I looked into building games for free online & this is what I discovered

-

I asked Claude a question:

provide me a list of options of the latest online GenAI powered environments where kids can focus mostly on concepts and imagination of games making rather than having to build everything from scratch, therefore requiring a simpler skill set and lower barrier to entry


Let me search for the latest options available.These results cover the professional/industry side. Let me search more specifically for kid-friendly, low-code AI game-making platforms.Here's a roundup of the most relevant options available right now, ordered roughly from the lowest barrier to entry upward.

1. Rosebud AI (rosebud.ai) You describe your idea and Rosebud builds it — no coding required. It lets anyone build games, from 2D to 3D worlds, just by typing their ideas. It runs in the browser and has a free tier. This is probably the simplest "type a prompt, get a game" experience right now, making it great for younger kids who want to focus purely on concepts and imagination.



2. MakeGamesWithAI (makegameswithai.com) These platforms are designed to transform text prompts directly into playable experiences, with a no-code editor, a large asset library, and chat-based editing using natural language. You describe the experience you want, not the code you need — within seconds, the platform generates a complete, playable game including game logic, assets, and scoring. Very much geared toward the "one prompt to playable game" workflow.


3. Nilo (nilo.io) Nilo is the only free online creator built specifically for 3D development with integrated AI help, using a "vibe coding" system where you describe what you want in plain language. Nilo is a platform on which both users with and without game development experience can generate and play 3D games with AI. It runs entirely in the browser, supports real-time collaboration with friends, and can export to Roblox. The workflow feels more like playing a game than using complex development software. Great for kids aged roughly 11–18 who want to build 3D worlds together.



4. Flowlab (flowlab.io) Flowlab is a beginner-friendly, fully in-browser no-code game builder popular with students and teachers, with a visual editor, built-in sprite tools, and instant web publishing. It uses a visual logic system (drag-and-drop behaviour blocks) rather than text coding, and includes a pixel art editor and audio library. It's not GenAI-powered per se, but the visual approach keeps the focus on game design concepts rather than syntax. Very popular in classrooms and homeschooling.


5. GDevelop (gdevelop.io) GDevelop is the only open-source engine with an intuitive no-code approach, using a logic system based on conditions ("If") and actions ("Then"), with over 130 ready-made behaviours and extensions. It has recently added an AI assistant to help answer "how-to" questions and generate logic. It supports both 2D and 3D, publishes to web, mobile, and desktop, and has a large library of tutorials. The no-code events system means kids can focus on game design while the AI helps when they get stuck.



6. Roblox Studio + AI tools Roblox Studio itself now has growing AI integration, and several third-party AI plugins supercharge it further. Tools like Rebirth let you describe what you want and the AI builds it directly inside your open Studio session — it sees your game's parts, scripts, and hierarchy. SuperbulletAI lets you generate UI, animations, VFX, 3D builds, and complete game systems with simple descriptions. The barrier is a bit higher (you need to install Roblox Studio), but the massive Roblox community and the ability to publish to millions of players makes it very motivating for kids.


7. Scratch (scratch.mit.edu) Still the gold standard for younger children (ages 8–16). Scratch is MIT's visual programming language that teaches coding ideas through simple games and animations, suited to complete beginners. While it doesn't have built-in GenAI features, it's the lowest-friction way for kids to learn game logic and design thinking with drag-and-drop blocks. Many kids use it as a stepping stone before moving to the more AI-powered platforms above.





In short: If you want the absolute lowest barrier (just describe your game idea in words), Rosebud AI, MakeGamesWithAI, and Nilo are the frontrunners. If you want something with a bit more hands-on design learning but still no coding, Flowlab and GDevelop are excellent. And if the child is already in the Roblox ecosystem, the new AI plugins like Rebirth and SuperbulletAI let them stay in familiar territory while dramatically reducing the technical work.


I was genuinely amazed at just how low the barrier to entry has become for making something that is visually impressive and with a well thought out idea, how a good game design and mechanics can be generated and enriched using these tools.

Don't get me wrong, AAA+ games creation houses like SONY Interactive Entertainment Europe are not going to be disappearing anytime soon, but you no longer have to wait for the next game to be created and released by the big development companies - you can take a wacky idea and make it real. It is creative, it is fun, it is personal and it is yours - that's the bit I really like.

It's like buying a mug from a shop, it already has the pattern / design mass produced onto it - however, the artistic person wants to make their own, with their own design and personality - no, they are not going to re-invent the mug itself, but they are going to put their individual stamp / mark on it and be proud of their art.

If these tools can help to inspire youngsters into being more creative and less passive, then this is a good thing!  They've had decades now of being passive users thanks to social media etc... it's about time they became the creators again & these tools are a small way to getting that mindset back again.


I just might have a go myself! I recall designing a few games on paper back in the late 1980s, that never saw the light of day, mainly due to the complexity of how to turn it into reality.  I'm sure I still have the information written down somewhere in the attic :-D


Comments

Post a Comment

Popular posts from this blog

Google Opal [experiment] - not in the UK yet

-
Image
Well, this is a turn up for the books and something long overdue for the general public: find out more here: https://opal.withgoogle.com/landing/ Now, you could just go off and do some gold-rush effort and I highly encourage you to do so - THIS is a game-changer.  It really is. As this is "my universe", I'm just going to pull it back to me (yes, very narcissistic, I know, but I don't care).  Here are a couple of articles that I just want to call attention to: https://tonyisageek.blogspot.com/2020/02/a-week-off-worksort-ofproject-o.html https://tonyisageek.blogspot.com/2020/12/project-o-my-machine-programming-project.html The basic premise was to use NLP (natural language processing) where you, as a non-technical person, could describe what you want an application to be and do.  Then, through the power of automation it would generate a starter-for-10 application from templated code and deploy it onto a Cloud environment, so that you could then see it / touch it / run i...
Read more

Weaviate Verba RAG with Node-Red & Ollama Engine

-
Image
Been absent a while, have had many things to be focused on; however, this recent little nugget needed to be documented & shared, mainly because I did this on my personal laptop & I need to recreate it somewhere else and this mechanism just makes it easier - also, this might help someone else out too. Right, so what am I talking about? About a year ago I was doing some new stuff with LLMs and RAG (ingesting own documents as the data to use rather than the LLM training data) and it was okay-ish, it did the job.  Zoom forward a year and obviously things have moved on, quite a bit. The RAG tools & code have improved significantly, it still takes time to ingest though - haven't found a way to speed that part up, well, I'm focused on offline/airgapped/onpremise solutions, it could probably be faster if using a Cloud SaaS offering, but that is of no interest to me, so I'll accept the time it takes. What are the steps inolved? Get a bunch of documents, upload them to be...
Read more

Remote Working Data Annotation options - Digital Nomad

-
Image
During the past, well, let's think, 10+ years, I've been involved in Machine Learning projects (okay, they call it "AI" now, but that's an argument for a different time) that require lots of data to be ingested / used to train the Machine Learning model. For instance, if it is text, we need lots of snippets of text that can then be categorised, so that the model "knows" that the 10 words grouped together in that context have a "meaning" and that meaning is labelled - this helps with questioning later on. It also helped to extract out the entities and relationships between the wording to give more context.  Here's a simple example using the spaCy tooling to give you an example: https://www.labellerr.com/blog/image-annotation-services-and-data-labeling-for-ai-models/ If it is imagery, we need lots of images with the segmented parts identified, usually a bounding box(?) to identify the elements / objects inside the image, so, again, this can b...
Read more