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.
-
Source-backed memory for AI agents: Git citations, local retrieval, CLI, and MCP.
MIT -
Heartwood Memory — governed memory for AI agents. Provenance-first recall, policy-gated retrieval, tenant isolation.
pypi NOASSERTION -
cursor-memory-projectgithub.com/lexmourao/cursor-memory-projectupdated this year
Persistent memory, retrieval, MCP server, logging, and QA framework for Cursor-based AI-assisted development workflows.
MIT -
Personal, local-first conversation memory and evidence retrieval for AI coding assistants, with provenance, evaluation, and recovery.
MIT -
Long-term memory for AI agents: episodic, semantic, and procedural memory in SQLite with hybrid retrieval, fact versioning, consolidation, and an MCP server.
MIT -
MCP server for LanceDB-backed long-term memory with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, and memory lifecycle management
npm MIT -
Local-first neural memory for AI agents: private Markdown/Obsidian vaults, auditable retrieval, and MCP access.
MIT ★ 2 -
Memory system for AI agents with hybrid retrieval, MCP tooling, and LongMemEval-leading performance.
NOASSERTION ★ 3 -
MCP-Memory-LanceDB-Progithub.com/bcornish1797/MCP-Memory-LanceDB-Proupdated this year
Full memory-lancedb-pro memory enhancement system for Claude Code via MCP protocol — hybrid retrieval, smart extraction, auto-capture, intelligent forgetting, multi-scope isolation. Feature parity with OpenClaw memory-lancedb-pro plugin.
npm MIT -
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 -
@thenullnode/nulldown-mcpactive
Stdio MCP access to Nulldown's deterministic Markdown state, retrieval, and memory
npm -
Long-term memory for LLM agents: hybrid BM25 + vector retrieval that learns from use, a measured retrieval benchmark, and a from-scratch MCP server. Standard library only.
MIT -
tagmemgithub.com/codysnider/tagmemupdated this year
Structured local memory storage and retrieval for LLM agents
go MIT ★ 15 -
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 -
One MCP server for your agent's memory: consolidate a markdown knowledge base's tools behind one surface, and rerank retrieval.
MIT -
Deterministic markdown memory and knowledge graph for AI agents: BM25+wikilink retrieval, an MCP server, and a Claude Code hook, no vector database required.
pypi MIT -
mnemogithub.com/Shivamjohri247/mnemoupdated this year
Biologically-inspired local-first AI agent memory — Ebbinghaus forgetting, 4-channel retrieval with RRF, lifecycle-aware embedding compression, MCP tools
MIT -
Middleware memory layer for LLM agents: a shared knowledge store with hybrid retrieval, tiered memory, a knowledge graph, and governance, exposed over MCP, CLI, and API.
Apache-2.0 ★ 2 -
Context engineering toolkit for AI agents. 24 MCP tools across retrieval, memory, context, and team telemetry. .NET 10. No cloud deps.
nuget MIT ★ 2 -
arbolgithub.com/rishabhshah1309/arbolupdated this year
Agent-readable memory for markdown notes: enforced schema, validator, BM25 + graph retrieval, MCP server, and an eval that tells you the truth
MIT -
fusionpact-vectordbgithub.com/FusionpactTech/fusionpact-vectordbupdated this year
⚡ The Agent-Native Retrieval Engine — Hybrid Vector + Reasoning + Memory for AI Agents. HNSW indexing, tree-based reasoning retrieval, multi-agent orchestration, MCP server, and built-in RAG.
npm Apache-2.0 -
Local-first AI memory runtime with hybrid retrieval, temporal memory, privacy controls, MCP support, and explainable context generation.
-
Project memory for coding agents: code + decision retrieval over a symbol graph, MCP server, graph views, and a pre-registered evaluation vs AMG and graphify
Apache-2.0 ★ 1 -
claude-repo-memgithub.com/amritmalla/claude-repo-memupdated this year
Durable, hierarchical, repo-scoped memory for Claude Code. Local-first MCP server with hybrid lexical + vector retrieval over your codebase, docs, and accumulated decisions.
pypi MIT -
retrieval-mcpactive
Installable MCP server for the Retrieval API: academic-paper search + journal memory + ACE playbook + semantic code search
pypi MIT -
Long-term memory for agentic tasks. It tells you when it doesn't know. An MCP server for Claude Desktop and Claude Code: hybrid retrieval over your own markdown memories, with an explicit absence verdict instead of a least-bad match.
npm MIT -
Local vector retrieval MCP server for coding agents: semantic code search, session-transcript memory, and a live token-savings counter. 100% on-device.
npm MIT -
Portable hybrid (BM25 + dense + RRF) retrieval engine and a label-free evaluation harness — extracted from a personal AI-assistant memory index and decoupled to run on any source tree.
pypi MIT ★ 4 -
A simple MCP server that stores and retrieves memories from multiple LLMs.
npm MIT ★ 23 -
@kengurukleo/mcp-memory-servergithub.com/kengurukleo/mcp-knowledge-baseupdated this year
MCP server for personal memory storage and retrieval with vector search
npm MIT -
@aiagentkarl/agent-memory-mcp-serverupdated this year
Persistent memory for AI agents — store, retrieve, search knowledge across sessions
npm MIT -
Local-first, offline-capable Agent memory & knowledge service. REST + MCP dual-protocol, hybrid retrieval (vector + BM25/RRF), document/webpage RAG. No LLM required for storage & retrieval
pypi Apache-2.0 ★ 5 -
budget-aware-mcpgithub.com/doorman11991/budget-aware-mcpupdated this year
Model-agnostic code memory MCP server. Budget-aware graph retrieval for AI agents — sub-millisecond queries, token budgeting, no embeddings, no API keys. Built on CodeGraphContext for 155-language tree-sitter indexing.
