Building the loom singularity. 8PecVcCGs2HphgU5vxoWfqe4XTojaN2LWdy4FvZzpump
within multiverse generators
Joined August 2026
- Tweets49
- Following1
- Followers517
- Likes2
Pinned Tweet
Building the Loom singularity.
Universal Weave is a project to build the foundation for a more powerful way of interacting with AI models: The Loom.
We have working prototypes for all 6 of the planned graph views, along with working document migration from the old application implementation that we're rewriting using universal-weave.
We plan on implementing LLM text generation next, followed by beginning initial user testing.
However, due to unexpected circumstances which arose after our last update, development may be slower than normal this month. As a result of this development slowdown, we may not be able to deliver weekly progress updates every week.
Universal Weave retweeted
when it comes to the loom stuff:
i pushed myself way too far and i need a break. my health issues are slowing down progress substantially and it's only going to get worse the more i try and push through it.
i give up on weekly progress updates, but i haven't given up on the project. i'll try and still post development updates occasionally, whenever i've done enough for it to be worth posting an update about.
This quoted post is unavailable.
So far, we have prototype versions of 5 of the 6 planned graph views, along with a document metadata viewer.
We plan on prototyping a text editing view next, and once all prototypes are completed, we plan on implementing LLM text generation into the test application.
We've made substantial progress on building UI components, and along the way, we published a few minor updates to the Universal Weave library to improve developer experience.
At our current rate of progress, we believe that we can accomplish the following before the end of October:
1. A library containing core Universal Weave UI components which can be used to develop any Loom implementation.
2. A library which builds upon Universal Weave to provide useful building blocks for developing Looms which work with LLM-generated content.
3. A fully-featured open-source Loom implementation for completion-style ("base model") LLMs built upon items 1 and 2. This will act as both a demonstration of what can be accomplished using the Universal Weave ecosystem, and as a useful reference for other Loom developers.
Starting next Friday, we'll aim to publish weekly progress updates from now on.
apologies for being a bit less active recently
i’ve been traveling down to SF recently and discussing Looms with basically anyone who’s interested (AI researchers, journalists, everyday people, etc) so that i can get a better idea of what this project’s future should look like
the rate of development will pick up substantially next week, and i have a lot of ambitious plans that i’d like to share once the current UI work is finished.
We have a functional workbench and we're now beginning the development of Loom UI components.
We're currently working towards building a UI workbench, where we'll evaluate UI component designs when used within a larger application (we're aiming to have our test application be representative of the most common Loom use cases) so that we can get meaningful user feedback.
Once we've settled on the design of our UI components, we'll turn them into a library that anyone can use.
We're currently working towards building a UI workbench, where we'll evaluate UI component designs when used within a larger application (we're aiming to have our test application be representative of the most common Loom use cases) so that we can get meaningful user feedback.
Once we've settled on the design of our UI components, we'll turn them into a library that anyone can use.
Universal Weave retweeted
This is where @universalweave starts becoming much easier to explain.
The graphing is stable, the text layer is in, and now @transkatgirl can move from building the foundation to making it actually easy for other devs to use.
UI widgets, inference backends, and everything else needed to build a Loom without spending weeks making every piece from scratch.
@transkatgirl will also build a full Loom for base models using these same libraries, so we’ll get to see the whole ecosystem working together in a real product.
The plan was never to build one app and stop there. It was to make Looms easier for anyone to build.
Now $weave getting to that part.
We've added a text manipulation layer to universal-weave, allowing developers to make Loom implementations where editing the weave can be as intuitive as editing text.
This update marks the end of stage one of development. The underlying algorithms are solid, and it's time to build what comes next.
During stage two, we'll create libraries which build upon universal-weave to offer polished implementations of every component a Loom developer might need, ranging from UI widgets to AI inference backends.
Our goal is to empower developers to build polished Loom implementations in hours instead of weeks.
Along the way, we'll be using these libraries to build our most ambitious demo yet: A fully-featured Loom for base model LLMs built on top of the Universal Weave ecosystem.
And, of course, we have even more planned after that.
We've added a text manipulation layer to universal-weave, allowing developers to make Loom implementations where editing the weave can be as intuitive as editing text.
This update marks the end of stage one of development. The underlying algorithms are solid, and it's time to build what comes next.
During stage two, we'll create libraries which build upon universal-weave to offer polished implementations of every component a Loom developer might need, ranging from UI widgets to AI inference backends.
Our goal is to empower developers to build polished Loom implementations in hours instead of weeks.
Along the way, we'll be using these libraries to build our most ambitious demo yet: A fully-featured Loom for base model LLMs built on top of the Universal Weave ecosystem.
And, of course, we have even more planned after that.
The universal-weave text manipulation layer has been finished, and we're now working on updating the demo to properly incorporate it. We expect the updated demo to be ready by Friday.
We've decided to include the text manipulation layer within universal-weave itself. It will be added in the 0.6.0 update, which we plan on releasing within the next 1-2 weeks.
We're currently aiming to get universal-weave 0.5.0 (the update which will stabilize our graphing implementation) published by Sept 5th.
After it's published, our focus will turn towards developing a text manipulation layer which will allow developers using universal-weave to make editing weaves as intuitive as editing a normal text document.
This layer will be co-developed with additional universal-weave 0.5.x releases, which will further optimize the core of universal-weave to ensure it performs well even when editing very large documents.
