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.
-
Four-layer memory substrate for long-horizon agents: write-gate admission, signed approvals, hash-chained ledger, revocable and portable.
MIT ★ 4 -
ai-memory-layergithub.com/NishantJLU/ai-memory-layerupdated this year
—
MIT ★ 6 -
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 -
High-speed shared semantic & hybrid memory layer for AI agents — MCP server, CLI, and Python library
pypi MIT -
MemOS - Universal local-first persistent memory layer for AI agents and LLMs
MIT ★ 10 -
Associative memory for LLM agents — a key-graph memory layer (MCP server) that recalls by association, not just vector similarity. A graph-based alternative to vector-store agent memory.
npm MIT -
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 -
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 -
Zero-knowledge persistent memory layer for LLMs — AES-256-GCM encrypted, semantic search via Qdrant, MCP server for Claude Desktop / Sovereign European MCP memory layer — self-hostable, AGPL v3
NOASSERTION ★ 1 -
anamnesis-memorygithub.com/oscardvs/anamnesisupdated this year
Cross-machine, file-first memory layer for Claude Code (MCP server)
pypi Apache-2.0 -
Alice: the continuity layer for AI agents. Local-first memory with provenance, open loops, resumption, and review-governed writes.
pypi MIT -
the trust layer for agent memory
pypi MIT -
Best AI Memory Layer for Claude Code and MCP Agents in 2026
-
Living memory layer across your AI coding agents and sessions..
NOASSERTION ★ 25 -
origin-mcpgithub.com/7xuanlu/originupdated this year
Local-first memory layer for AI agents - MCP server
npm Apache-2.0 -
Next-gen AI memory layer with hierarchical memory, importance scoring, and temporal retrieval
pypi Apache-2.0 -
Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.
Apache-2.0 ★ 107 -
Wake Intelligence: 5-Layer Temporal Intelligence for AI Agents A production-ready Model Context Protocol (MCP) server implementing a temporal intelligence "brain" with five layers: Past (causality tracking), Present (memory management), Future (predictive pre-fetching), Adaptive (meta-learning — per-project weight tuning), and Personality (tempora
MIT ★ 4 -
The memory layer for AI · Adaptive Memory And Fact Ordering System · Remote MCP server
NOASSERTION -
Universal, local-first, persistent memory layer for AI agents, LLM apps, and chatbots.
npm MIT -
Zero-knowledge persistent memory layer for Claude — MCP server
pypi AGPL-3.0-or-later -
A memory layer for AI Agents
Apache-2.0 ★ 84 -
The intentional memory layer for your AI agents.
MIT ★ 25 -
The associative memory layer for LLM agents — recall by association, not just similarity.
npm MIT ★ 3 -
A small mcp service to record things in sqlite. A simple GPT memory layer. ;)
NOASSERTION ★ 1 -
cogmemgithub.com/writerslogic/cogmemupdated this year
A self-improving, verifiable memory layer for AI coding agents.
pypi Apache-2.0 -
An MCP server that provides an immortal memory layer for AI agents and clients
npm MIT -
cursor-memory-servergithub.com/TbusOS/cursor-memory-serverupdated this year
A persistent memory system for Cursor IDE — Hooks + MCP hybrid, auto-recall at session start, dual-layer global/project memory, bilingual full-text search.
★ 1 -
MCP server for external memory layer for AI agents + more . Download from pypi , and get started
Apache-2.0 ★ 45 -
opencode-memorygithub.com/xpajonx/opencode-memoryupdated this year
Distributed local-first hybrid-RAG memory layer and Harness bootstrapper for opencode agents, with dynamic pre-injection and styled console TUI.
★ 1 -
MCP-native persistent memory layer for AI agents across Claude Code, Cursor, VS Code, and OpenClaw.
Apache-2.0 ★ 1 -
cursor-mem0github.com/xwqiang/cursor-mem0updated this year
AI agent memory layer (mem0-compatible) powered by Cursor SDK
pypi Apache-2.0 -
@iflow-mcp/moonx010-hive-memorygithub.com/moonx010/hive-memoryupdated this year
Cross-project memory layer for AI coding agents — MCP server that maintains context, decisions, and knowledge across workspaces
npm MIT -
The memory layer that can be corrected: provenance-first agent memory with a real corrections API and a one-command junk audit.
