MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Persistent, self-linking memory for LLM agents in one Go binary with a CLI and an MCP server.
-
llm-memory-bridgegithub.com/user0857/llm-memory-bridgeupdated this year
给大模型加上“长期记忆”。通过 Chrome 插件和本地向量库实现自动记忆与上下文注入,支持 MCP 协议。
★ 1 -
Local-first MCP memory server with SQLite storage, scoped retrieval, governance, and audit trail for agents.
MIT -
llm-memorygithub.com/DamianTarnowski/llm-memoryupdated this year
Persistent, cross-model memory for LLM assistants — MCP server in .NET 10 over Postgres + pgvector + Apache AGE. Hybrid retrieval (vector + BM25 + graph PPR + LLM rerank), bi-temporal supersession, multi-tenant RLS.
MIT -
Recursive Language Models for Claude Code - Infinite memory solution inspired by MIT CSAIL paper
pypi MIT ★ 39 -
memcpgithub.com/maydali28/memcpupdated this year
A persistent memory MCP server for Claude Code - Recursive Language Model integration for Claude Code inspired by MIT CSAIL paper
pypi MIT ★ 18 -
A powerful, production-ready context management system for Large Language Models (LLMs). Built with ChromaDB and modern embedding technologies, it provides persistent, project-specific memory capabilities that enhance your AI's understanding and response quality.
MIT ★ 5 -
RCLL — self-hosted shared memory for a team of AI agents. Rooms, hierarchical L0-L3 depth, MCP. The read path never invokes a language model. We publish the measured cost of one shared store versus ten private ones. Fork of vectorize-io/hindsight (MIT).
npm MIT -
climategpt-performance-enhancementgithub.com/Mkatika37/climategpt-performance-enhancementupdated this year
Grounds a climate language model in real satellite (NASA VIIRS) and water-risk (WRI Aqueduct) data via MCP tools, so answers trace back to evidence, not just the model's memory.
-
MemoGraphgithub.com/Indhar01/MemoGraphupdated this year
MemoGraph is an intelligent personal memory management system for Large Language Models (LLMs) that transforms markdown notes into a queryable, graph-based knowledge base. It enables LLMs to access contextually relevant information from your personal knowledge vault using hybrid retrieval techniques.
pypi MIT ★ 4 -
my-local-storage-mcpgithub.com/avm-sistemas/my-local-storage-mcpupdated this year
A pragmatic, low-overhead Model Context Protocol (MCP) server that provides Large Language Models (LLMs) with a persistent, local long-term memory.
GPL-3.0 ★ 4 -
long-term-memory-mcpgithub.com/Rotoslider/long-term-memory-mcpupdated this year
Large language model persistent memory module that lives outside the model itself
MIT ★ 34 -
myBrAIngithub.com/lilium360/myBrAInupdated this year
myBrAIn is an MCP (Model Context Protocol) server designed to provide persistent and contextual memory to language models (like Google Antigravity). It acts as a "second brain" for your development environment, allowing the AI to remember project rules, architectural decisions, and technical insights across different chat sessions
MIT ★ 32 -
Memory framework for LLM
MIT -
A simple MCP server that stores and retrieves memories from multiple LLMs.
npm MIT ★ 23 -
Agent memory for Claude Code, Cursor, Codex: MCP server + Graph RAG over your Obsidian or markdown notes, a search layer for a Karpathy-style LLM Wiki. Wikilinks are the graph, SQLite the only store.
pypi MIT ★ 15 -
@jerrysv/memory-mcp-serverupdated this year
MCP server for LLM long-term memory storage and recall
npm MIT -
agent-memory-sitegithub.com/nikopastore/agent-memory-siteupdated this year
Compile your Markdown vault into a portable agent memory. One build, every agent: Claude, Codex, Cursor, MCP, llms.txt.
npm MIT -
MemOS - Universal local-first persistent memory layer for AI agents and LLMs
npm MIT ★ 10 -
MCP Server for LLM Long-Term Memory using KG and Google Drive
npm MIT -
hermes-memoryupdated this year
Persistent, structured memory layer for LLM agents — MCP-native, zero infra, SQLite-backed.
pypi MIT -
loci-memoryupdated this year
Holographic based MCP Server - Provide memory capabilities using Vector Database for LLM Applications
pypi MIT -
Associative Memory MCP Server for LLMs - Knowledge management system with hierarchical scope organization
pypi MIT -
mcp-super-memorygithub.com/donggyun112/super-memoryupdated this year
N:M Associative Memory System for LLM Agents
npm MIT -
High-performance Go tools for LLM Agents (MCP/CLI). 100x faster than Python. Includes native MCP Server, token-optimized search, and persistent project memory.
go MIT ★ 3 -
Persistent, bi-temporal memory for LLM agents — local-first, MCP-native, Obsidian-readable.
pypi Apache-2.0 -
Persistent AI memory with crossover — your AI at home shares the same memory as your AI at work. What one LLM learns, all your AIs know. Memory + PKM for Claude, GPT, Gemini & local models. MCP-native. (Engine stays private.)
npm MIT -
Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Importance scoring, contradiction resolution, confidence-aware retrieval.
go Apache-2.0 ★ 50 -
titan-memory-mcpstale
A neural memory system for LLMs that can learn and predict sequences while maintaining state
npm MIT -
Agent-Memorygithub.com/PREETHAM1590/Agent-Memoryupdated this year
AI-powered memory system for agents. Provides persistent, context-aware memory storage with MCP integration for LLM applications.
