The persistent context and memory layer for AI agents. 5-layer cognitive architecture, 7 specialist agents, 6 memory vaults, 6 platform adapters. For Claude Code, OpenCode, Codex, Gemini, Cursor more integrations in development

Starlight Intelligence System

The persistent memory layer for humans and AI agents. Six semantic vaults that compound your intelligence over time. Local-first. Forkable. Free.

Why

Every AI session starts from zero. You re-explain your stack, re-share your preferences, re-teach patterns the agent mastered three sessions ago. The intelligence never compounds.

SIS fixes that. It is a small, local-first memory layer that stores your insights, decisions, and intentions in six semantic vaults, then exposes them to any AI tool through MCP. Use it once and the next session already knows.

Quick Start (2 minutes)

Option 1: As an MCP server (recommended for AI tools)

Install the package, then add this to your Claude Code settings.json:

{
  "mcpServers": {
    "starlight": {
      "command": "node",
      "args": [
        "node_modules/@frankx/starlight-intelligence-system/dist/mcp-server.js",
        "--vault-dir",
        "~/.starlight/vaults"
      ]
    }
  }
}

Restart Claude Code. You now have ten sis_* tools available in every session.

Option 2: As a library

pnpm add @frankx/starlight-intelligence-system

import { StarlightIntelligence } from "@frankx/starlight-intelligence-system";
import { createAdapter } from "@frankx/starlight-intelligence-system/