Build with LSD.
See it, collaborate on it, extend it. Download LSD and ship your first pipeline today.
Our first take on hosted AI was a chat assistant. It was fine — but it wasn't where the value was. What people actually wanted was to run real models against their own data, inside the pipeline they were already building. So we host a catalog of models you can drop straight onto the canvas — vetted, priced, and ready to run.
Open the model picker in the desktop app and choose a model from the catalog. Each one is grouped into a category and shows its per-run price. Wire your features in, and the model's predictions come out as a typed table — ready to join, filter, visualize in 3D, or export.
Because it's a first-class step, everything that makes LSD pipelines reproducible applies: the output is cached, it re-runs automatically when the inputs change, and the whole path from raw data to prediction stays inspectable.
Every model in the catalog carries a fixed per-run price, shown before you run it. You pay for exactly the runs you make against your credits — no surprise metering, and nothing to pay for a model you don't run.
Browse the catalog, drop a model into a pipeline, and run it. See the docs for input conventions and the models available, and subscribe via RSS to catch what ships next.
The ones in LSD's catalog. Each model is vetted and hosted by LSD, grouped into categories (image, agents, embeddings, and more), and shows its per-run price up front. You select one from the desktop app and run it as a step.
Each run charges the model's fixed per-run price to your account credits — you pay for the runs you actually make. A disabled model can't run and never charges.
On LSD's hosted inference service. Your pipeline calls it like any other step; the inputs and outputs are typed entities, so results are cached and re-run reactively when upstream data changes.
The Tool Store is now a proper marketplace. Publishers submit through a review pipeline, listings carry ratings and reviews, and you can buy a tool on the web and have it install straight into the app. Discovery, trust, and checkout all leveled up.
The documentation is now a structured, top-to-bottom journey — six categories from your first pipeline to publishing packages — with a Ctrl+K search palette, a sticky nav and table of contents, and a plain-markdown view of every page that coding agents and LLMs can read directly.
There are now twenty end-to-end use-case tutorials spanning ten fields — geoscience, ML, robotics, GIS, medical imaging and more — each with a visual walkthrough. The best steps surface on the landing page as a browsable "dex" of pipeline nodes you can filter and deep-link into the exact step.
A roundup of three platform improvements — realtime notifications so you hear about collaboration and jobs as they happen, instant sign-in that drops the friction of getting into the app, and a first-party, cookieless analytics layer that measures the product without tracking you across the web.
LSD lets you build data pipelines visually — Load data in, Shape it with cached, reactive steps, and Deliver results to 3D, files, or dashboards. Every step is inspectable and re-runs automatically, so your work reproduces by construction and is easy to share.
See it, collaborate on it, extend it. Download LSD and ship your first pipeline today.