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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
An OpenClaw (2026.4/2026.6+) and Hermes Agent plugin that turns AI conversations into a permanent Zettelkasten knowledge base — atomic notes, bi-directional links, knowledge distillation, and MCP tool exposure.
MIT ★ 17 -
@neverprepared/mcp-obsidian-second-braingithub.com/neverprepared/mcp-obsidian-second-brainupdated this year
MCP server for Obsidian-based second brain memory using PARA methodology
npm MIT -
Build a second brain every AI can share: your content in Oracle AI Database 26ai — semantic search with in-database embeddings, a self-compiling wiki, four kinds of agent memory, and an MCP server that plugs it into Claude, ChatGPT, and any MCP client. Runs on the free local container or Always Free cloud.
MIT ★ 13 -
elingupdated this year
Unified second brain for AI agents — 5-tier memory, HRR reasoning, 14 MCP tools, Zettelkasten linking, memory evolution
pypi MIT -
Windows app that combines a local second brain for AI agents (MCP), file search and memory with safe PC cleanup and encrypted GitHub backup.
-
Native macOS second-brain for Claude: isolated per-profile memory over MCP, with a shared Keychain vault for API keys. One-click Desktop Extension.
MIT -
A self-hosted second brain: capture everything you think on, condense it into memory, and serve it back through MCP, a daily brief, foresight, and a galaxy map.
MIT ★ 1 -
oh-my-braingithub.com/agentpolis/oh-my-brainupdated this year
The second brain that follows you across every agent. Importance-aware memory for Claude Code, Codex, and MCP-compatible tools. (Formerly squeeze-claw.)
npm Apache-2.0 -
knit-mcpgithub.com/pdgit12/knitupdated this year
Knit — second brain for any MCP-speaking AI coding agent (Claude Code, Cursor, Codex CLI, Cline, Continue, GitHub Copilot). Per-project memory, tier-routed workflow protocol, parallel team worktrees.
npm MIT -
A self-hosted, MCP-accessible second brain: episodic + semantic memory in Postgres, one persistent memory layer any AI tool can plug into.
MIT -
@tomosborne/second-brain-mcpgithub.com/degendoes/second-brain-mcpupdated this year
MCP server for Tom Osborne's Second Brain — talk to Tom's voice-cloned AI agent built on 100+ interview answers + 21,000 marketing articles + 15 years of operator memory, from inside Claude Desktop, Claude Code, Cursor, or any MCP-compatible client.
npm MIT -
Persistent second memory for your personal AI system — local-first MCP server backed by SurrealDB
AGPL-3.0 -
Miniongithub.com/Good-and-Company/Minionupdated this year
Capture-first macOS second brain: ambient window context, local vault, Activity stream + proactive guide (42), life graph, and MCP memory for Claude. Local-first; private by default.
-
🧠 CLI-first knowledge base & second brain for LLMs (Obsidian-style Markdown, wikilinks, core/brain memory, and MCP server)
MIT ★ 1 -
aion-memory-nexusgithub.com/234194027-cpu/aion-memory-nexusupdated this year
Predictive AI Agent Memory & Second Brain — trusted long-term memory, vector search, temporal knowledge graph, decision intelligence, and MCP.
MIT -
Official Model Context Protocol (MCP) server for Purmemo - Your AI-powered second brain with 94% memory retrieval accuracy
npm MIT -
A second brain for AI coding agents — long-term, structured, queryable project memory over MCP
npm MIT -
Give Claude a memory that survives the conversation - an MCP server that turns TriliumNext into a persistent, graph-structured second brain. MIT.
npm MIT -
Second brain for your AI: a self-hosted memory vault your AI agents read and write over MCP. Install with npm, Docker or one command.
npm AGPL-3.0 ★ 11 -
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift
npm Apache-2.0 ★ 810 -
Universal AI memory layer — your second brain across every AI tool. Local-first, open source, MCP-compatible.
pypi Apache-2.0 ★ 3 -
A second brain for Claude Code, Codex & Gemini — persistent git-native project memory with searchable citations, an MCP server for Claude Desktop, and invisible hook-based context. No database.
npm AGPL-3.0-only -
Protocol-SIFT-Async-Bridgegithub.com/mwarsss/Protocol-SIFT-Async-Bridgeupdated this year
Type-safe async MCP server for LLM-assisted memory forensics via Volatility 3: closes the 60-second attacker breakout window without LLM timeouts or evidence spoliation.
