AI agents are getting smarter every day — but they still suffer from a fundamental limitation: they forget.
Different agents working on the same problem rarely share context, history, or decisions. One agent discovers a breaking API change, another reviews code, a third generates documentation — and none of them know what the others have already learned.
MAGI — Multi-Agent Graph Intelligence. Universal memory server for AI agents. MCP + gRPC + REST API with semantic search, knowledge graph, and behavioral pattern analysis.
Estrelas
3
Ferramentas
—
Disponibilidade
—
Switch machines and your agent has amnesia. Switch providers and your context is gone. Every session starts cold.
In short: plenty to panic about.
What Is MAGI?
Don't.
MAGI is a universal memory server for AI agents. It acts as a shared, persistent brain that any agent can read from and write to — regardless of framework, language, or orchestration model.
Host it on your own hardware, point every agent at the same server, and your context persists across sessions, machines, and providers. No vendor lock-in, no rebuilds, no cold starts.
MAGI exposes memory through multiple protocols — MCP (stdio), gRPC, REST API, and a Web UI — making it easy to integrate into existing workflows without forcing a specific toolchain.
Why MAGI Is Different
MAGI isn't just another vector store or RAG backend.
Git-Backed Memory
Every memory write is committed to a Git repository — full history, diffs, rollback, auditable changes. The database is a derived index, not the source of truth.
Distributed Node Mesh
Dedicated Writer, Reader, Index, and Coordinator node pools with session affinity for read-your-writes consistency. Supports both embedded and multi-node deployments.
Hybrid Semantic Search
Combines vector embeddings and BM25 for accurate recall across structured and unstructured memories.
Knowledge Graph + Pattern Detection
Automatically links memories into a knowledge graph and surfaces behavioral patterns — preferences, habits, recurring decisions — across agents.
Built for Production
Async write pipeline — returns 202 Accepted in under 10ms
Caching layers — queries, embeddings, and hot memory
Health probes — /readyz, /livez, expanded /health for Kubernetes
Metrics endpoint — latency, queue depth, cache stats, and more
This project is dedicated to Mary Margaret — a dear friend who believed that the things worth remembering are the things that connect us. MAGI carries her spirit: nothing important should ever be forgotten.
⚠️ Stability
MAGI is not production-ready yet. It is useful today and improving fast, but expect breaking changes, rough edges, and the occasional surprise until a stable release is tagged. Back up your data, test in your own environment, and plan for things to break. Bring a towel.
SQLite is the most-tested backend; PostgreSQL, MySQL/MariaDB, and SQL Server backends exist but see less CI coverage. The distributed node mesh is architected but currently ships as a single-node embedded process. Git-backed history is optional and off by default.
License
Elastic License 2.0 (ELv2) — free to use, modify, and self-host. Cannot be offered as a managed/hosted service without a commercial license from the author.
M
Magi
j33pguy·3 estrelas·
MAGI — Multi-Agent Graph Intelligence. Universal memory server for AI agents. MCP + gRPC + REST API with semantic search, knowledge graph, and behavioral pattern analysis.
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Perguntas
Como instalo Magi?
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
Magi precisa de uma chave de API?
Este registro não lista nenhuma variável de ambiente obrigatória.
Qual transporte Magi usa?
Magi roda localmente via stdio.
Quando Magi foi verificado pela última vez?
Última verificação: 2026-10-28. MAGI — Multi-Agent Graph Intelligence. Universal memory server for AI agents. MCP + gRPC + REST API with semantic search, knowledge graph, and behavioral pattern analysis.