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.
-
Layered Memory MCP Server — Durable common-core memory for AI agents: L0 index, L1 knowledge, TODO and provenance, with deterministic persistence routing
pypi MIT -
mcp-memory-layergithub.com/chapmancl/mcp-memory-layerupdated this year
Persistent memory layer for AI agents — MCP server + REST API backed by MongoDB with vector search. Self-curating, schema-free, cross-session. Works with Claude, Copilot, Bedrock AgentCore, LangChain, CrewAI, AutoGen.
Apache-2.0 -
Memory for AI agents with rules that are kept, not just written - P0-P6 layered rules enforced in code, SQLite + PostgreSQL, MCP server, eval harness. PyPI: p-layers
MIT ★ 3 -
MemOS - Universal local-first persistent memory layer for AI agents and LLMs
npm MIT ★ 10 -
aethenegithub.com/Nuro-Labs/aetheneupdated this year
The Open-Source AI Memory Layer: store content, extract atomic memories, search semantically and recall context for AI agents. Self-hostable with an MCP server.
MIT ★ 6 -
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 -
p-layersupdated this year
Memory for AI agents with rules that are kept, not just written. P0-P6 layered rules enforced in code. SQLite + FTS5 + pluggable embeddings, PostgreSQL backend, MCP server, eval harness. (GitHub: p-layer)
pypi MIT -
@noelclaw/mcpgithub.com/noelclaw/mcpupdated this year
The runtime layer for Agentic AI. 121 MCP tools: persistent memory, autonomous agents, vault storage, scheduled workflows, DeFi on Base (base_mcp_*), Robinhood Chain tokenized stocks and arbitrary crypto with V3/V4 smart routing (rh_*), live market data,
npm MIT -
aide-memorygithub.com/aide-memory/aide-memoryupdated this year
Persistent memory layer for AI coding agents — your agent remembers what you taught it
npm NOASSERTION ★ 3 -
anamnegithub.com/venumittapalli576/anamneupdated this year
Brain-inspired local-first memory layer for Claude, Cursor, and any MCP-compatible AI tool. Three memory layers (episodic / scratchpad / working), ACT-R activation decay, 21 MCP tools. Local SQLite + ChromaDB, no SaaS.
MIT -
uml-memorygithub.com/unified-memory-layer/umlupdated this year
MCP server for Unified Memory Layer — persistent memory across AI coding tools
pypi MIT -
MCP memory layer for AI agents (Memora-based)
MIT ★ 1 -
mnemon-memorygithub.com/cipher813/mnemonupdated this year
Universal long-term memory layer for AI agents via MCP
pypi MIT -
ide-memory-mcpgithub.com/prasanna-pmpeople/ide-memory-mcpupdated this year
Cross-IDE persistent memory layer for AI coding agents via MCP
pypi MIT -
sagagithub.com/mopanc/sagaactive
Topic-grained, layered memory layer for AI coding agents — local-first, MCP, single binary. Plug Claude Code / Cursor / Windsurf / Antigravity into persistent memory across sessions and machines.
go Apache-2.0 ★ 1 -
Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth
npm -
decay-memorygithub.com/trssantos/decay-memoryupdated this year
Memory that forgets. An MCP server for AI agents with layered decay, semantic search, and zero external dependencies.
MIT -
Local-first, MCP-first portable memory, role, and skill layer for AI agents.
Apache-2.0 ★ 1 -
memory-governancegithub.com/mzyag/memory-governanceupdated this year
A governance layer for AI agent memory — access control, audit trails, retention policies, and PII redaction via MCP.
MIT -
arelaupdated this year
The AI's Memory Layer for Vibecoding - Context persistence via MCP
npm MIT -
mnemo-notegithub.com/fwgadmin/mnemoupdated this year
AI-native memory layer — notes, embeddings, and MCP for intelligence systems
npm MIT -
sovereign-universal-memory-mcpgithub.com/nnaveenraju/sovereign-universal-memory-mcpupdated this year
User-sovereign, vendor-neutral memory layer for AI tools and agents — exposed as an MCP server
npm (MIT OR Apache-2.0) -
origin-mcpgithub.com/7xuanlu/originupdated this year
Local-first memory layer for AI agents - MCP server
npm Apache-2.0 -
Best AI Memory Layer for Claude Code and MCP Agents in 2026
-
The memory layer for AI · Adaptive Memory And Fact Ordering System · Remote MCP server
NOASSERTION -
multimodemindupdated this year
Multi-store memory layer for AI agents, exposed over MCP
npm MIT -
A memory layer for AI Agents
Apache-2.0 ★ 84 -
The intentional memory layer for your AI agents.
go MIT ★ 25 -
local-memorygithub.com/RanchoCooper/local-memoryupdated this year
LocalMemory is a local-first memory layer for AI agents with semantic search, memory decay, and association linking, integrable with Claude Code via the MCP protocol.
