their knowledge

Zero-config, traceable, MCP-native long-term memory for agents.

Agent memory in a single SQLite file — no vector DB, no server, no cloud. Keyword recall on stdlib alone; torch-free hybrid semantic search

A neutral, persistent working-state broker that keeps your AI coding tools (Claude, Cursor, …) on the same page — over MCP.