MIT ★ 1 -
One memory, every terminal — a shared memory layer for any MCP client.
npm MIT ★ 15 -
remembrallmcpgithub.com/cdnsteve/remembrallmcpupdated this year
Persistent knowledge memory layer for AI agents. Rust core, Postgres + pgvector backend, MCP protocol.
npm MIT -
Your portable AI memory layer. Classify, store, and recall what matters across models, tools, and devices.
pypi MIT -
The deterministic trust layer for autonomous AI coding agents. Compiler-grounded verification of what an agent actually did vs. what it claimed, blast radius mapping, and persistent contract memory.
npm MIT -
memforgegithub.com/memforgeai/memforgeupdated this year
The open-source memory layer for AI agents — MCP server backed by PostgreSQL + pgvector + Apache AGE
npm BUSL-1.1 -
The open memory layer for collective agent awareness — a vendor-neutral MCP service for shared AI-agent memory.
Apache-2.0 ★ 24 -
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 -
jamjet-engramgithub.com/jamjet-labs/engramupdated this year
Engram — durable memory layer for AI agents. Temporal knowledge graph, semantic search, and MCP-native tools.
pypi Apache-2.0 -
Local-first persistent memory layer for AI agents. SQLite-backed, MCP-compatible, cross-agent. Privacy: secret-blocking writes, file-only storage.
MIT ★ 2 -
ai-longterm-wiki-memory-ClaudeCodegithub.com/giovannifrontera/ai-longterm-wiki-memory-ClaudeCodeupdated this year
Persistent semantic memory for Claude Code. Three-layer wiki + LanceDB vectors, hooks, self-healing lint, knowledge graph. Native MCP integration.
AGPL-3.0 ★ 1 -
openbrain-mcpgithub.com/crack-kitty/openbrain-mcpupdated this year
Self-hosted AI memory layer (MCP server). Typed memory tables, hybrid search, session handoff. For Onramp + any MCP client.
MIT ★ 2 -
Evidence-based agent memory layer for Codex, Claude Code, and development teams
pypi Apache Software License -
Unified Workspace with Multi Agent memory - Slipstream - 5-layer associative graph memory (MAGMA) with autonomous REM cycle, CLI, GUI, DXT-MCP Cloak Tools.
NOASSERTION ★ 6 -
praxosgithub.com/JustVugg/praxosupdated this year
MCP-powered memory, policy, and experience layer for safer AI agents.
MIT ★ 12 -
Local-first memory layer and protocol for AI coding agents. Markdown source of truth, SQLite FTS5 index, zero cloud.
npm Apache-2.0 -
Persistent intelligence layer for LLM-powered agents. Memory that compounds across sessions.
NOASSERTION -
Multi-layer agent memory MCP server — working, episodic, semantic, procedural & affective — for Claude Code and any MCP client.
MIT ★ 3 -
mementogithub.com/veerps57/mementoupdated this year
A local-first, LLM-agnostic memory layer for AI assistants
npm Apache-2.0 ★ 24 -
soroban-memorygithub.com/duraznito16/stellar-memoryupdated this year
Persistent memory layer for Stellar/Soroban projects. Scans your repo, links code to on-chain reality, and serves the result to you and to your AI agents over MCP.
npm Apache-2.0 -
Local-first, auditable memory layer for AI apps and coding agents — Codex, Claude Code, MCP, HTTP, TypeScript, and Python.
MIT ★ 21 -
Shared, structured memory for AI coding agents — MCP server + CLI. One memory layer for Claude Code, Codex, Cursor & every MCP client.
MIT ★ 12 -
Self-hosted MCP server that gives LLM agents (Claude Code, Claude Desktop) persistent cross-session memory across four CoALA-style layers (Postgres + pgvector + TimescaleDB, Redis).
Apache-2.0 -
memforgegithub.com/MemForgeAI/memforgeupdated this year
The open-source memory layer for AI agents. MCP-native, single Postgres, #1 on LOCOMO benchmark.
NOASSERTION ★ 2 -
mori MCP server — a governed memory layer for AI coding agents.
AGPL-3.0 ★ 32