MAGI

Multi-Agent Graph Intelligence

Open Source · MIT Licensed

Memory that persists.
Knowledge that grows.

The open-source persistent memory layer for AI agents. Git-backed, privacy-first, zero dependencies.

Get Started View on GitHub
magi-terminal
$

Everything your agents need to remember

A complete memory infrastructure built for production AI systems.

Git-Backed Versioning

Every memory is version controlled. Diff, rollback, branch. Your AI's knowledge base has a full audit trail.

Zero Dependencies

SQLite + ONNX embeddings. No API keys. No cloud. Runs entirely on your hardware.

Pluggable Storage

SQLite, PostgreSQL, MySQL, SQL Server, Turso. Plug into your existing database infrastructure.

Blazing Fast

Async write pipeline: <10ms client response. Caching layer: <1ms cached searches. 8+ writes/sec throughput.

Knowledge Graphs

Memories auto-link with typed relationships. See how your agent's knowledge connects and evolves.

Multi-Protocol

MCP, gRPC, REST, Web UI. Works with Claude, GPT, Codex, or any agent framework.

How it works

A clean architecture with async writes, hybrid search, and pluggable backends.

AI Agent MCP gRPC REST API Web UI MAGI Core Engine SQLite PostgreSQL / MySQL ONNX Embeddings Semantic Search Git Backend Version Control Knowledge Graph Relations & Patterns Async Write Pipeline 202 Accepted in <10ms • Workers handle embedding & indexing Hybrid search: semantic + keyword + graph traversal Auto-classify • Contradiction detection • Pattern analysis

How MAGI compares

The most complete memory layer for AI agents.

Feature MAGI Mem0 Letta Zep
Git versioning ✓ — — —
Local / offline ✓ — ✓ —
Knowledge graph ✓ — — ✓
MCP support ✓ — — —
gRPC ✓ — — —
Auto-classify ✓ — — —
Contradiction detection ✓ — — —
Pluggable SQL backends ✓ — ✓ —
Open source MIT Apache Apache Apache

Get started

Up and running in under a minute.

Install

binary curl -sSL https://raw.githubusercontent.com/j33pguy/magi/main/install.sh | bash
docker docker run -p 8080:8080 -v magi-data:/data ghcr.io/j33pguy/magi
source git clone https://github.com/j33pguy/magi && cd magi && go build ./cmd/magi
1

Start the server

magi serve
2

Store a memory

curl -X POST :8080/memories
  -d '{"content": "..."}'
3

Search & recall

curl :8080/search
  ?q=user+preferences

Use with Claude via MCP

Add MAGI as an MCP server in your Claude config: 

{
  "mcpServers": {
    "magi": {
      "command": "magi",
      "args": ["mcp"]
    }
  }
}