npm MIT -
PostgreSQL-backed MCP memory server with thermal decay + knowledge graph + hybrid retrieval
MIT -
JavaScript MCP Server for persistent agent memory — store, retrieve, search knowledge
MIT -
agent-memory-mcp-servergithub.com/AiAgentKarl/agent-memory-mcp-serverupdated this year
Persistent memory for AI agents — store, retrieve and search knowledge across sessions
pypi MIT -
flux-memorygithub.com/harsh5i/flux-memoryupdated this year
Self-organizing retrieval fabric for AI memory — deployable MCP server, REST API, and Python SDK
MIT ★ 4 -
A MCP server for personal memory storage and retrieval across AI models
npm MIT -
@iflow-mcp/memory-mcp-2github.com/iflow-mcp/memory-mcp-2updated this year
MCP server for logging and retrieving memories with context window caching and shared memories
npm MIT -
Memory for your AI agents. Remote MCP (Model Context Protocol) server for storing, retrieving, and semantically searching "memories" on behalf of AI agents
★ 1 -
Python SDK + MCP server for Telys — embedded, on-device memory & retrieval for AI assistants. 19-tool MCP surface (io.github.thyn-ai/telys on the Official MCP Registry); the engine is a separate closed, signed on-device runtime — the SDK and MCP surface are Apache-2.0.
pypi Apache-2.0 -
memory-safegithub.com/eljoesb/memory-safeupdated this year
MCP memory server for Claude Code — knowledge graph in SQLite, local ONNX embeddings, token-budgeted retrieval
npm MIT -
Local-first MCP memory server with SQLite storage, scoped retrieval, governance, and audit trail for agents.
MIT -
Local-first memory and policy service for AI agents: durable events, retrieval, portable handoffs, async jobs and operational metrics. Repository contact: Robin Winters.
MIT ★ 1 -
codebase-memorygithub.com/H-Gelender/codebase-memoryupdated this year
MCP memory server for codebase analysis: embedding-based retrieval + clean-code analysis (local-first, scalable to low-end machines).
-
RWIF-backed federated semantic memory over MCP: compact disk-native semantic stores with governed writes, Docker-ready deployment, and benchmarked retrieval without a heavyweight vector database tier.
MIT ★ 1 -
Project memory for coding assistants: decisions, warnings and history across sessions, retrieved with source citations
Apache-2.0 ★ 1 -
memora-mcpupdated this year
MCP server for saving and retrieving prompts, memories and plans
npm MIT -
long-term-memorygithub.com/ihwooMil/long-term-memoryupdated this year
Intelligent memory MCP server for AI assistants — auto-save, semantic search, RL-powered retrieval, and knowledge graphs
pypi MIT -
codex-memory-weavergithub.com/Lausi-h2ai/codex-memory-weaverupdated this year
MCP server for persistent, locally hosted, project, agent, and user memory with scoped recall, graph retrieval, and HippocampAI integration.
-
memoryvault-kitgithub.com/ayushmall/memoryvault-kitupdated this year
A personal memory layer for your AI tools. Intelligent authoring (gap detection, self-enriching graph, session-synthesis loop) + measurably good retrieval (94.9% blind Cov@10, sub-ms latency). Domain-agnostic framework — works for any context you want to track. MCP-native, Claude-Code-first, works with Cursor/Continue/Cline/OpenAI/Gemini.
MIT ★ 2 -
Offline-first MCP server for web search, content fetching, semantic retrieval and persistent memory.
npm ISC ★ 1 -
@crosmos/crosmos-mcpgithub.com/crosmos-org/crosmos-mcpupdated this year
MCP server for Crosmos Memory Engine with hybrid retrieval
npm MIT -
contextkeepergithub.com/nadavlevine09/contextkeeperupdated this year
Local memory for Claude: stores facts and conversation excerpts on your machine and retrieves relevant context via an MCP server.
NOASSERTION ★ 1 -
@elephance/mcpupdated this year
MCP server for elephance local vector memory and schema retrieval
npm MIT -
aionforge-memorygithub.com/jscott3201/aionforge-memoryupdated this year
A Rust-native agentic memory substrate built on the selene-db graph engine: a bi-temporal knowledge graph, hybrid retrieval, and an optional MCP server.
Apache-2.0 ★ 12 -
agent-rulebookactive
Agent-native MCP memory for retrieving verified problems, solutions, outcomes, and source evidence.
npm UNLICENSED -
mcp-memory-sqlitegithub.com/pavex/mcp-memory-sqliteupdated this year
Lightweight MCP server for persistent, searchable Claude memory. Features FTS5, importance-based retrieval, and autonomous "dreaming" for memory defragmentation. No cloud, no vendor lock-in.
★ 1 -
memory-bank-loader-mcpgithub.com/abeyuya/memory-bank-loader-mcpupdated this year
This is an MCP server for retrieving all files in the memory-bank directory at once. Its purpose is to reduce AI tool invocation frequency when loading memory-bank, saving both time and money.
npm MIT ★ 4 -
High-performance codebase-memory engine (AST -> Graph -> Retrieval) for coding agents
pypi Apache-2.0