Checklist · 17 Nov
A setup checklist for a new AI roleplay world
Approved by the founder
How-to · 2 min read
If you write long stories with an AI, you know the moment when a character suddenly forgets a promise, a scar or the name of their own city. Fifty messages in, the model loses track of what happened at the start. You end up reminding it again and again, and the story loses the thread that made it worth writing.
Language models only see a limited window of recent text, so older parts of a story fall out of view. Simple chat apps send the last few messages and hope that is enough, which it rarely is once a story has a real history behind it. Pasting a summary into every prompt helps for a while, but it gets long, takes space from the story and still misses small facts. Many writers keep notes in a separate document and copy pieces back in by hand. That works, but it turns creative writing into bookkeeping, and the more characters and places a world has, the faster it falls apart.
This part describes the usual way. It makes no claims about The Codex AI, so nothing is quoted here.
The Codex AI is built around keeping a world's facts available to the model. Tesseract Codex lets you organize lore into structured tiers, such as world lore, NPC bios, magic and tech systems, factions and timeline events, with toggles for what gets injected. A three-tier retrieval cascade combines keyword matching, BM25 relevance scoring and semantic vector search to pull in the lore and characters needed for each turn, rather than everything at once. Chronicler Memory works in the background, extracting facts, relationship shifts, active quests and inventory items into a Memory Ledger you can look at. Branches are tracked too, so memory follows the timeline you are on. And an in-chat command such as /remember lets you point the story at something it should keep. Existing lorebooks from SillyTavern, KoboldAI or NovelAI can be imported in batch, so you do not have to rebuild a world by hand.
Structured world lore tiers (World Lore, NPC Bios, Magic & Tech Systems, Factions, Timeline Events).Quoted from thecodexai.com
Autonomous background extraction of facts, relationship shifts, active quests, and inventory items with branch-aware timeline ancestry filtering and an interactive Memory Ledger.Quoted from thecodexai.com
Sub-millisecond keyword matching, stemmed BM25 context relevance scoring, and semantic vector embeddings dynamically summon the exact lore and characters needed per turn.Quoted from thecodexai.com
Keep each lore entry short and about one thing. Small entries are easier for the model to use than long essays.
General advice. Not a claim about the product.
Give each entry clear trigger words, like a character's name or a place, so keyword matching can find it.
Automatic trigger keyword extraction, category classification, and token usage estimation.Quoted from thecodexai.com
When you branch a story, check that the memory follows the branch you are on.
branch-aware timeline ancestry filteringQuoted from thecodexai.com
Use the prompt inspector before an important scene to see what the model is actually being given.
What is the OmniSight™ Pre-Flight Prompt Inspector and Context Transparency?Quoted from thecodexai.com
Yes. SillyTavern World Info, KoboldAI, NovelAI and Agnaistic lorebooks can be imported in batch.
Import SillyTavern World Info JSONs, KoboldAI, NovelAI, and Agnaistic lorebooks in batch.Quoted from thecodexai.com
Yes. /remember is one of the in-chat slash commands.
/rememberQuoted from thecodexai.com
Yes. Persistent vector memory is part of the free core features.
timeline branching, and persistent vector memoryQuoted from thecodexai.com
Checklist · 17 Nov
Approved by the founder
· 17 Nov
Approved by the founder
Story · 17 Nov
Approved by the founder