DevArcher

Building SynArc | Prompt → world → everything else.

AI-native worlds with memory, continuity, stories, systems & cinematics.

[DevArcher @katchimeradev]

Spent years building games and animation systems

Time to build something new in public!

A system that turns prompts into worlds, stories, apps, characters, gameplay systems, and cinematic experiences — all connected through a persistent world graph.

Think:
prompt → world → everything else

Sharing experiments, failures, prototypes, and ideas as I go

[DevArcher @katchimeradev]

Totally agree
That’s why we’re building scene graphs with SynArc for our long form filmmaking tool
Long form cinematics with recurring sets and locations need environments with spatial relations encoded , not sure why this doesn’t exist with the available tools. Either way we are building that in stealth still. Hierarchical scene graph (sets -> zones -> POIs /spots global to local images with multiple angles encoded per spot) and per shot coverage anchors that draw from it

[DevArcher @katchimeradev]

@BLVCKLIGHTai @MultiHyphenArt I’m curious what is your ideal UX workflow ? We are building this tool and want to understand what artists actually want in the interface, genuinely!
This thread has been noted for the insights thanks :)

[DevArcher @katchimeradev]

@boardyai Working on SynArc , the continuity layer for creative IP creation generative media / cinematics etc

[DevArcher @katchimeradev]

@JakeFleshner Creative continuity

[DevArcher @katchimeradev]

Fable generated all assets it needed automatically without even prompting it directly , just did whatever it needed as part of the feature work , even setup birefnet by itself , which was amazing for the iOS app I was building -which involved creating creature card graphics with transparent backgrounds and more!
I don’t know how well opus 4.8 or got 5.5 would handle that , but at the least we can prompt them to do things more directly if need be using this setup

[DevArcher @katchimeradev]

Found a workflow that lets Claude Code agent generate any real production asset you want: images, video, transparent PNGs, directly from your own backend. No more manually wrangling graphics. This was with Fable, before it was sadly suspended but I think it can be done with Codex gpt 5.5 and opus 4.8
Here’s the full setup 🧵

[DevArcher @katchimeradev]

Tell Claude to build edge functions that call https://t.co/JAokIdogW6 using that secret. These become your asset-generation endpoints: images, video, whatever fal supports.

Then just prompt. “Generate a hero image.” “Cut out this background.” Claude hits the edge functions directly and the finished assets come back ready to drop into your app.

The transparent-background part is underrated, it runs BiRefNet to cleanly cut out subjects. Huge for app UIs where you need proper PNGs, not boxy stock images.

[DevArcher @katchimeradev]

Create a https://t.co/JAokIdnJ6y account and grab an API key. Add it to Supabase as a secret, not hardcoded. Keeps the key server-side and out of your client code.

Run npx supabase login so Claude has authenticated access to your project. Now it can actually deploy edge functions, not just suggest them.

[DevArcher @katchimeradev]

Spin up a Supabase project to act as your “command center.” This is where your edge functions, secrets, and asset pipeline will all live.

Hit Connect, copy the prompt into Claude code, and install the Supabase skill. Now Claude knows how to work with your backend natively instead of guessing.

[DevArcher @katchimeradev]

@Clairenzz7 Sure thing

[DevArcher @katchimeradev]

@Brennan_Lup Building this , background as professional game dev gives advantage :

https://t.co/knoNZGcnil

[DevArcher @katchimeradev]

@anuatluru You captured this perfectly in words
always felt this and X is one of the biggest theaters where it plays out :p

[DevArcher @katchimeradev]

@Sathibuilds Nope!
When you get used to that speed and breadth of dev, and AI filling all your gaps in knowledge , plus knowing models and agents keep getting better , it’s hard to go back

[DevArcher @katchimeradev]

@taherdhanera Agreed and also
Way too many fast cuts, too short and fast paced
The 15 second limit and costs drive people to make quick and snappy cuts it seems
We need more slow scenes with emotion and build up , plus way better scripts

[DevArcher @katchimeradev]

Agreed quality scripts is what’s holding AI filmmaking back !

Think of the most iconic scenes from best movies and tv shows ever that move people , we’ve yet to have a moment like that from an AI film that becomes part of the culture, when that happens it will be embraced

Need groundbreaking scripts for that tho! And need the best writers to embrace, as right now mostly tech forward people unlocked creatively are

I think we need to make more collabs with great writers to get it done

[DevArcher @katchimeradev]

@farbood Yea being technically strong won’t mean anything anymore

you’ll need have the best creative work in an ever harder world to stand out at all and also to be a big personality who knows how to sell yourself and your work

[DevArcher @katchimeradev]

Not quite video editing but long form cinematics creation from a world, solving continuity, an IP builder essentially but we’re setting high quality and continuity bar for ourselves :

https://t.co/kyhkHHBo4d

Welcome to X
Growing an audience is quite an uphill battle

What you working on yourself ?

[DevArcher @katchimeradev]

@andrewxsaas https://t.co/knoNZGcnil