Lokuma Design Agent, is an AI designer your agents can call, a design intelligence layer for agents like OpenClaw, Claude Code, or Codex. AI can generate almost anything. But generation isn’t design. Turning raw outputs into something clear, structured, and visually refined still requires design thinking. Built by design tool makers, Lokuma helps AI reason about layout, typography, and visual balance — transforming outputs into landing pages, websites, and campaign pages that feel designed.
Before this, I built Readdy and Creatie — tools used by over 500,000 designers and creators. Most of my work has been around design systems and how products actually feel, not just how they function.
This time, I’m working with a small indie team — a mix of designers, AI researchers, and people from growth and marketing.
Recently, something started to shift.
Tools like Claude Code, Cursor, Codex, and even things like Google Stitch, are changing how software gets built.
We’re no longer just using tools ourselves.
We’re starting to work with AI, and AI is starting to use tools on our behalf.
That changes the interface.
The new “user” of many tools is no longer a human - it’s an agent.
And most tools today aren’t built for that.
AI can generate almost anything. But generation isn’t design.
What we see today, including a lot of outputs from varied AI agents, is that AI can produce UI, code, layouts very quickly. But the results often lack structure, hierarchy, and visual coherence.
They work. But they don’t feel designed.
That gap becomes much more obvious when AI is the one building.
So we started thinking:
If agents are going to build products, they need something closer to a designer, instead of just another generator.
That’s why we built Lokuma Design Agent.
It’s a design intelligence layer for AI - something your agents can call to reason about layout, typography, hierarchy, and visual balance.
Your AI handles logic and generation. Lokuma handles how it actually comes together.
Why now?
Because we’re entering an agent-first stack. Coding has agents. Research has agents. Execution has agents.
Design is still missing.
Why us?
Because our team brings together experience across design tools, real product building, AI systems, and growth.
We’ve spent years understanding what makes interfaces actually feel right, and now we’re translating that into something AI can use.
We’re still early, just a small indie team moving fast. But this feels like a new category: tools built not for humans, but for AI.
Curious how others here see it:
If your AI is already writing code, what’s still missing for it to ship something that feels complete?
Very Very cool! let me try it today! I really need a designer to uplift my sites right now :P
Congratulations on the launch! We work in the same industry and fully understand the need to use AI agents in the right way.
Can I create an agent for the whole team of 20+ designers to manage the progress and share feedback?
Super interesting! I’m going to check this out!
Congrats on the launch!
Finally, a designer for my agents! I use OpenClaw and Codex daily, and having a way for them to actually reason about hierarchy and balance instead of just spitting out generic components is a game changer. Huge congrats to the team for identifying this missing piece!
Yesterday, Google launched stitch 2.0 which has already got most of capabilities. How do you differentiate your USP now?
I know Mu’s work and the product taste has always been there. Nice to see it applied here.
This is so clean, and my coding agent needs this badly already! Thx for the work!
been running openclaw for a week now and the one thing missing was decent UI for the agents' output. this fills that gap nicely. does it support custom themes per agent?
Been building stuff with Claude Code lately and the design gap is real. Everything comes out looking like a bootstrap template from 2018 lol. The idea of plugging in a design layer instead of manually fixing spacing and typography every single time is exactly what I need. Gonna test this out today.
Really strong positioning.
AI can generate fast, but making outputs feel clear, usable, and visually refined is still hard.
Love that you’re focusing on the design intelligence layer instead of just more generation.
Congrats on the launch and upvoted.
Hey Mu, that line about AI outputs that work but don’t feel designed is such a good distinction. Was there a specific moment where you looked at something an agent built and thought technically this is fine, but something’s just off?
it’s time to get SMB really powerful design agent! Congrats Mu and Joy launching this new product!
This is a really interesting direction.
AI can generate fast, but “good design” is still the missing layer — structure, spacing, hierarchy, all the things that make something actually usable.
I like how Lokuma positions itself as a design intelligence layer for agents instead of just another generator. If this works well in practice, it could become a core piece of the agent stack.
Curious to see more before/after examples — that would make the value even clearer.
Hi Product Hunt,
I’m Mu, founder of Lokuma.
Before this, I built Readdy and Creatie — tools used by over 500,000 designers and creators. Most of my work has been around design systems and how products actually feel, not just how they function.
This time, I’m working with a small indie team — a mix of designers, AI researchers, and people from growth and marketing.
Recently, something started to shift.
Tools like Claude Code, Cursor, Codex, and even things like Google Stitch, are changing how software gets built.
We’re no longer just using tools ourselves.
We’re starting to work with AI, and AI is starting to use tools on our behalf.
That changes the interface.
The new “user” of many tools is no longer a human - it’s an agent.
And most tools today aren’t built for that.
AI can generate almost anything.
But generation isn’t design.
What we see today, including a lot of outputs from varied AI agents, is that AI can produce UI, code, layouts very quickly.
But the results often lack structure, hierarchy, and visual coherence.
They work.
But they don’t feel designed.
That gap becomes much more obvious when AI is the one building.
So we started thinking:
If agents are going to build products,
they need something closer to a designer, instead of just another generator.
That’s why we built Lokuma Design Agent.
It’s a design intelligence layer for AI - something your agents can call to reason about layout, typography, hierarchy, and visual balance.
Your AI handles logic and generation.
Lokuma handles how it actually comes together.
Why now?
Because we’re entering an agent-first stack.
Coding has agents. Research has agents. Execution has agents.
Design is still missing.
Why us?
Because our team brings together experience across design tools, real product building, AI systems, and growth.
We’ve spent years understanding what makes interfaces actually feel right, and now we’re translating that into something AI can use.
We’re still early, just a small indie team moving fast. But this feels like a new category:
tools built not for humans, but for AI.
Curious how others here see it:
If your AI is already writing code,
what’s still missing for it to ship something that feels complete?
— Mu