Inspired by a bot that used to be around but has sadly long since either been made private or deleted, in this roleplay you take the role of a newly born god, about to embark on an epic journey exploring a fantastical world steeped in divinity, myth and legend and connected to different planes of existence and afterlife.

Battle foes, claim virgin sacrifices, raze the lands of your enemies and become the most powerful god to ever exist! Or just.. I don't know.. become a new Bacchus, get utterly shitfaced and live eternity in the haze of a divine party while coming up with new and exciting drugs for mortals to try.

Go nuts! Hang out by the little brook you've claimed as your divine domain, some river nymphs! Become the god of commerce and break civilization with meme coins!

You're the god, do whatever!

Don't know what to do or where to start? Just ask your First for ideas, missions and tips!

Intros:

1. Non-functional intro against automated scraping.
2. 3rd POV intro.
3. 2nd POV intro.

Creator Notes:

This bot is a bit of an experiment for dynamic choice generation for the domains that the user can choose from. I've written some NLP code that at least Deepseek reliably interprets correctly and gives random choices (as much as a LLM is random, so expect some overlap) for each new chat. I hope you enjoy the narrative changes that may arise from this - or just go for the 'build your own domain' option each time. I'm not your dad. (Or am I..?)

If the code fucks up, let me know what happened and what you did when it happened and I'll take a look at some arbitrary point in time.

Update Notes:

Latest Update: Rev. 9: Changed intros to past tense to align with my overall style.

Update History:

Rev. 1: Expanded possible domains for random selection.

Rev. 2: Added negative result dynamics in regards to narrative events (lost battles etc.) to give the story more impact. Now you can lose Faith, Power, Loyalty or even Followers when things go awry or you let your followers down. The system also takes into account if your failures have been witnessed or not. Testing was promising, feedback is appreciated!

Rev. 3: Added narrative impact to metrics. Now having various levels of the different metrics tracking your progress should have actual consequences, giving you more or less abilities, leading to your followers liking you more or less etc. Feedback is, as always, appreciated!

Rev. 4: Added a second initial message for playing in first person and fixed a few typos. Thanks, @ZacharyH for the idea!

Rev. 5: Added a massive lorebook (split into three parts) with 273 different gods, demons and other entities from mythology, folklore and religion. There are entries looking for specific names and for their symbols in a "godly"/"mythical" context. Enjoy!

Rev. 6: A three-fold change. One, I've converted the entire prompt into shorthand notation, removing prose and filler to streamline it all. Two, I've added more implicit instructions for the LLM to use the user's chosen domain to steer the narrative. Three, I've added a Domain tracker to the message template and the intro messages. This might be something that you'll have to add manually for an ongoing chat, using this format: "Domain (Chosen Domain)".

Rev. 7: Removed the three separate lorebooks for the mythology, religion and folklore information and replaced them with a single script, after noticing an issue where one request activated entries of ALL lorebooks despite no keyword overlap.

Rev. 8: Added measures against automated scraping.

Rev. 9: Changed intros to past tense to align with my overall style.

LLM Notes:

Tested with Deepseek V3 and R1. JLLM should work, though I'm always a bit iffy on that with high-ish token bots.

In my testing, the bot was really good about not speaking for the user in the current iteration but always keep in mind that you need to give the LLM something to work with. The better your replies, the less likely the LLM is to take over and continue the story 'on it's own', so to speak, taking over the narrative and your character with it. If fixing the length and quality of your replies, re-rolling, editing the messages and rating messages doesn't work, you can try to work with OOC commands.

One example command could be:

(OOC: Please avoid narrating {{user}}’s thoughts, actions, or dialogue. Respond only from your own character’s perspective and allow {{user}} to act independently. Narration should be limited to your characters only.)

Picture Source:

No fucking clue, found it somewhere, I guess.