MIT -
spatial-memory-mcpgithub.com/arman-tech/spatial-memory-mcpupdated this year
Spatial bidirectional persistent memory MCP server for LLMs - vector-based semantic memory as a navigable landscape
pypi MIT -
Portable semantic memory layer for LLM agents over MCP
MIT ★ 2 -
memory-bridge-mcpgithub.com/le-vai/memory-bridgeupdated this year
Unified MCP memory server bridging Mind (concept graph) and Honcho (semantic vector) memory with episodic timeline and LLM synthesis
pypi MIT License -
MCP server giving LLM clients shared long-term memory with semantic search (sentence-transformers, FAISS, SQLite).
★ 1 -
Self-hosted, markdown-first memory for LLM agents across devices and sessions
MIT ★ 2 -
@iflow-mcp/adshaa-mempalacejsgithub.com/iflow-mcp/adshaa-mempalacejsupdated this year
Native TypeScript AI memory system and MCP server (Zero-LLM, LanceDB)
npm ISC -
Voice + chat assistant with long-term memory built from scratch: LLM fact extraction, pgvector, conflict resolution (90% held-out accuracy vs 0% baseline), relevance-filtered RAG, a memory-poisoning screen, and Langfuse tracing. LangGraph, FastAPI, React/TS, MCP
-
ctx-memorygithub.com/ghadisaab/llm-memoryupdated this year
Persistent memory layer for LLM coding agents (Claude Code, Codex, Gemini, OpenCode) — zero cloud, local SQLite + MCP
npm MIT -
consolidation-memorygithub.com/charliee1w/consolidation-memoryupdated this year
Local-first persistent memory for AI agents — store, recall, and consolidate knowledge across sessions using FAISS, SQLite, and any LLM. MCP server for coding agents and any MCP client.
pypi MIT ★ 8 -
Semantic, persistent knowledge graph memory for LLM-based and multi-agent systems, exposed via the Model Context Protocol (MCP).
MIT ★ 4 -
Persistent memory + workflow orchestration as an MCP server. 78 canonical tools across 21 namespaces, SQLite-backed, with an LLM-as-judge drift gate and a vibe-flow loop (spec to artifact to drift to publish).
npm NOASSERTION ★ 2 -
A long-term memory service for any LLM: REST, MCP and a CLI on Postgres with pgvector. No generative model inside.
MIT -
.NET SDK and MCP server implementing a cognitive science-based 3-axis memory system (type x scope x tier) for LLM context management beyond finite context windows.
nuget MIT ★ 1 -
Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.
npm MIT ★ 25 -
Personal cross-LLM memory layer. Markdown files are the source of truth; the server exposes them over MCP so Claude/ChatGPT/Cursor/etc. share one memory.
MIT ★ 1 -
The associative memory layer for LLM agents — recall by association, not just similarity.
npm MIT ★ 3 -
Private, encrypted on-device memory for macOS: captures what you read, serves it to any LLM over MCP, and finds the loops you left open.
AGPL-3.0 -
Governed multi-agent memory for AI agents — hybrid markdown+SQLite, FTS, vector search, LLM reranking. One Go binary, MCP stdio + HTTP + SSE.
Apache-2.0 ★ 1 -
becomerupdated this year
Persistent memory API for any LLM — Python SDK + MCP server
pypi MIT License -
vMemgithub.com/soolaugust/vMemupdated this year
Zero context compaction for Claude Code & LLM agents. Persistent memory powered by OS primitives (demand paging, kswapd eviction, mlock pinning). Single SQLite file, MCP-native, multi-agent shared.
★ 5 -
Persistent memory for Claude Code, Codex CLI, Cursor and any MCP client. Local-first, MCP 2026-07-28, zero LLM calls in the hot path. One command to install.
npm MIT -
Tool-agnostic long-term memory for LLM agents (HTTP API, MCP, CLI, embedded WebUI)
MIT -
Local-first knowledge graph memory for LLMs and AI agents: MCP server, RAG context, provenance
pypi MIT -
Local-first memory engine for AI-agent teams — private/team/project ACL, associative recall, federated sync, and a built-in MCP server. One SQLite file, no LLM required. Apache-2.0.
Apache-2.0 ★ 9 -
给 AI Agent 的长期记忆库:会遗忘、会弃答、零依赖 · Long-term memory for LLM agents with forgetting curve, abstention, SQLite/WAL, multi-process writes and an MCP server. No vector DB required.
MIT ★ 1 -
Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns from use, forgets the irrelevant, and strengthens what matters. No cloud, no API keys.
pypi Apache-2.0 ★ 323 -
Neural LLM Memory MCP Server - High-performance neural memory system for AI assistants
npm MIT -
MCP Server for MnemoX Lite - Semantic Memory for LLMs
npm MIT -
Source-grounded MCP memory runtime and Obsidian-compatible vault template for LLM agents.
NOASSERTION ★ 76 -
Memory module for LLMs and Agents with MCP
pypi MIT ★ 6