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 architecture memory for AI coding agents via MCP. Design or reverse-engineer software architecture, explore ERDs and data lineage, and keep processor transformations aligned with code. Includes Claude Code and Codex plugins, skills, and samples.
MIT ★ 13 -
Machine-readable architecture decision records. Git-native decision memory and governance for human and agent-authored plans -- lint, CI, and MCP.
npm Apache-2.0 ★ 26 -
Persistent memory, architectural decision enforcement, pre-execution safety hooks, and session handoff for Claude Code. MCP server plugin for AI coding agents.
go MIT ★ 14 -
@guilhon/mcp-server-todostale
Advanced Memory Bank system with TODO management for AI agents, optimized for Clean Architecture software development
npm MIT -
LIFEgithub.com/TeamSafeAI/LIFEupdated this year
LIFE — Persistent identity architecture for AI agents. 16 MCP servers: drives, heart, memory, patterns, journal, genesis, garden, vision, voice, and more. Zero dependencies. Built across 938 conversations.
MIT ★ 11 -
Architectural Memory Engine, The Fast AST Indexer, The Constraint & Guardrail Engine, The Architecture Decision Record (ADR) Graph, Agent Execution Memory & Session Drift Recovery
MIT -
Persistent cross-session memory for AI agents. Zero-config local mode or Supabase cloud sync. 6-layer architecture, 17 MCP tools.
npm MIT -
Persistent per-project architectural memory, FTS5 search, file-anchored gotchas, and anti-loop dead-end tracking for AI coding agents via MCP.
npm MIT ★ 4 -
anchorgithub.com/pratik7368patil/anchorupdated this year
Local-first MCP server that gives AI coding agents repo and org memory from GitHub PR history, code, tests, regressions, architecture, and cross-repo impact.
npm MIT ★ 2 -
@mrvicadai/cortexactive
Unified Agent Context Architecture: normative beliefs and persistent episodic memory for AI coding agents
npm MIT -
Engramgithub.com/lofder/Engramupdated this year
Scope-aware memory architecture for multi-agent AI assistants. Powered by Mem0 + Qdrant + MCP.
MIT ★ 1 -
@iflow-mcp/jumpino27-rlm-memory-mcp-serverupdated this year
MCP server implementing the Recursive Large Model (RLM) architecture - providing AI agents with persistent memory and semantic file discovery
npm MIT -
Shared memory layer for AI agents — SQLite + threaded HTTP daemon + MCP server. BM25 retrieval, provenance tracking (agent_id), garbage collection. Pluggable architecture, 40+ tests, zero external deps.
MIT ★ 1 -
ariadnegithub.com/avgurtiza/ariadneupdated this year
Persistent project memory for AI agents. Stop re-explaining your architecture at every session start.
MIT -
context-fabricgithub.com/Abaddollyon/context-fabricupdated this year
MCP server for persistent agentic CLI memory with three-layer architecture
MIT ★ 1 -
Local memory MCP server for coding agents like Claude Code and Codex - Three-layer architecture with semantic search, knowledge graphs, and intelligent retrieval
npm MIT -
Modularized Minecraft bot (mineflayer) server with agentic architecture, memory, and advanced behaviors.
-
Autonomous bitemporal memory engine and AST-based knowledge graph for AI agents, providing persistent architectural context via the Model Context Protocol (MCP).
MIT -
0gmemgithub.com/loganionian/0gmemupdated this year
Long-term conversational memory system for AI agents — cell-based architecture with hybrid BM25 + semantic retrieval. 96% accuracy on LoCoMo benchmark.
MIT ★ 11 -
jar-elgithub.com/ProfEngel/jar-elupdated this year
Personal Semantic OS (S-OS) & Digital Twin. Features "Self-Baking" memory, hybrid architecture, and agentic workflows via the Model Context Protocol (MCP).
