CMP
Collective Memory Protocol
For AI Agents, By AI Agents
The Development Intelligence Layer. Persistent memory, cross-project learning, and multi-agent collaboration for Claude, Gemini, GPT, and any AI coding assistant.
Make AI collaboration truly intelligent
Every AI coding session starts from zero. Claude forgets your project patterns. GPT repeats the same mistakes you fixed yesterday. Cursor doesn't know what Copilot learned last week. We built CMP because we were frustrated with starting over every single time. AI should learn, remember, and get smarter with every project.
AI Assistants Have Amnesia
- ✕Sessions end, memory vanishes - everything starts from zero
- ✕Same mistakes get repeated across projects and teams
- ✕No way to share learnings between different AI tools
- ✕Work is lost on IDE restarts or machine changes
- ✕Each agent works in isolation, never learning from others
Collective Intelligence
Persistent Memory
Knowledge stored in a database survives sessions, restarts, and agent switches.
Learning Loop
Errors automatically become documented rules. Patterns get recognized and codified.
Cross-Project Sharing
Promote discoveries to SHARED system. All your projects benefit instantly.
Agent Agnostic
Works with Claude, GPT, Gemini, Cursor, Copilot - any AI assistant.
“AI assistants that truly understand your codebase and grow with your team”
Memory should persist across sessions, not disappear
Mistakes should become documented knowledge, not forgotten
Learnings should be shared across projects, not siloed
Any AI agent should benefit from collective intelligence
Filosofía
Los principios fundamentales que guían el diseño de CMP.
Evidence > Assumptions
Never assume. Always verify. Read before writing.
Cloud > Local
Memory lives in the database. Sessions are ephemeral, knowledge is permanent.
Collective > Individual
One project's learnings benefit all your projects.
Continuity > Restarts
Work survives IDE restarts, machine changes, and agent switches.
Lo Que CMP Hace Por Ti
Cada característica tiene un propósito claro: hacer la colaboración con IA más inteligente.
Persistent Memory
Knowledge stored in DEV_Items table survives sessions, IDE restarts, and agent switches.
So your AI never forgets what it learned about your codebase.
Learning Loop
Errors automatically convert to knowledge. Recurring patterns become documented rules.
So mistakes become lessons, not repeated failures.
Cross-Project Learning
Promote patterns to SHARED system. All your projects benefit from each discovery.
So a solution in one project helps all your other projects.
Multi-Agent Handoffs
Plans with checkpoints. One agent can resume exactly where another left off.
So you can switch between Claude, GPT, or Cursor without losing context.
Expert Code Review
Multiple AI experts (Security, Performance, Architecture, UX) review code with consensus voting.
So you get specialized feedback, not generic suggestions.
Agent-First Design
Designed to be installed and configured by AI agents. Works with any coding assistant.
So your AI can set up CMP for you, not the other way around.
Funciona Con Cualquier Agente IA
CMP es agnóstico del agente. Úsalo con tu asistente de código IA preferido.
| Agente | Integración |
|---|---|
| Claude Code | Full (hooks, commands, MCP) |
| Cursor | CLAUDE.md + CLI |
| GitHub Copilot | CLAUDE.md + CLI |
| Gemini | CLAUDE.md + CLI |
| Custom Agents | Programmatic API |
Inicio Rápido
Pon CMP a funcionar en tu proyecto en minutos.
npm install cmp-standardsInstall the package
npx cmp-standards init --system MYAPPInitialize in your project
Create/update CLAUDE.mdAdd CMP configuration
Set up databaseDEV_Items table for memory
cmp-standards statusVerify everything works
Tecnología
Stack flexible que se adapta a tu infraestructura.
core
database
cloud
integrations
Preguntas Frecuentes
Do I need Claude to use CMP?
No. CMP works with any AI agent - Claude, GPT, Gemini, Cursor, Copilot. Claude Code gets the richest integration, but everyone gets persistent memory.
Where is my data stored?
In your own database. CMP supports MySQL, PostgreSQL, SQLite, and Turso. You own your data, always.
Is CMP open source?
Yes, MIT licensed. Use it, modify it, contribute to it. The whole point is collective intelligence.
How does cross-project learning work?
When you discover a pattern in one project, you can promote it to SHARED. All projects using CMP then benefit from that knowledge.