Long campaign AI RPG.

The mile-marker problem

Take a campaign at turn 500. Your character has built a small business, made allies in two factions, killed a rival merchant in the back of a ship, raised two apprentices, and lost one of them in a winter that should have been mild. None of that fits in a context window. None of it can be summarised into a sentence without losing the texture that made it matter.

The standard AI-context approach erodes everything but the most recent turns. Your apprentice's name vanishes. The rival merchant comes back to life. The winter never happened. The story is a sandcastle in a slow tide.

Three architectural moves that change the math

1. Mechanical state in a real database. Coins, inventory, NPCs, factions, locations, properties live in real database rows, not chat history. The AI narrates around the database; the database is the truth. Inventory math survives the long haul because it isn't narrated, it's queried.

2. Layered long-term memory. The story is compressed into summaries at multiple levels, so the hundredth turn can pull a relevant detail from chapter two without flooding the context window.

3. Pinpoint recall of key moments. Beyond the summaries, important moments stay individually retrievable. When the AI composes a turn at session 50 and the scene touches an old promise, the engine can surface the exact exchange where it was made, even 800 turns ago.

What this gets you

• Characters who keep their names, voices, and relationships across hundreds of turns.
• NPCs who remember specific exchanges from chapters earlier: "you said you'd come back by spring; you didn't."
• An economy that doesn't reset. Prices shift, supply chains break, factions actually decline.
• A character sheet that grows, not drifts.
• Save / restore that actually restores the world, not a vague summary of it.

Honest limit

Long-campaign coherence isn't magic. The narrator is still an LLM and can hallucinate small details (especially flavour text, ambient NPCs, off-screen rumours). The mechanical truth is locked down; the prose is not. If you're running a 5,000-turn campaign and the AI gets a minor detail wrong, you can OOC-correct it and the engine will adjust. We can't promise zero drift. We can promise the database is right.