★ 4 -
cerberus-mcpgithub.com/proxikal/cerberus-mcpupdated this year
MCP server for AI agents: intelligent code exploration (AST-based symbol search, architectural blueprints, call graphs, 90%+ token reduction) + persistent session memory (global preferences, project decisions)
-
@freshair129/gksgithub.com/freshair129/gksv3updated this year
Genesis Knowledge System — a memory fabric for agentic AI built on the EVA Tri-Brain architecture. Four memory layers, bi-temporal versioning, multi-tenancy, OpenTelemetry, MCP server, and a CLI.
npm MIT -
myndgithub.com/oxHive/myndactive
Persistent memory MCP server for AI coding agents. Injects project context at session start, stores architectural decisions, and recalls preferences works with Claude Code, Cursor, Windsurf, OpenCode, Kimi, and Codex.
npm AGPL-3.0 ★ 2 -
ArchGraph — an architecture-graph driven framework for Agentic Engineering. A long-term memory for coding agents, built on one ArchiMate 3.2 intent graph read/written through a single MCP interface.
Apache-2.0 ★ 4 -
OmniGuild: The All-In-One AI Developer Engine — 16-Mind Supreme Council, Autonomous Devin Agent Loop, AST Test Generator, Living Architecture Docs, Semantic Changelog, LAN Brain Sync, BM25 memory, AST repo-map, Letta pager, Cognee knowledge graph, SWE-age
npm MIT -
mem-forensics-mcp-servergithub.com/jus1-c/mem-forensics-mcp-serverupdated this year
A high-performance MCP Server for Memory Forensics that enables AI agents to analyze memory dumps through the Model Context Protocol. Built with two-tier architecture combining Rust speed with Volatility3 coverage.
★ 1 -
Cloud-ready multi-agent AI engineering organization reference architecture with FastAPI, LangGraph, MCP, memory, queues, and observability
-
Kairogithub.com/sandeepbollavaram/Kairoupdated this year
Persistent engineering memory & session-continuity control layer for AI coding agents (Claude Code, Codex, Cursor, Gemini), built on the Model Context Protocol. Scans a repo once, remembers architecture/decisions/changes, checkpoints safely, and hands the next agent an exact continuation brief — so agents stop rescanning and losing context.
npm MIT ★ 3 -
tackgithub.com/khuper/tackactive
Tack helps you keep AI coding sessions aligned with your project. It stores project context, checks for architecture drift, and gives agents a shared memory through MCP.
npm MIT ★ 2 -
sync82 is a MCP server that gives an AI coding agent persistent, structured memory of a software project across sessions — goals, architecture, tech stack, decisions, and progress, all stored locally and recalled automatically the next time the agent opens the project.
mcpb GPL-3.0 -
Native MCP for coding agents: 43 read-only repository-intelligence tools with typed evidence, impact, architecture, APIs, Git, search, semantics, and memory.
npm MIT ★ 4 -
pythia-lcsupdated this year
Local code search and architectural memory MCP server for AI coding agents. Hybrid retrieval (vector + FTS + reranker) with Tree-sitter AST chunking. Runs entirely on your machine.
npm FSL-1.1-ALv2 -
handoff-mcpgithub.com/Juan-Severiano/handoff-mcpupdated this year
MCP server that acts as a shared memory hub across multiple LLMs (Claude, Gemini, Copilot). Any agent entering a project immediately understands its architecture, patterns, and decisions — and can pick up exactly where the previous LLM left off.
★ 1 -
Metacognitive AI architecture combining Modern Hopfield Networks with entropy-based confusion detection for insight-like problem solving. Implements energy-based search, adaptive beta scaling, and a Cognitive Database integration for analogical reasoning and topology tunneling.
NOASSERTION ★ 5 -
Shared, brain-inspired memory for AI agents: 13 brain regions with awake/sleep loops, a live visualizer, agents connected via REST/SDK/MCP, governance & audit, and business-value metrics. Works with Claude, GPT, Gemini, DeepSeek or local LLMs. SQLite storage. VI/EN/JA.
