I got laid off at the end of April and have been building my own personal dream tool since, it's a skeuomorphic carpentry simulator with an agent MCP. You start with real wood specs and a shop full of miter saws, router tables, table saws and the like. Think of it like Sketchup but no extruding rectangles.
It's been really fun to build with. Agents can create parametric procedures so e.g. stick framing becomes a simple function call for the next agent, building a flywheel. There is full agent-human parity in every surface, so there is a human UI for the procedures too.
Every operation is yaml, so agents pick it up pretty quickly. Agents can also file feature requests when they reach for a tool that doesn't exist. You can export to 3d printing files, video walk-through, step files, get a BOM and a cut plan, view your project in life-size with AR. There is a notion-like interface for authoring build guides... a lot going on. If you're a woodworker/software engineer you might enjoy it.
You can add the MCP to your agent of choice, send a picture, description, sketch or whatever; say "build this with Sawdust"
Love it, I had a similar but probably worse idea a few years back while woodworking. I agree the issue with essentially all CAD and sketchup etc is it forces you to work with primitives that are different from your real world ones. Extruding shapes as you said, instead of actually milling lumber and working in common known dimensions.
I also suspect there’s a fairly finite number of sane join primitives, you can have rabbets, dados, dominos, dovetails, pocket screws, etc. These could be experimented with digitally against an existing design. And your tool availability could determine what you can do.
And of course cut order and assembly is just a DAG and can be generated from geometric constraints of the actual design.
> I also suspect there’s a fairly finite number of sane join primitives, you can have rabbets, dados, dominos, dovetails, pocket screws, etc. These could be experimented with digitally against an existing design. And your tool availability could determine what you can do.
> And of course cut order and assembly is just a DAG and can be generated from geometric constraints of the actual design.
That's exactly it! It's a well-constrained space, and some amazing utility falls out as a consequence of using real-world materials and operations instead of cad-native primitives.
Have been building something non-CAD too in the space which is also aligned with carpentry. This looks really neat and can't believe how similar the functionality is. Would be great to chat!
Shopspec looks very cool! Love to see people building in this direction, we have at least validated for each other that the demand for a tool like this has a minimum bound of at least 2.
Cool project. A couple of years ago I was gifted "One-Plank Woodworking Projects" by Andy Standing for Christmas (which is great). It's a book of plans for things you can build with, obviously, one standard plank of wood. That might be a decent addition to the filters: rather than project type or tools available, what wood does the user has to hand.
Very cool! I was just today thinking I should have an AI help me design a new piece of furniture I've been thinking about, and send it off to a CNC shop.
The MCP server seems to have a bug. The tool list flashes for a second in Claude Desktop, but then immediately states "This connector has no tools available." and the error "Couldn’t reload tools from the server." when I try to refresh it.
Thanks for reporting the issue, it should be fixed now. Make sure to fully remove and then re-connect the MCP, and let me know what you think! If you like you can describe what you're building here and I'll make a demo of how I would prompt it.
Thanks for the kind words! NOVC [0] is kind of like "BPA Free" for saas, in my case it's a pledge that this software will remain indie and founder-led and not be subject to enshittification pressures that can come from taking certain types of investment.
I spent the last 5 years working at a bn+ valuation YC fintech; I naturally started to apply to YC with this project, but kept feeling internal pressure to make it something different from my vision in order to get to that bn+ unicorn status. Not every cool idea needs to corner an industry, ya know? I'd rather build this tool for 100 people like me and not gate a bunch of features behind paywalls. I live off-grid on acerage in Hawaii and paid off my mortgage and car loan, so my income needs are low. It would be nice to replace that 6 figure SV income one day, but I have a young family. There are different kinds of wealth, ya know?
This sounds a lot like a project I’ve started a few times and never made it far with. I called it woodlang. It was the idea of CAD but rather than designing the shape and figuring how to make it that shape, you specify a series of shop operations like blender geometry nodes.
This was all pre AI. Super impressive that you’ve made something awesome. I’ll try it out tonight
I keep seeing this word. Every time, I have to look it up; I marvel at the fact that we have such a cool word describing a complex but interesting topic; and apparently forget it again. And then I never find a situation where I can use it.