MIT ★ 1 -
Personal-GraphRAGgithub.com/djuvinall/Personal-GraphRAGupdated this year
Self-hosted GraphRAG for personal memory — Claude writes the entities and the edges directly over MCP, no second extraction model. Journal-first durability, optional local stack.
Apache-2.0 -
swarmvaultgithub.com/swarmclawai/swarmvaultupdated this year
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.
npm MIT ★ 736 -
engramgithub.com/rwnalds/engramupdated this year
Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, no vector DB.
oci MIT ★ 22 -
Shared long-term memory for your AI tools: Git-backed Markdown wikis (LLM wiki, second brain) that Claude, Codex, Gemini CLI, Cursor and agents like OpenClaw and Hermes read and write over MCP, with citations and human review. Run locally or self-host lobe-server.
MIT -
Open-source, LLM-agnostic second brain. Connect any LLM (local llama.cpp, Claude, Codex, GPT, Gemini, Grok, Ollama) via MCP — memory lives as Markdown in YOUR GitHub repo, independent of any model. Desktop, VPS or bot VM. MIT.
MIT ★ 2 -
Local Markdown second brain with MCP memory, Neural Atlas CPU companion, Windows auto-start, crash recovery and daily semantic Graphify refresh.
MIT -
Collaborative wiki + governed second brain for people and AI agents. Real-time co-editing, Confluence import, hybrid search in Arabic and English, and a shared memory that Claude Code, Codex and VS Code use over MCP. Self-hosted: .NET 10, Blazor, Postgres + pgvector.
NOASSERTION -
🏆 1st place, UIUC Product Hackathon 2026, Caterpillar challenge 'Cat Track: Memory for Physical AI'. A 3D jobsite simulator with a memory: replay any second, talk to the site, ask why production was down.
NOASSERTION -
An MCP server that lets Claude Code ask Qwen for a second opinion while it works, with memory for each project.
MIT -
elder-care-facility-intelligence-mcpgithub.com/apifyforge/elder-care-facility-intelligence-mcpupdated this year
Elder care facility intelligence delivered as a Model Context Protocol server — assess any nursing home, assisted living, or memory care facility in seconds from your AI client.
MIT -
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 -
Selvedgeno update data
**Persistent decision memory for AI coding agents.** Selvedge records why code changed, which approaches were rejected, and when decisions deserve another look, so future sessions can retrieve that context before editing. Query a function, database column, API route or dependency instead of reconstructing its history from an old conversation. Claude Code, Codex, Cursor, Copilot, Gemini CLI and Windsurf can connect through MCP. The CLI works independently. Decisions live in a local SQLite store, with no required hosted account and no LLM in the core storage or retrieval path. A saved explanation is testimony supplied by a person or agent. Selvedge does not extract hidden model reasoning, verify that an explanation is true, or guarantee that an agent will consult it. [Compatibility and capabilities](https://selvedge.sh/reference/compatibility/) · [56-second technical demo](https://youtu.be/wXoA9htThAM)
smithery -
second-braingithub.com/guoan1tang/second-brainupdated this year
—
MIT ★ 1 -
Persistent memory for Claude Code — the full plugin: hooks, skill, MCP server, workflows. A Markdown vault you own, no server and no account. Hooks-only version: continuum.