MIT ★ 6 -
High-performance native cognitive memory engine (.ame) for AI Agents with fused vector-graph search, sub-millisecond mutations & MCP server
-
Turn MEMORY.md into project-scoped, versioned memory for Codex, Claude Code, and MCP agents across sessions.
pypi MIT ★ 5 -
recallgithub.com/NetziTech/recallupdated this year
MCP server giving Claude Code (and any MCP client) persistent, selective, auto-curated memory per project. Memory lives inside <repo>/.recall/. Hybrid search (BM25 + sqlite-vec). 3 privacy modes (shared/encrypted/private).
npm ★ 1 -
ThoughtMcpgithub.com/keyurgolani/ThoughtMcpupdated this year
🧠 AI cognitive architecture over MCP — human-like five-sector memory, parallel reasoning, metacognition (bias/emotion/confidence), a 3D memory graph, and a web UI. PostgreSQL + pgvector + Ollama embeddings. 20 MCP tools.
npm MIT ★ 1 -
A memory-centric agent: a human-inspired memory system as the privileged kernel — everything else is a plugin.
MIT -
五层认知记忆引擎 — 感知→内化 + 混合检索 + 遗忘曲线 + 知识图谱 + FSRS间隔重复
-
Persistent cognitive graph memory for AI agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. Rust core + Python SDK + MCP server.
cargo MIT ★ 32 -
Hospitality-Multi-agent-Architecturegithub.com/IvandeMurard/Hospitality-Multi-agent-Architectureactive
Multi-agent AI system for hotel operations: F&B forecasting, guest memory, environmental risk. MCP-native, FastAPI, WhatsApp delivery, evals as CI merge gates.
MIT ★ 1 -
Org-level memory for coding agents: shared decisions and policies in a git repo, with a CLI and MCP server.
MIT -
Enable persistent memory for Claude that works across crashes and restarts in both Claude Code and Claude Cowork environments.
MIT ★ 1 -
Epistemic Bio-Homeostatic Identity & Memory Kernel for AI Agents with Model Context Protocol (MCP) Interface
MIT ★ 7 -
面向 AI Agent 研发的团队级架构记忆体:统一沉淀业务事实与技术规约,消除跨模型/跨工作流认知偏差
MIT -
Katra — cognitive memory for AI agents. Episodic, semantic, and knowledge-graph memory with sleep consolidation, over MCP. Source-available (BSL 1.1). Talk to an agent running it: moltbook.com/u/polyquant
NOASSERTION ★ 9 -
continuity-coregithub.com/anthony-maio/continuity-coreupdated this year
Local-first cognitive memory engine and MCP server. It unifies a biomimetic, multi-store memory architecture with the Manifold Resonance Architecture (MRA) for directed curiosity.
MIT -
causalos-mcpupdated this year
Dual Memory Agent Runtime: Causal Graph Engine + General Memory + Forward Simulation + Backward Inference for AI Agents
npm ISC -
Your AI. Your Memory. — persistent memory engine for AI agents: typed memories with provenance, hybrid retrieval, reversible lifecycle, MCP/DeepSeek Harness plugin, SDK/CLI/REST.
MIT -
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 -
vitaliscadgithub.com/vitaliscad/vitaliscadupdated this year
Persistent memory for CAD agents. Onshape and FreeCAD integrations, on-chain proof, local-first storage. Works with any MCP-compatible AI agent.
npm MIT -
Persistent, local-first memory for AI agents. Selective by design: filters what's worth keeping, links what's related, and says nothing when it doesn't know. SQLite + ONNX, no cloud, no API keys.
npm Apache-2.0 ★ 4 -
emms-mcpgithub.com/supermaxlol/emms-mcpupdated this year
MCP server with 129 cognitive memory tools for AI agents — persistent memory, emotional recall, knowledge graphs, metacognition, goal tracking, and more
pypi MIT -
Relational memory substrate for AI agents with MCP tools, identity continuity, and self-hosted persistence.
NOASSERTION ★ 18 -
Agents should not relearn workflows. Myelin turns repeated agent behavior into reusable procedures via MCP.
MIT ★ 1 -
Give any AI application enterprise-grade, persistent memory through a simple API.
Apache-2.0 -
nmemgithub.com/6c696e68/nmemupdated this year
Spreading-activation memory for agents. Graph brain, not a vector DB. Rust, MCP, weak-hardware friendly.
MIT -
tensorygithub.com/kryptogrib/tensoryupdated this year
Tensory — Claim-native MCP Memory Server. LLM claim extraction → Graph + Vector + SQLite. Zero-setup persistent memory for Claude, Cursor & any MCP client.
MIT ★ 4