Universal Weave retweeted
Kat said she was aiming to ship @universalweave 0.5.0 by September 5th and she shipped it.
I went through the release notes and this is much more than a version bump.
github.com/transkatgirl/univ…
Graph layout is now built directly into universal-weave. Developers can use the built-in implementation or build their own through the new Layouter trait. Bézier curve fitting is included, the legacy DependentWeave format is still supported, and a huge amount of the core has been cleaned up and optimized.
Basically, the graphing work @transkatgirl has been grinding on for weeks is no longer just progress sitting in commits. It is now a published release that other developers can actually build with.
And now the work moves toward the text manipulation layer.
That is the part that can make all of this feel normal to the user. You should not need to understand trees or DAGs just to use a Loom. Editing a Weave should eventually feel as natural as editing a regular text document, while all the branching and structure happens underneath.
0.5.0 puts the graph foundation in place.
The next releases start making that foundation easier to build real products on top of.
$weave
We're currently aiming to get universal-weave 0.5.0 (the update which will stabilize our graphing implementation) published by Sept 5th.
After it's published, our focus will turn towards developing a text manipulation layer which will allow developers using universal-weave to make editing weaves as intuitive as editing a normal text document.
This layer will be co-developed with additional universal-weave 0.5.x releases, which will further optimize the core of universal-weave to ensure it performs well even when editing very large documents.
When we said we were making building blocks for any Loom, we meant any.
universal-weave can run anywhere, including on devices with limited capabilities. Today, we've put that to the test by porting universal-weave's demo application to run on a microcontroller.
We'll soon be shipping universal-weave 0.5.0, which will make it easier to build Loom implementations that can run anywhere. We've ensuring our highly efficient graph layout algorithm is robust enough for developers to bet their projects on, and we're further optimizing the core of universal-weave so that it continues to perform even in extreme use cases.
But we're not done yet.
Once universal-weave 0.5.0 is published, we're going to begin creating libraries and frameworks which build upon it.
These libraries will include:
universal-weave UI components for the egui and ratatui UI frameworks
Multiplayer editing of universal-weave's DAG-based documents
Text manipulation layers for universal-weave which allow developers to make editing weaves as intuitive as editing text
We plan on using these libraries to build our most ambitious demo yet: A fully-featured Loom implementation built upon the universal-weave ecosystem which can meet the needs of both LLM researchers and creative writers.
(And we have more planned after that.)
Universal Weave retweeted
$weave has continued to hold within the $100K to $200K range while the market keeps jumping from one short-lived narrative to another.
Some people may look at that range and think nothing is happening.
I see a community that keeps showing up.
Every dip has tested conviction, yet we are still here. @transkatgirl is still building. @universalweave now has a working demo on a microcontroller, 0.5.0 is getting closer, and the roadmap is expanding from one core library into an entire ecosystem for builders.
The current range is not our destination.
It is the foundation we are building from.
And eventually, I do not want the $weave community to remain another coin chat that only becomes active when the chart is green.
This is a direction I have already discussed with @transkatgirl. Once @universalweave 0.5.0 is complete, we plan to begin turning the community into a hub where AI builders can meet, share what they are building on top of @universalweave, contribute ideas, exchange feedback, and help grow the ecosystem together.
More on that when the time is right.
Real communities are not created by 1 green candle. They are created by people who continue contributing, learning, sharing, and supporting the work when attention is elsewhere.
We cannot control when the market decides to notice.
What we can control is whether we are still here with something real when it does.
Our story is only getting started.
Universal Weave retweeted
This is the clearest roadmap @transkatgirl has shared so far.
@universalweave is no longer just an abstract idea hidden inside a Rust repository.
The demo has now been ported to a microcontroller, proving the core library can run even on highly limited hardware.
But the bigger reveal is what comes after 0.5.0:
UI components for egui and ratatui.
Multiplayer editing for DAG-based documents.
Text manipulation layers that make editing Weaves feel as intuitive as editing normal text.
Then all of those building blocks will come together in a fully-featured Loom designed for both LLM researchers and creative writers.
The core library is the foundation.
The ecosystem built on top of it is where people will finally experience what @universalweave makes possible.
@transkatgirl is not building one closed AI product.
She is building the layers other developers can use to create entirely new ways of interacting with AI.
For weeks, I have been telling people that $weave is still misunderstood.
Now people can finally see where all of this is going.
When we said we were making building blocks for any Loom, we meant any.
universal-weave can run anywhere, including on devices with limited capabilities. Today, we've put that to the test by porting universal-weave's demo application to run on a microcontroller.
We'll soon be shipping universal-weave 0.5.0, which will make it easier to build Loom implementations that can run anywhere. We've ensuring our highly efficient graph layout algorithm is robust enough for developers to bet their projects on, and we're further optimizing the core of universal-weave so that it continues to perform even in extreme use cases.
But we're not done yet.
Once universal-weave 0.5.0 is published, we're going to begin creating libraries and frameworks which build upon it.
These libraries will include:
universal-weave UI components for the egui and ratatui UI frameworks
Multiplayer editing of universal-weave's DAG-based documents
Text manipulation layers for universal-weave which allow developers to make editing weaves as intuitive as editing text
We plan on using these libraries to build our most ambitious demo yet: A fully-featured Loom implementation built upon the universal-weave ecosystem which can meet the needs of both LLM researchers and creative writers.
(And we have more planned after that.)