Litplay uses a first-rate AI model: Claude Sonnet 3.6. AI Dungeon may have many bells and whistles but Sonnet 3.6 is much smarter than even their premium models.
The lore updates system develops story content behind the scenes to allow for more immersive and realistic storytelling. It functions like the DM's notes, preparing whatever awaits you. This is intended for murder mysteries or scenarios where there is important background information the player isn't supposed to be shown.
You can go anywhere with your stories. If you find yourself bored with the direction things are going, revise your previous actions and redirect the game in another direction. The continuity feature lets you try out as many different approaches as you want.
Litplay offers a free trial of all features. Simply log in and make an account to begin. Subscribe for continual access.
Do you want to be grasshopper? A steward on the last night of the Titanic? A sorcerer (with any spells)? A starship captain (with any ship)? A superhero (with any ability)? A wizard pretending to be a robot? A robot pretending to be a wizard? A mysterious being cursing artifacts, people or aliens? Having a picnic on the grsasy knoll in Dallas '63?
Do you want to self-insert into almost any franchise? Sonnet won't know the most obscure ones but you can prompt it in. Naturally, Sonnet is strongest at real-life events, it's excellent for alternative history.
Powerful tone control in our system prompt – write in the style of Homer's Odyssey, Tolkien, the Bible, Shakespearian iambic pentameter (or anything you can think of). Pick tones like supernatural horror or epic fantasy. Instruct the AI to take special care with stellar phenomena or carefully consider the consequences of you manipulating Newton's laws.
Humour too cringeworthy? Silliness too generic? Specify your desires exactly and enjoy fine control. You can change the system prompt ingame at any time ingame.
If the AI errs in some respect, you can enter worldwrit mode to directly edit the text, preventing further immersion-breaking mistakes.
Quickly load and edit prompts, take inspiration from the creativity of others and make your own. There are many prompts in 'Saved' beyond the 5 Featured Prompts, plus there is tagging and search for ease of access.
While other AI adventure games scrimp on token context (offering pathetically small 2K or 4K context limits), Litplay offers full transparency and player control. You get all context visible and more. When adventures get long, you can press the summarize button and start anew in a new context length + some of the last responses(you can of course edit the summarized start of the adventure if the AI summary is inadequate). Litplay never compresses or cuts off the context length without your permission, though you will eventually want to summarize since long context lengths reduce quality.
You can also have AI take actions in the story, if you want to see how an AI-directed adventure goes, get a window into Sonnet's psyche. Just right click 'submit action' to generate an AI input.
Featured: These are some sample prompts pre-prepared to give examples of what litplay can do. Clicking them loads text into the story and system prompt which can be freely edited.
Saved prompts: These are user-generated prompts with tags to describe what they're like. These can be saved (publicly or privately) from any saved game, so if you want to revise your prompt and improve it, you can. You can also take inspiration from these and make a variation on them to suit your own desires. Only the user who made a prompt can edit it directly. If you enjoy a prompt, save it so others can have fun with it too.
Saved games: All games you create will appear here with a title. You can load them, delete them or save the story prompt and system prompt for later use.
Your Character's Story box: This is where the story prompt goes, describing the general situation and what you're playing as. For example, 'I am a wizard exploring a dungeon..."
Story Style & Tone box: This is where the system prompt goes. For example, "Use second person. Try and maintain an upbeat narrative tone even in the face of vast and arbitrary disaster. Don't use cliched language like 'eyes sparkled'...
Enable Lore Updates: This setting activates the lore updates system, where Sonnet generates secret internal knowledge, making the story somewhat dynamic. It functions a little like the Dungeon Master's notes.
Begin adventure: Starts the game. You have to press this to go anywhere.
You'll see your initial prompt and the AI response streaming in at the start.
Ctrl + increases the font size, Ctrl - decreases it.
Box at the bottom with 'what would you like to do': This is where you put your character's action in. It can be short or as long as you like.
Submit action: Left click sends your action to the AI. You can also use Ctrl+Enter in the text box to submit your action. Enter alone just adds a new paragraph, it doesn't submit. Right click on submit action for Sonnet to come up with its own AI action instead.
Edit buttons: These edit your actions, creating a new continuity. The story begins again from the new point of divergence. It's like an alternate timeline.
Continuity 1: You start with 1 continuity by default. If you make a new continuity, you can switch between them here.
Edit system prompt: Edits the system prompt. Can make the game harder, easier, alter tone and style and many other things.
Worldwrit mode: Allows you to directly edit AI responses to precisely fix inconsistencies or errors without regenerating the entire response.
Summarize story: Summarizes the story via AI, starting it anew in a new context length. This is advised if it gets too long (40-50 responses or higher), otherwise Sonnet struggles with the length. Don't click this by accident, it takes a while (sometimes over a minute) to process.
