SQLite Local AI Memory
100% In-Process Bare-Metal Hybrid Memory Engine & MCP Server for LLMs (SQLite + Int8 Vectors).
Servidor MCP · de cheveguerra
Resumen
SQLite Local AI Memory es un servidor MCP publicado por cheveguerra. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). El último cambio que registramos fue el 2026-10-19. Según nuestra pasada por los marketplaces del 2026-10-21.
Qué pide
- Se ejecuta en tu equipo
- Secretos: 1
- Ajustes: 2
Requiere: GEMINI_API_KEY (secreta)
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.
Funciona con
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
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 npm
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --env "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" --transport stdio sqlite-local-ai-memory -- npx -y sqlite-local-ai-memory[mcp_servers.sqlite-local-ai-memory]
command = "npx"
args = ["-y", "sqlite-local-ai-memory"]
[mcp_servers.sqlite-local-ai-memory.env]
GEMINI_API_KEY = "<YOUR_GEMINI_API_KEY>"{
"mcpServers": {
"sqlite-local-ai-memory": {
"command": "npx",
"args": [
"-y",
"sqlite-local-ai-memory"
],
"env": {
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
}
}
}
}Sustituya los valores entre corchetes angulares por los suyos. Mostramos los nombres de los ajustes, nunca valores.
Ajustes opcionales que también indica: SQLITE_MEM_PATH.
Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 1.5.0 | Forks (GitHub): 0 Estrellas (GitHub): 1 |
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.
Qué cambió
- Official MCP Registry: publicó la versión 1.5.0 (antes 1.4.7)
- Official MCP Registry: publicó la versión 1.4.7 (antes 1.4.6)
- Official MCP Registry: publicó la versión 1.4.6 (antes 1.4.5)
- Official MCP Registry: cambiaron las variables de entorno (ahora 2): añadido: GEMINI_API_KEY, SQLITE_MEM_PATH; retirado: SQLITE_AI_MEMORY_DB
- Pasó a ser un producto que seguimos
- Official MCP Registry: 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.
-
Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.
-
A local memory engine. You own the SQLite file. Not Mem0's hosted OpenMemory MCP.
-
nlqdb — analytical memory for AI agents
Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command.
-
memorymesh io.github.sparkvibe-io/memorymesh
Persistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable.
-
Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.
-
Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.
-
Memory database for LLM agents — persistent semantic + keyword memory, project namespacing, served o
-
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
-
Long-term memory and context fitting for agents, with no LLM in the loop. Local SQLite.
-
hmem — Humanlike Memory for AI Agents
Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.
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.
-
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…
-
agent-knowledge io.github.keshrath/agent-knowledge
Cross-session memory for AI agents - knowledge graph, scoring, semantic search
-
claude-code-plugin-for-goodmem-a-memory-infra-for-agents
With this plugin, you can operate Goodmem's memory infra in plain English, to create, manage, and orchestrate embedders, rerankers, and LLMs, to ingest and create memories from…
-
Save 60-90% on LLM token costs with intelligent memory compression. agent-memory automatically compresses tool output into structured observations, shares context across agents…
Publicado en Claude Code: claude-plugins-official (5)
-
DuckDB-powered skills for Claude Code: read any data file, attach and query DuckDB databases, search DuckDB/DuckLake docs, search past session logs, and install/update DuckDB…
-
Pinecone vector database integration. Streamline your Pinecone development with powerful tools for managing vector indexes, querying data, and rapid prototyping. Use slash…
-
Agent skills for Qdrant vector search covering scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across…
-
Create, connect, and interact with an AlloyDB for PostgreSQL database and data.
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
Publicado en Claude: knowledge-work-plugins (5)
-
Agent skills for Qdrant vector search covering scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across…
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
-
Connect Claude to your ClickHouse Cloud databases. Browse organizations, services, databases, and table schemas. Run read-only SQL queries against your data and get instant…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Connect Claude Code directly to your CockroachDB clusters for hands-on database work — explore schemas, write optimized SQL, debug queries, and manage distributed database…
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…
-
Manage Supabase projects directly through ChatGPT. Execute SQL queries on PostgreSQL databases, design and modify table schemas, deploy serverless edge functions, and configure…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Bring operational data and context into the flow of your ChatGPT conversations. You can ask questions, create and update records, and analyze your data—all through conversation…
Publicado en Community GitHub marketplaces (5)
-
Graph-vector memory for AI assistants using FalkorDB and Qdrant
-
memtomem io.github.memtomem/memtomem
Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.
-
Montycat MCP - Shared Memory for AI Agents
Shared, persistent memory for AI agents, with semantic recall and live updates.
-
yantrikdb-mcp io.github.yantrikos/yantrikdb-mcp
Cognitive memory for AI agents — semantic recall, knowledge graph, and contradiction detection
-
Connect Claude Code to Membase persistent memory over MCP — memory search and store, wiki, and session handoffs.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Explore and query TimeBase streams, schemas, QQL, symbols, and server status via MCP.
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
Comprehensive collection for building declarative agents with Model Context Protocol integration for Microsoft 365 Copilot
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Build and manage Microsoft Dataverse solutions using natural language. Includes table/column creation, solution lifecycle, data operations, and MCP server configuration.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
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)
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Explore datasets and tables and run SQL queries.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Capture, search, and organize notes and collections.
Publicado en Docker MCP Catalog (5)
-
A Model Context Protocol (MCP) server implementation that provides database capabilities for Chroma.
-
Database interaction and business intelligence capabilities.
-
mcp-neo4j-memory io.github.neo4j-contrib/mcp-neo4j-memory
MCP Neo4j Knowledge Graph Memory Server
-
MCP server for SQLite, PostgreSQL, and MySQL with natural language to SQL and direct SQL tooling.
-
The Official Model Context Protocol (MCP) server for Kagi Search & other tools.
Publicado en Official MCP Registry (5)
-
Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.
-
A local memory engine. You own the SQLite file. Not Mem0's hosted OpenMemory MCP.
-
nlqdb — analytical memory for AI agents
Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command.
-
memorymesh io.github.sparkvibe-io/memorymesh
Persistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable.
-
Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.
Publicado en npm registry (MCP servers) (5)
-
gitmem io.github.gitmem-dev/gitmem
Persistent institutional memory for AI coding agents. Memory that compounds.
-
Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.
-
Run SQL queries and inspect database schemas through safe, visible MCP tools.
-
easytable-mcp io.github.chrischall/easytable-mcp
easyTable restaurant reservations for Claude — availability, and create/modify/cancel bookings
-
google-surf-mcp io.github.HarimxChoi/google-surf-mcp
Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.
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.
¿Quieres esta marca para tu plugin en nuestro catálogo?
Demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS, y podrás mostrar esta marca en la ficha, con banners en vivo para tu web y tu README. Cómo funciona la verificación
Además 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. 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.