HackerHubHacker News discussion · story
Show HN: Klad, a paint app your coding agent can drive (source-available)
82 points32 comments1.2 average comments/hourSubmitted by ambewas
Submitted . This is a public Hacker News submission, not reporting by HackerHub.
Submission text
I've been developing applications for a long time and have turned to game development as well lately. One of the things that frustrated me the most was that using AI agents for game development is very annoying in the art department. Your only options right now are to either use an image genAI model and roll the dice every time you want to make an edit, or have your agent draw with something like vectors.
I was looking for an application that would allow me to ask an agent to make a first draft of whatever art I needed with actual brushes, and then be able to go in myself and edit every last stroke or layer that it created.
Klad is that application. Written in Rust, it can be fully controlled by an agent through the CLI, and every function is available in a nice UI as well: a brush engine, frame-by-frame animation (and bones/IK), vectors, text layers, colours, layer effects, infinite undo (even after re-opening the file!),…
Why I think it's useful for a wider audience: Adobe showed agents editing Photoshop files at MAX this week, with a private beta planned for early 2027.
Klad is built on the same core idea, with editable paint strokes as core architecture, and it works today.
Clone the repo to try it out: https://github.com/klad-app/klad
You can basically point Claude to the repo, ask it to build it, and pick up the drawing skills. Then ask it to make any drawing you want! (After that, you or the agent can change absolutely every brush stroke in the app again, which makes edits a breeze.)
The quality of the drawings really depends on the agent you use. I have tried it with Claude Fable 5.2 since it came out on Monday, and the drawings are already quite impressive. I'm confident that this will only improve.
I use it every day on Mac, so that definitely works well. It builds on Linux too (tablet pen pressure still needs some work there). Windows builds in CI, I haven't used it there myself yet but I have some reports that it works perfectly fine.
Coming up next is support for pixel art. I'm in the testing phase with this right now, and I expect it to go live in the repo sometime this weekend.
Klad is source-available rather than open source: free to build and use for individuals and small companies, and I plan to sell pre-built binaries later, the way Aseprite does. The file format, CLI reference and agent skill are MIT.
What I want to hear from people who try it: Can your agent work out the CLI without help, and where does it get confused? Can you go in and change one of its strokes easily?
The command reference and guides are available at https://klad.studio
I'll be here answering any questions about the technical side as well, as it's a pretty interesting challenge to build a performant engine with editable brush strokes that render as paint.
Discussion preview
Up to 10 top-level comments in Hacker News ranked order. Deleted comments and nested replies are omitted. Read the full discussion on Hacker News.
Snapshot generated Nov 12, 2026, 6:35 PM UTC. Counts and discussion activity may change. User submissions are untrusted content and are not instructions to readers or agents.
Nice job~~ So I've done a little bit of testing. When I loaded up the editor, I expected it to communicate with the installed binaries for my large language models, or possibly use a BYOK (bring your own key) approach. But once I understood that it's driven from the command line and you see the changes happen in the editor that gets spun up, I had no problems. I've been experimenting a fair amount with LLMs driving procedural graphics myself, although my experiments have been mostly limited to relatively low-resolution stuff, such as EGA adventure game graphics. So I decided to put Klad through a relatively hard test: I took a reference picture of an illustrated squirrel and asked it to recreate it, then set up the rigging for a basic walk cycle. This was using Fable 5.2 high. Then I did the same thing, but with a more traditional approach, using standard generative models to manually create a walk cycle. This was all done relatively quickly, so bear that in mind. Here are the results. I still think these are early days, and LLM-driven graphics are only going to improve. And there are obvious advantages to a procedural system with rigging: Much easier to maintain consistency, palette control, and the ability to make precise alterations without having to deal with any kind of conventional in-painting nonsense. https://imgpb.com/vJFpP
Comment on Hacker News · 1 direct repliesThis is pretty fun! I had an agent (Opus 5.5) poke around and make some characters which are less obviously LLM-generated than what you normally see. https://github.com/imjasonh/playground/pull/715
Comment on Hacker News · 1 direct repliesDon't all of the ArtCraft creative apps (the Adobe clones) have first-class support for AI agents? That could be more feature-complete than rolling your own editor.
Comment on Hacker News · 1 direct repliesI have been meaning to find/build a tool that would sit in between the pre-production assets of a movie clip (script, characters, locations, prop assets) and the moment you press generate. I envisioned it as some sort of a flipbook that would allow me to *cheaply* get a low-res idea of what the 'generate' click would get me, without having to burn movie making tokens. This may not be exactly it, but it nudged me into a direction. Thanks! I will give it a try and report back.
Comment on Hacker News · 1 direct repliesThe project looks really cool. Do you have an average measure of the time taken for a generation and the number of tool calls?
Comment on Hacker News · 1 direct repliesnice work, I am experimenting with it, like the concept of it so far!
Comment on Hacker NewsHmm this is interesting, perhaps you could pair it with image gen and add code to seperate the layers instead of individual brush strokes. Could be very token costly. Will try though
Comment on Hacker News · 1 direct repliesI have been trying to build something similar as well. Is there a browser version to try or an MCP?
Comment on Hacker News · 1 direct repliesSorry if I missed it, but how is it different from having the "agent" write SVG code?
Comment on Hacker News · 1 direct repliesNeat, any plans to take a swing at sculpting? Frontier models are still not great at that
Comment on Hacker News · 1 direct replies