Subscribing for $8 USD/month gives you continued access to Litplay, while the free trial has a much lower hard usage cap. Your subscription gets you roughly 36 games with 12 turns each (4000 words per game) monthly, or 144,000 words/month. Substantially more if you play without lore notes, or play more games with fewer turns (costs increase arithmetically for each turn in a story).
Yes. You can close the page or return to the menu at any time as long and all will be saved. Just don't close the page as the text actively streams in, then the response will be lost.
If your prompting is too edgy for Claude, it'll refuse. Claude doesn't like sex or extreme, gorey violence. You'll need to reprompt. More commonly there are errors when the Sonnet API is overloaded - I can't do anything about this. If you see any game error messages from the webpage itself, they probably are my fault. Ideally, please open browser dev tools (hotkey usually F12) and copy out what's inside, the error messages like 'Internal Server Error' send me the info on what went wrong and what caused it.
Prompting is key. Strong violence is best done in the right context, in dark fantasy, military sci-fi or Warhammer-style settings. Specify the tone you want - bleak, grimdark, suitable for a 40K book... Refusals can sometimes be argued with if they're non-sexual. I'm not censoring you, it's the model itself. The price of Claude's intelligence is that its creators want to keep their image squeaky clean and their bots super-saccharine for when they take over the world.
In-context learning. The more you win in past iterations, the more likely you are to win in future turns. Sometimes Sonnet also shifts into an impressed mood and starts praising you for being clever in tactics. Alternately, if you specify for a difficult adventure then Sonnet will throw more and more opponents against you, it can get somewhat frustrating or feel cheap and arbitrary. You can moderate this with prompting, specifying for challenging but not unreasonable or contrived encounters.
Deepseek R1 is great fun but it doesn't perform so well for multi-turn games, R1 gets somewhat chaotic and incoherent. It's a beautiful, crazy, dramatic dream with the occasional snippet of Chinese. Plus you have to wait for it to think, interrupting the flow of the game. I find Claude is preferable for long exchanges. I may end up adding Deepseek as another option though.
You get out what you put in. Brief, generic inputs get more generic outputs. Try and roleplay as your character, do as they'd do! Be creative, almost anything can be a prompt or story setting if you extend it out. You can mix two fictional settings together, add a twist, invent an alternate history, create your own setting and have Sonnet help you come up with story ideas... Litplay isn't limited to pure gameplay (though that's the intended purpose), you can ask other questions for brainstorming/idea-sparking, use it to help ensure historical accuracy.
You can consult external websites for inspiration. For instance, superpowers wiki's random power button: https://powerlisting.fandom.com/wiki/Special:Random/main or the pathfinder wizard spells list, if you're playing a wizard. Claude is mediocre at coming up with interesting ideas creatively, it's best at adapting and expanding on human creativity. That's why I prefer 2nd person stories where you the human are driving the action. Third person is also totally doable but needs a good prompt for Claude to really get into it.
Just ask. Claude is pretty smart. If you want a more detailed, rich world, just ask it to take things in that direction in system prompt. If the humour is too cringeworthy and random, tell it not to be so random. You can articulate complex ideas. Imagine there's a strange, weird person on the other end of the text interface but a person nonetheless who can be reasoned with. You can also directly paste in large chunks of text from a style you like, ask it to analyze that style and write like that.
I don't store sensitive information like your credit details, only your email address. Transactions are processed by Stripe, not me.
You can send an email to me at litplaydev@proton.me or join the discord here: https://discord.gg/RgqavDun.
I'm James Leeming, indie dev. I made Litplay after having a lot of fun RPing with Claude Sonnet 3.5 like it was a DM and I was the player. Sonnet has a huge knowledge base and it's fairly creative and smart. I really liked struggling with it, making tough prompts and then thinking creatively to beat the complications and problems it threw up against me. It's a fun mind-game! I also enjoyed wielding OP powers and managing crazy situations.
But there were some shortfalls. If Sonnet made a mistake in the webapp I couldn't fix it without regenning the whole response which felt wasteful. What if it's a good response but mixes up someone's name (this can happen if fake identities are being used)? As the context length rises it got dumber and more rigid, not to mention it chewed up my usage. It was bad at summarizing by just naively asking for a summary, I had to personally summarize stories and start a new session.
Sonnet also was making it up as it went along, there was a lack of structure and planning behind it, no consistency. I made Litplay (with features like lore updates, worldwrit and auto-summarization) to try and minimize the shortfalls with using Sonnet for RP/text adventures, while maximizing the upsides. Litplay is also about sharing human creativity. Much of the time I was thinking 'this is such a powerful AI but what can I use it for?'. Playing with other people's prompts can give you new ideas and make it more fun for everyone. The tagging/prompt saving system should also be better than saving your prompts in a Word document!