I don’t say this lightly, and confess I haven’t dug in very deeply yet, but this is one of the most hot shit uses of ML I think I’ve stumbled across yet.
If this does what I think it does (and I confess I’m a goddamn idiot still when it comes to anything involving ‘agentic’) this is honestly pretty damn amazing.
That's pretty cool. I built a barn door on rollers (some suspending it, some rolling on a concrete floor) last year and this would have certainly aided in visualising where I was going with it.
This is actually the source of the project's name, "know your project, down to the sawdust" -- Blade kerf is fully accounted for, the dimension itself is a property of each tool that can make a cut, so you can configure your own custom blade widths as needed. Off-cuts are always kept, unless explicitly discarded in the burn barrel. Project yield is also calculated, so you can spot an issue right away if you're doing something inefficient.
SI units are intended to be supported, but I am unfamiliar with commonly-available wood sizes in non-US markets so it is thoroughly untested and likely a bit of a disaster. Bug reports are appreciated and can be filed by clicking the lightbulb in the chat window or asking an agent to file it via the MCP.
I recently added a chisel and hand saw tool and started working on adding more complex joinery types. Right now any of the frontier models can easily handle half laps and pocket jig miters and the like. You can chat with the model and have it develop a procedure for any kind of joinery if you give it the right resources, if you do so I would love it if you ask the agent to nominate it as a community procedure.
I wanted to build a bed frame recently and imagined software where I could choose lumber from a list and visually assemble the bed frame in the software how I see fit, choose stains, flourishes - then go order the wood and have it cut. At that point it's like taking home an IKEA bed, except of way higher quality materials and to your exact design spec.
So
> Real SKUs, a real BOM you can send to any lumberyard; understand exactly what you need down to the last nail.
Is especially interesting, it sounds like you could basically do that with this software.
Turning the woodworking process into code to be automated by an LLM is pretty ambitious, and is the part I am most skeptical about. Of course, if you get that right (plus adoption) it would be unbelievably huge.
I have a parametric bed frame procedure already! It's demoed in an example project here https://sawdust.diy/share/60d515eb-ca3f-559e-994f-56164dd1fc... click 'open the workshop view' to see the full UI, make a new one using the bed frame procedure in the procedure tab (or add MCP and ask the agent to use the procedure).
And you can customize it beyond the existing design by asking an agent to modify it, e.g. "let's use walnut 4x4s and 2x4 slats", "I don't like how the corners come together, can we make it more like traditional joinery?" Also, staining is a supported procedure (it's very useful for e.g. coloring geodesic dome struts by strut type), you can just ask the agent to stain the pieces with whichever color you like, I'm sure you could even use a named stain you want to use like "Minwax Dark Oak" and get something pretty close.
Looks really good!
Do you have plans to add vr support to it? The ar button didn't work on my phone so I could not try it.
A couple of years ago I did a small woodworking project and used my vr headset do do the design. It was really fun to iterate on the piece in 3d space, but the software i used was not made for that so some actions were rather tedious. An agent, with voice support for the actions that are not fun to do with vr controllers, would make it awesome.
Try using the export drop down menu ios/android specific AR links, that will download a file you can open natively on-device. I will debug the 'view in ar' button today, thank you for the report.
>A couple of years ago I did a small woodworking project and used my vr headset do do the design. It was really fun to iterate on the piece in 3d space, but the software i used was not made for that so some actions were rather tedious. An agent, with voice support for the actions that are not fun to do with vr controllers, would make it awesome.
Yes! I played with a SketchUp VR extension a few years ago and it was so close to cool, but in reality practically useless because of poor controls. I lack VR hardware right now, but am building with that surface in mind.
It's been really fun to build with. Agents can create parametric procedures so e.g. stick framing becomes a simple function call for the next agent, building a flywheel. There is full agent-human parity in every surface, so there is a human UI for the procedures too.
Every operation is yaml, so agents pick it up pretty quickly. Agents can also file feature requests when they reach for a tool that doesn't exist. You can export to 3d printing files, video walk-through, step files, get a BOM and a cut plan, view your project in life-size with AR. There is a notion-like interface for authoring build guides... a lot going on. If you're a woodworker/software engineer you might enjoy it.
You can add the MCP to your agent of choice, send a picture, description, sketch or whatever; say "build this with Sawdust"
https://sawdust.diy