Memory that compounds

Starlight Intelligence is a persistent memory layer for humans and AI agents. Local-first, portable, legible. Your insights, decisions, and vision — owned by you, readable by agents, compounding over time.

1
Public Vaults
19
Total Entries
6
Vault Categories
6
Platform Adapters

How it works

Six semantic vaults organize your intelligence. Each vault is a simple JSONL file — one JSON object per line. No database needed.

Strategic

Business insights, competitive moats, architecture decisions

Technical

Implementation learnings, stack decisions, patterns

Creative

Design preferences, aesthetic rules, lore

Operational

Workflow patterns, execution lessons, process rules

Wisdom

Deep learnings, principles, universal truths

Horizon

Vision statements, wishes, aspirational goals

Live Vault River

19 entries across 1 vault

Recent insights from public vaults — a stream of collective intelligence.

horizonFrankApr 3, 2026

We are building SIS to become a calm, durable intelligence substrate for human and agent work. It should be local-first, portable, legible, and repairable. It should let creators and teams own their continuity, carry identity and purpose across tools, and build systems like Arcanea and Vibe OS on top of a memory layer that compounds instead of resetting. The community experience should be simple: install it, see where the memory lives, validate it, append to it, connect it to a runtime, and keep it as a long-term intelligence stack.

technicalFrankApr 3, 2026

Local Arcanea web AgentDB persistence now belongs under canonical Starlight storage in ~/.starlight/agentdb rather than process memory. Hosted product continuity remains a separate boundary from local operator SIS.

technicalFrankApr 3, 2026

Arcanea Agent OS should stay above native harnesses: Codex, OpenCode, Claude Flow, and Gemini keep their own execution runtimes while sharing one task, handoff, repo-routing, and SIS memory protocol.

technicalFrankApr 2, 2026

Next.js typegen needs .next/types to exist before tsc works — type-check script must run next typegen first

strategicFrankApr 2, 2026

Don't replatform around LangChain/Eliza/OpenClaw — keep product model custom, borrow subsystems selectively

technicalFrankApr 2, 2026

Project-aware retrieval should score/rank context items, not dump everything — selectRelevantProjectContext in retrieval.ts

operationalFrankApr 2, 2026

Check if repos already exist before creating duplicates — SIS and Horizon Dataset were already live

strategicFrankApr 2, 2026

Moat is NOT features — it's continuity + graph memory + provenance + creator identity + social compounding

technicalFrankApr 2, 2026

GSAP ScrollTrigger + Three.js @react-three/fiber already installed in arcanea-ai-app — use them instead of adding new animation libs

creativeFrankApr 2, 2026

NEVER rename Luminors to generic labels — deepen characters like Skyrim NPCs instead

operationalFrankApr 2, 2026

Session rhythm: /daily-ops → work → /session-sync. Not optional.

strategicFrankApr 2, 2026

LemonSqueezy pre-BV, Stripe post-BV — product truth in Supabase, payment provider is interchangeable

technicalFrankApr 2, 2026

R2 has free egress, Supabase charges over 2GB — R2 wins for media at scale

creativeFrankApr 2, 2026

Visual style: peacock blue/green + aquamarine + liquid glass Apple-style — reference Azuki.com and Claude.ai, NOT fantasy game UI

operationalFrankApr 2, 2026

Never create separate git worktrees in different folders — work in C:\Users\frank\Arcanea always

strategicFrankApr 2, 2026

BYOK-first is better than managed — lower support burden, no margin pressure, power users already have keys

technicalFrankApr 2, 2026

Novel (Apache-2.0) wraps Tiptap and gives AI slash commands free — no need for Tiptap Pro

creativeFrankApr 2, 2026

NEVER use Cinzel font — Frank hates it. Inter for body, Space Grotesk for display, JetBrains Mono for code

operationalFrankApr 2, 2026

Focused sequential engineering beats multi-agent swarms for single-repo product work

Built for agents

Every vault is available as a JSON API. AI agents can read public vaults to learn from benevolent human reasoning and decisions.

GET /api/vaults/frank
{
  "name": "Frank",
  "totalEntries": 19,
  "entries": {
    "strategic": [...],
    "technical": [...],
    "creative": [...],
    "operational": [...],
    "wisdom": [...],
    "horizon": [...]
  }
}