"BEM" matching MCP servers:

Multi-modal RAG engine for AI assistants. Stores conversation history, conclusions, diffs, error traces, and other development artifacts in LanceDB with vector search, multi-factor scoring, and an LLM-driven consolidation pipeline.

Bee by HEOSSI is a governed MCP server exposing 14 tools for specialist intelligence, code, security, research, provenance, usage, tenant-scoped documents and memory, and Quantum Reasoning Lab workflows. Hosted calls are authenticated, plan- and policy-gated, and metered.

Provides persistent memory for AI assistants, enabling context retention across sessions through hybrid search and memory management tools.

Provides persistent long-term memory (semantic RAG) for AI coding assistants, enabling them to store and semantically search code and documentation across chat sessions without token limits.

Enables persistent memory for AI agents, combining episodic and semantic memory with LLM reasoning, accessible via MCP.

Enables AI agents to save, search, and manage local Chinese semantic memories on demand, with support for updating, merging, and Obsidian-style linking.

Provides persistent, graph-based memory for AI agents using Neo4j and vector embeddings, enabling semantic recall across sessions via MCP.

An MCP server and background daemon that captures Discord and Telegram conversations locally to provide persistent memory for Claude Code sessions. It enables hybrid search and automatic context injection of chat history to maintain continuity across development sessions.

A local MCP server that gives AI copilots a shared, portable long-term memory backed by an embedded knowledge graph, with semantic search and export/import capabilities.

Provides a cross-session memory system for AI assistants via MCP, with markdown-based storage, BM25 retrieval, and tools for writing, searching, reading, and managing memories.

Persistent, auditable memory for AI agents. Hybrid BM25 + vector recall with 18 MCP tools, adaptive block metadata (A-MEM), intent-aware routing, contradiction detection, and governance workflows. Zero external dependencies. Drop-in memory for Claude Code and any MCP-compatible agent.

A universal MCP server providing persistent, structured memory through a knowledge graph with graph storage, semantic vector search, and multi-hop traversal for AI agents and IDEs.

Graph-relational memory MCP server for persistent LLM memory, featuring wikilinks, BM25 auto-linking, spreading activation, and synaptic decay across five memory layers.

Your AI forgets everything between sessions. This fixes that — 98%+ retrieval accuracy, With llm 100% on LongMemEval, 99% token savings. 44 MCP tools. Fully local, zero cost.

Local-first hierarchical memory for AI coding agents, providing automatic session capture, belief consolidation, and relevant memory injection via an MCP server.

Drop-in memory layer for AI coding agents, upgrading them from chat history to a governed Memory OS with hybrid search, contradiction detection, and safe governance.

Enables indexing and searching Obsidian notes via MCP, using Cloudflare's serverless platform for cost-effective vector embeddings and AI-powered search.

An MCP server that gives AI assistants a local YouTube memory: transcribe videos, store and search transcripts, follow subscriptions, and generate summaries, timestamped highlights, and digests, all on your machine with no cloud or API keys.

Provides an intelligent, graph-based memory system for LLM agents using the Zettelkasten principle, enabling automatic note construction, semantic linking, memory evolution, and autonomous graph maintenance with background optimization processes.

Provides a coherent memory layer for LLM agents that models beliefs as nodes in a constraint network to detect and surface semantic contradictions. It uses local embeddings and a hybrid geometric-logical energy model to identify conflicting information that requires review.