MIT -
@stitchdb/agentgithub.com/stitchdb/stitchdbupdated this year
Memory layer for AI coding agents — MCP-native, BYO-LLM
npm MIT -
An MCP server that provides an immortal memory layer for AI agents and clients
npm MIT -
blaxx-memorygithub.com/dineshs737/blaxx-memoryupdated this year
A self-updating AI memory layer for Claude Code: knowledge-graph engine + Obsidian vault, with per-session knowledge injection and skill/MCP usage tracking.
pypi MIT -
Persistent cross-session memory for AI agents. Zero-config local mode or Supabase cloud sync. 6-layer architecture, 17 MCP tools.
npm MIT -
cogmemgithub.com/writerslogic/cogmemupdated this year
A self-improving, verifiable memory layer for AI coding agents.
pypi Apache-2.0 -
biblibitgithub.com/shugav/biblibitupdated this year
Persistent three-layer memory for AI agents, exposed as an MCP server.
pypi MIT -
Local-first MCP memory layer for AI agents with SQLite persistence and evidence-gated self-revision.
Apache-2.0 -
Experimental local-first canonical memory layer for AI agents. Go + SQLite + HTTP API + MCP.
MIT ★ 1 -
Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.
pypi Apache-2.0 ★ 107 -
chip-memorygithub.com/chakurov1907-cyber/chip-memoryupdated this year
Local-first, self-organizing memory layer for AI agents. Auto-absorbs knowledge from shell history, git, and Claude Code sessions. MCP-native.
pypi MIT License -
MCP server for external memory layer for AI agents + more . Download from pypi , and get started
pypi Apache-2.0 ★ 45 -
mnemon-memory-mcpgithub.com/nikitacometa/mnemon-memory-mcpupdated this year
Persistent layered memory MCP server for AI agents — SQLite + FTS5 + vector hybrid search (RRF), multilingual, zero-cloud
MIT ★ 3 -
Cognitive memory for AI agents — six layers, epistemic governance, portable via MCP.
Apache-2.0 -
MCP-native persistent memory layer for AI agents across Claude Code, Cursor, VS Code, and OpenClaw.
Apache-2.0 ★ 1 -
shared-memory-skillgithub.com/qingjian0/shared-memory-skillupdated this year
Cross-tool shared long-term memory for AI coding agents (Codex, Claude, Hermes). 5-layer memory hierarchy, hybrid FTS5+vector search, MCP server, local-first.
MIT -
mnemon-mcpgithub.com/nikitacometa/mnemon-mcpupdated this year
Persistent layered memory MCP server for AI agents — SQLite + FTS5 backend
npm MIT -
Shared memory layer for AI coding tools. One local SQLite DB, every tool reads the same verified facts. Local-first, zero cloud.
pypi Apache-2.0 ★ 10 -
remembrallmcpgithub.com/cdnsteve/remembrallmcpupdated this year
Persistent knowledge memory layer for AI agents. Rust core, Postgres + pgvector backend, MCP protocol.
npm MIT -
@raviolelabs/engram-mcpgithub.com/raviolelabs/engram-mcpupdated this year
EngramMCP — local-first semantic memory layer for AI agents
npm Elastic-2.0 -
engram-semanticgithub.com/jblacketter/engramupdated this year
Self-hosted semantic memory layer for AI tools. MCP-native, privacy-first, hybrid search.
pypi MIT -
Anchorgithub.com/OCTOBER-sk/Anchorupdated this year
The memory layer for your AI agents — remote MCP server with semantic memory, agent keys, and a web dashboard
MIT ★ 2 -
hindsight-mempalace-mcpupdated this year
Standalone MCP server for Hindsight MemPalace — hierarchical AI memory with Rooms, Halls, Layers, Closets, and Tunnels
npm MIT -
nemp-mcp-servergithub.com/sukinshetty/nemp-mcp-serverupdated this year
Nemp Memory — Persistent local memory layer for AI agents. MCP server for universal tool integration.
npm MIT -
Self-hosted MCP server for personal AI memory: a searchable episodic archive of AI sessions plus a curated, high-trust semantic facts layer.
MIT -
contextkeeper-mcpgithub.com/ahmedessyad/context-keeperupdated this year
Persistent, structured memory layer for AI coding agents. MCP server.
npm MIT -
sovereign-braingithub.com/blankexcalibur/sovereign-brainupdated this year
Shared memory layer for AI coding agents. One brain, every tool. MCP-native.
npm MIT -
bbb-mcp-servergithub.com/aiaiohhh/bbb-mcp-server-coreupdated this year
Open-source persistent memory + context layer for AI-assisted dev teams via MCP.
npm MIT -
verbative-memoryupdated this year
On-device memory system for AI coding agents — dual-layer engine (distilled facts + lossless event ledger), automatically captured and injected, exposed over MCP. Shared across agents, persistent across sessions; files in your repo.
pypi Other/Proprietary License -
The open memory layer for collective agent awareness — a vendor-neutral MCP service for shared AI-agent memory.
Apache-2.0 ★ 24 -
memoric-aigithub.com/nicosharonfox/memoricupdated this year
Memory layer for AI agents. Persistent memory with intelligent deduplication for Claude Code, Cursor, Codex, and any MCP-compatible client.
npm MIT -
@smyslenny/agent-memorygithub.com/smysle/agent-memoryupdated this year
Agent-native memory layer with lifecycle management for AI agents — SQLite-first, Write Guard, hybrid recall, MCP, CLI, and HTTP API.
npm MIT