MCP Server Directory

firatmio/aletheia

Project memory for coding agents whose memories carry code evidence, re-checked on every recall.

cuemap-dev/cuemap-mcp

Local memory and context retrieval for AI agents through CueMap.

baixianger/langchain-MCP

LangChain/LangGraph/DeepAgents knowledge + LangGraph agent debugging (Polly-like)

jordanhindo/lore

Lightweight MCP for infinite agent memory. Any agent, any session, anytime.

OnourImpram/mneme

Vault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.

AliceLJY/recallnest

Local-first memory for coding agents: hybrid vector/BM25 retrieval with reranking, knowledge graph, session checkpoint/resume and multi-scope isolation.

xChuCx/agent-memory

Git-native project memory for coding agents: Markdown in your repo, reviewable staged updates, secret/PII-safe and branch-aware, without cloud or vector DB.

ashlesh-t/cognirepo

Persistent memory and codebase context for coding agents: FAISS vector store, AST symbol index, knowledge graph, episodic journal and cross-agent handoff.

yaminbkk/NexusMem

Correlates failed shell commands and their exit codes with whatever later fixed them, alongside git diffs and docs, stored locally in SQLite.

pmady/gpu-mcp-server

NVIDIA GPU metrics as MCP tools — utilization, memory, temperature, power. Supports MIG.

camgitt/memoir

Persistent memory for AI coding tools via MCP. Remembers across sessions and machines.

mrfentmen/midi-tools-mcp

MIDI note math: note names, frequencies, and note numbers. No network and no key.

HZYAI/RagScore

Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

ailenshen/apple-notes-mcp

Read and write Apple Notes with bidirectional Markdown conversion: SQLite queries for listing and search, AppleScript for full CRUD.

Wynelson94/longhand

Persistent local memory for Claude Code: indexes all sessions verbatim into SQLite and ChromaDB for semantic recall across your history, with no API calls.

michael-denyer/memory-mcp

Two-tier memory (hot cache and cold semantic search) that promotes frequently used patterns, extracts knowledge from Claude outputs and links it in a graph.

vornicx/Midas

Local-first long-horizon agent memory: source-traceable recall, belief revision, selective forgetting and a guard against memory-driven destructive actions.

bolnet/attestor

Self-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log.

thebasedcapital/brainbox

Hebbian memory for AI agents. Learns file patterns, predicts next tools, saves tokens.

diegoperezg7/evalsmith-mcp

Evaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.

ozankasikci/global-agent-memory

Shared, project-aware memory for Claude Code, Codex, and other agents with human review.

maxtechera/hushdrop

Open-source artifact sharing for AI agents: private, branded, zero-knowledge links.

stonematt/mcp-obsidian-cli

Save chat notes from Claude Desktop to your vault — MCP on Obsidian CLI. Keep what matters.

tunahanaliozturk/partner-center-mcp

Unofficial Partner Center REST API knowledge & codegen assistant (scenarios, auth, errors).

Smart-AI-Memory/empathy-framework

Five-level AI collaboration system with persistent local-first memory via MemDocs and anticipatory capabilities.

bluzername/lennys-quotes

Search Lenny's Podcast transcripts with YouTube timestamps for product management insights on PRDs, strategy and PM careers.

mattjoyce/mcp-persona-sessions

Structured, persona-driven sessions for interview preparation, personal reflection and coaching, with timers and performance evaluation.

TheGoatPsy/mneme

Vault-native, accountable memory for Claude Code: Markdown is the source of truth, with no LLM on the Stop path and redaction before any derived store.

The-40-Thieves/obsidian-tc

Obsidian vault access with role-based access control, native search, multi-vault support, pluggable embeddings and SLSA provenance.

ellmos-ai/ellmos-homebase-mcp

Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.

primeline-ai/kairn

Local-first knowledge engine for AI agents: memory, graph, and recall over MCP.

dominiclachance/neurakeep

Local-first, source-cited memory for AI agents with proposal review, failure memory, and MCP tools.

goyohan0611-png/turnbook

Local long-term memory shared by all your AI agents, kept word for word on your own PC.

Cavinooo/claude-find

Retrieve memory from across your Claude Code sessions on demand.

phillipclapham/anneal-memory

Two-layer memory for AI agents with an immune system. Zero dependencies.

everest-an/Awareness-Market

Local-first persistent memory for AI coding agents - 96.0% R@5 on LongMemEval, zero LLM calls.

arjunkumargiri/cortex

Shared, persistent memory for AI agents — works with Claude, Kiro, Cursor, or any MCP client.

var-gg/pindoc

Code-pinned team memory for AI coding agents — typed artifacts, MCP-native, self-host.

base76-research-lab/token-compressor

Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.

LuiggiVal08/toon-memory

Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM

juliangeymonat-jpg/wikimoth

Deterministic, token-minimal agent memory: multi-hop [[wikilink]] recall with no LLM in the loop.

xkumakichi/xaip-protocol

AI agents get on-chain identity, credentials, reputation, escrow, and persistent memory on XRPL.

TeamSafeAI/LIFE

Persistent identity for AI agents: servers for drives, relationships, semantic memory with decay, working threads, learned patterns, journaling and forecasting.

hyunjae-labs/lore

Local semantic search across Claude Code conversations with hybrid vector and keyword search, background indexing and per-project selection.

AkashGoenka/coldstart

Codebase memory for coding agents: a deterministic AST index finds task-relevant files, and in-repo Markdown notes flag themselves stale when code changes.

mlorentedev/hive

On-demand Obsidian vault access: adaptive context loading, full-text and ranked search, health checks, auto git commits and delegation to cheaper models.

IgorGanapolsky/mcp-memory-gateway

Pre-action gates that prevent coding agents from repeating known mistakes by turning captured feedback and failures into rules enforced via hooks.

Auctalis/nocturnusai

Deterministic reasoning engine for agent context compression: extracts structured facts with logical inference, proof chains and truth maintenance.