Apache-2.0 ★ 2 -
Universal persistent memory layer and context manager for AI agents, Claude, Cursor, and LLMs via Model Context Protocol (MCP)
npm Apache-2.0 -
second-brain-mcpgithub.com/noesskeetit/second-brain-mcpupdated this year
MCP server that turns an Obsidian vault into semantic memory for any coding agent
pypi MIT -
Own your AI memory, don't rent it. A native Claude Code skill AND a standalone, zero-dependency MCP server over one local SQLite file. git clone and go — full-text knowledge graph, plain-markdown, you own the data.
MIT ★ 7 -
second-brain-mcpgithub.com/giovani-junior-dev/second-brain-mcpupdated this year
—
MIT -
本地优先的 AI 第二大脑:Markdown/Obsidian 知识库、MCP 检索、经历记忆与知识治理。
MIT -
second-brain-mcpgithub.com/anyesh/second-brainupdated this year
MCP (Model Context Protocol) server for second-brain — thin HTTP client to the daemon
cargo MIT -
ai-second-braingithub.com/abelgonzalezr/ai-second-brainupdated this year
Self-hosted shared memory for AI agents (Claude Code, Cursor, Codex, Gemini) — Neo4j + Graphiti MCP + local Ollama. Temporal knowledge graph, multi-agent, one-command setup.
MIT -
Open-source context engineering scanner for Claude Code. Scores 45 check layers across CLAUDE.md, skills, hooks, memory, and planning artifacts. Free local tools + paid upgrades via MemoryOS.
npm MIT -
One memory layer, every AI tool. Store anything once — recall it in Claude, ChatGPT, Cursor, or any MCP client. Self-hosted on Cloudflare's free tier.
MIT ★ 866 -
Zero-dependency, offline-first Graph-RAG memory system for AI agents — hybrid semantic+keyword+graph search, multi-agent task queue, MCP server, Obsidian-native vault.
npm MIT ★ 1 -
@matthesketh/second-brain-mcpgithub.com/wrxck/matts-second-brainupdated this year
MCP server for matts-second-brain — exposes brain_recall / brain_remember / brain_scan_transcripts / brain_setup_check / brain_install on top of a Trilium Notes ETAPI backend.
npm MIT -
A self-maintaining personal knowledge database — powered by MCP, DuckDB, and biological memory models.
pypi MIT ★ 7 -
@alie.me/mcpgithub.com/parimoody/alie_newupdated this year
ALIE MCP server — read + write your second brain from any AI tool. v0.4 adds folders: alie_list_boards + alie_assign_to_board.
npm Apache-2.0 -
Second brain for your LLM.
pypi ★ 1 -
sherpa_braingithub.com/the-data-sherpa/sherpa_brainupdated this year
A durable, local-first second brain for AI agents: evidence, forgetting, portability.
MIT -
Scaffold and maintain an AI-readable second-brain vault for you and your AI agents.
npm MIT -
Motor de memoria estruturada, governanca epistemologica e busca hibrida local integrado ao Obsidian via Model Context Protocol (MCP).
NOASSERTION ★ 1 -
Give Claude Code a memory that survives between sessions, stored as plain Markdown in your Obsidian vault.
MIT -
Source-grounded MCP memory runtime and Obsidian-compatible vault template for LLM agents.
MIT ★ 76 -
A searchable second brain for AI agents: a file-based knowledge base with ranked keyword and semantic (hybrid) search, as a CLI and MCP server.
npm AGPL-3.0-only -
Local, private long-term memory for Claude Code: markdown notes, hybrid FTS5 + vector search over MCP, decision records, lessons and a measured retrieval eval.
pypi MIT ★ 1 -
Self-hosted memory for AI assistants: Claude Code, Codex, and a Telegram agent save to one Obsidian vault over MCP, with human approval and hybrid search.
MIT -
Kioku (記憶) — second brain for your repos. Wires a local repo to your Kioku instance: MCP server, SessionStart hook, CLAUDE.md snippet.
npm MIT