M3 Memory
Local-first memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search, GDPR, no cloud.
Servidor MCP · de skynetcmd
Resumen
M3 Memory es un servidor MCP publicado por skynetcmd. Marketplaces que leemos y que lo publican: 2 (Official MCP Registry, Community GitHub marketplaces). Lo vimos por primera vez el 2026-10-11 y desde entonces no hemos registrado cambios. Según nuestra pasada por los marketplaces del 2026-10-14.
Qué pide
- Se ejecuta en tu equipo
- Ajustes: 6
- Hooks declarados: 3
Lo que declara, pide y ejecuta, completo
Instala solo plugins de desarrolladores en los que confíes. Mostramos lo que publican los marketplaces y no probamos plugins.
Paquete
PyPI m3-memory (m3-memory en PyPI)
- Descargas de PyPI por semana: 982 (2026-10-13)
- Descargas de PyPI por mes: 5 393 (2026-10-13)
- Última versión en PyPI: 2026.10.7.1, publicada el 2026-10-08
Sin vulnerabilidades conocidas en OSV para 2026.10.7.1 (comprobado el 2026-10-14)
Los datos de PyPI proceden de pypi.org y las descargas de PyPI de pypistats.org. Cada cifra es del propio registro y nunca se suma a otra. Un registro que no publica una cifra no muestra ninguna: sin cifra no es cero. Los registros de vulnerabilidades proceden de OSV.dev (CC BY 4.0) y solo se refieren a la versión declarada; un listado sin versión declarada no recibe respuesta. No analizamos código.
Funciona con
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Un enlace de un clic abre el cliente, que pide confirmación antes de añadir el servidor.
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por ti ni probamos plugins.
Como servidor MCP local: paquete PyPI
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport stdio m3-memory -- uvx m3-memory[mcp_servers.m3-memory]
command = "uvx"
args = ["m3-memory"]{
"mcpServers": {
"m3-memory": {
"command": "uvx",
"args": [
"m3-memory"
]
}
}
}Como plugin de Claude Code
Generado a partir de lo que declara Community GitHub marketplaces.
/plugin marketplace add skynetcmd/m3-memory
/plugin install m3@skynetcmdDónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 2026.10.7.1 | Descargas por mes (PyPI): 5 393 Descargas por semana (PyPI): 982 Forks (GitHub): 4 Estrellas (GitHub): 28 |
Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
También figura en un marketplace de la comunidad
| Marketplace | Repositorio | Estrellas (GitHub) |
|---|---|---|
| skynetcmd | skynetcmd/m3-memory | 28 |
Qué contiene el paquete
Tal como se publica en Community GitHub marketplaces.
Servidores MCP: 1
memory
Skills: 1
m3-guide
Comandos: 15
agentsexportfind-in-chatforgetgetgraphhealthhelpinstallnotifysavesearch
Mostrar los otros 3
statustaskswrite
Agentes: 2
curate-chatlogcurate-memory
Hooks: 3
PreCompactSessionStartStop
Qué cambió
- Apareció en un nuevo marketplace: Community GitHub marketplaces
- Community GitHub marketplaces: apareció
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta lista.
-
Your AI's memory for what you actually know: recall across your documents, notes, and meetings
-
Memory your agent can trust — every answer carries its source; when it doesn't know, it says so.
-
mcp ai.zine/mcp
Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.
-
Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.
-
core io.github.omega-memory/core
Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.
-
Shared memory for all your AI agents, your whole team and every MCP client — save, search, recall.
-
Markdown memory for coding agents that audits itself: drift reports and session digests.
-
One user-owned memory shared across AI assistants: recall, spaces, and confirmed references.
-
Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).
-
memtomem io.github.memtomem/memtomem
Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.
Plugins similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en Claude Code: claude-plugins-community (5)
-
Local-first persistent session memory for Claude Code and other agents. SQLite + FTS5, no cloud.
-
engram io.github.tstockham96/engram
Intelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.
-
Local memory for Claude Code. Semantic recall across session history with zero API calls.
-
Persistent semantic memory for Claude Code. Stores knowledge in a local ChromaDB vector database and automatically retrieves relevant context on every message using Ollama bge-m3…
-
Mac & Windows: let ChatGPT, Claude & Cursor use your email, calendar, iMessage, Teams, files.
Publicado en Claude Code: claude-plugins-official (5)
-
mdk-mcp-server io.github.SAP/mdk-mcp-server
Model Context Protocol (MCP) server for AI-assisted development of MDK applications.
-
Skills for designing and building MCP servers that work seamlessly with Claude. Guides you through deployment models (remote HTTP, MCPB, local), tool design patterns, auth, and…
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
mcp-server io.github.cap-js/mcp-server
Model Context Protocol (MCP) server for AI-assisted development of CAP applications.
-
Continuous memory for Claude Code. Extracts, summarizes, and compresses conversations into tiered daily logs. Claude remembers what you did yesterday.
Publicado en Claude: knowledge-work-plugins (5)
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
MCP server for terminal commands, file operations, and process management
-
Search companies and contacts, enrich leads, find lookalikes, and get AI-ranked contact recommendations. Pre-built skills chain multiple ZoomInfo tools into complete B2B sales…
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
Sanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual…
Publicado en Codex: openai-curated (openai/plugins) (5)
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Granola MCP connects your meeting history to ChatGPT so your assistant can pull real context from past conversations while you work. Use MCP when you're already working on…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
Publicado en Community GitHub marketplaces (5)
-
Markdown memory for coding agents that audits itself: drift reports and session digests.
-
memtomem io.github.memtomem/memtomem
Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.
-
Token-saving persistent memory for AI agents: recall durable facts instead of re-reading files.
-
Local-first, governable long-term memory for AI coding agents
-
Montycat MCP - Shared Memory for AI Agents
Shared, persistent memory for AI agents, with semantic recall and live updates.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
Complete toolkit for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk. Includes instructions for best practices, a…
-
Complete toolkit for building Model Context Protocol (MCP) servers in TypeScript/Node.js using the official SDK. Includes instructions for best practices, a prompt for generating…
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Comprehensive collection for building declarative agents with Model Context Protocol integration for Microsoft 365 Copilot
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
Publicado en Cursor: cursor/plugins (5)
-
Capture, search, and organize notes and collections.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Let Grok Bot reach MCP servers on your private Tailscale network. Sign in to Tailscale to connect your tailnet; Grok Bot joins it as one tagged device and only reaches the hosts…
-
Search company knowledge and draft verified answers.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
Publicado en Docker MCP Catalog (5)
-
Discover and connect to a curated marketplace of MCP servers for extending AI agent capabilities.
-
The Official Model Context Protocol (MCP) server for Kagi Search & other tools.
-
A universal MCP (Model Context Protocol) server to integrate any API with Claude Desktop using only Docker configurations.
-
A unified MCP proxy that aggregates multiple MCP servers into one interface, enabling seamless tool discovery and management across all your AI interactions. Manage all your MCP…
-
MCP server providing Prometheus metrics access and PromQL query execution for AI assistants
Publicado en Official MCP Registry (5)
-
Your AI's memory for what you actually know: recall across your documents, notes, and meetings
-
Memory your agent can trust — every answer carries its source; when it doesn't know, it says so.
-
mcp ai.zine/mcp
Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.
-
Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.
-
core io.github.omega-memory/core
Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.
Encontrados por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Es tu plugin?
Añádelo a tus proyectos y demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS. Recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Datos de Official MCP Registry. Datos de Community GitHub marketplaces. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.