codememory
🧠 CodeMemory
La capa de inteligencia persistente para bases de código
Herramienta CLI local-first y obsesionada con la privacidad, y servidor Model Context Protocol (MCP) para agentes de IA.
🌐 Sitio web y documentación oficiales: https://codemem.vercel.app/
⚡ Aspectos destacados
🔒 100 % local y privado: cero telemetría, cero llamadas de red externas. Toda la inteligencia se almacena localmente en SQLite en modo WAL.
🌐 Explorador interactivo de arquitectura web: diagrama de flujo visual local y panel de memoria con desplazamiento temporal y actualizaciones en vivo en tiempo real.
⚡ Eficiencia de tokens: minimiza el consumo de tokens de los prompts de IA al proporcionar fragmentos de contexto específicos y grafos de llamadas en lugar de volcados de archivos sin procesar.
🔍 Análisis AST multilingüe: extrae funciones, clases, interfaces, structs e imports en TypeScript/JavaScript, Python, Rust, Go, SQL y más.
👀 Observador en vivo en tiempo real: detecta cambios de código al instante con un debounce de 100 ms e integración con
.gitignore.🤖 Servidor MCP nativo: listo para conectarse con Antigravity, Claude Desktop, Cursor, Copilot y agentes de IA personalizados.
📊 Visualizador de arquitectura: genera diagramas Mermaid en vivo, documentación en Markdown y mapas JSON.
Related MCP server: Graft
🚀 Inicio rápido
1. Instalación
# Clone the repository
git clone https://github.com/EldrexDelosReyesBula/CodeMemory.git
cd CodeMemory
# Install dependencies
npm install
# Build TypeScript
npm run build2. Comandos básicos
# Initialize CodeMemory in your repository
npm run dev -- init
# Scan the current codebase and index all symbols
npm run dev -- scan
# Search for any function, class, or symbol
npm run dev -- query authenticateUser
# Extract token-budgeted AI context
npm run dev -- context AuthService --budget 2000
# Start the live background file watcher
npm run dev -- watch
# Export Mermaid architecture diagram
npm run dev -- export --format mermaid
# Check repository health and statistics
npm run dev -- status🤖 Conexión a agentes de IA mediante MCP
CodeMemory proporciona un servidor stdio completo de Model Context Protocol (MCP).
Herramientas MCP disponibles
Herramienta | Descripción |
| Busca símbolos, firmas y funciones de código |
| Contexto con presupuesto de tokens, dependencias y llamadores |
| Imports ascendentes y dependientes descendentes |
| Modificaciones recientes de archivos y registros de commits de Git |
| Genera diagramas de arquitectura Mermaid en tiempo real |
| Estadísticas generales de la base de código y desglose por lenguajes |
Configuración de Antigravity y Claude Desktop
Añade lo siguiente a tu configuración de MCP (mcp_config.json o claude_desktop_config.json):
{
"mcpServers": {
"codememory": {
"command": "node",
"args": ["c:/Users/Eldrex/Downloads/classhost/Needs/CodeMemory/dist/cli.js", "mcp"],
"env": {}
}
}
}🏗️ Arquitectura
CodeMemory/
├── src/
│ ├── types/ # Domain data types & contracts
│ ├── db/ # SQLite engine with WAL mode & indexes
│ ├── parser/ # Multi-language AST symbol & dependency extractor
│ ├── watcher/ # Real-time debounced file watcher with .gitignore
│ ├── git/ # Git commit and diff history monitor
│ ├── generator/ # Mermaid diagram & Markdown/JSON exporters
│ ├── context/ # Token-budgeted context assembly & symbol ranker
│ ├── mcp/ # Model Context Protocol stdio server
│ └── cli.ts # CLI commands router
└── tests/ # Complete Vitest test suite📜 Licencia
Licencia MIT - Copyright (c) 2026 Eldrex Delos Reyes Bula.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenancePersistent codebase knowledge layer for AI agents. Pre-digests codebases into structured knowledge (symbols, dependency graphs, co-change patterns, architectural decisions) and serves via MCP. 28 languages, 14 tools, ~85% token reduction.537MIT
- AlicenseBqualityDmaintenanceLocal-first codebase context engine that parses code into a ranked dependency graph and serves it to AI tools via MCP for deep structural understanding.581MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to retrieve and manage code context with hybrid search, project memory, and observability via MCP tools.29MIT
- AlicenseNot gradedqualityDmaintenanceServes structured code context via MCP, enabling AI agents to understand codebases with dependency graphs and significantly reduce token usage.39MIT
Related MCP Connectors
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/EldrexDelosReyesBula/CodeMemory'
If you have feedback or need assistance with the MCP directory API, please join our Discord server