Sorted
Our own search engine and index. Clean results, cited answers, a reader view, and a keyless API for agents.
Used in: wAIve.online · Implementation
Our own search engine and index. Clean results, cited answers, a reader view, and a keyless API for agents.
Used in: wAIve.online · Implementation
One tiled workspace for terminals, SSH, browsers and AI agents. Goals that finish, and a dashboard for the whole fleet.
Used in: Hardware · Implementation
An open format for the web, written for models. Agents read pages with ~85% fewer tokens.
Used in: wAIve.online · wAIve Desktop · Sorted · The Engine
GPU tuning and control for the boxes we build and run.
Used in: Hardware
Thermal watchdog that keeps GPUs inside safe limits around the clock.
Used in: Hardware
See into every terminal session across the fleet at once. ClusterSpace's companion.
Benchmarks how to split models across GPUs. Showed that two smaller replicas can beat one big tensor-parallel split on the same cards.
Used in: The Engine · Hardware
Blind-test models side by side on your own prompts before you pick one.
Used in: Consulting
Graph pipelines with human approval gates and connectors.
Used in: Implementation
An autonomous app builder: give it a spec, get a working app.
Used in: Implementation
Apps built end to end by cadillac with zero human edits, kept as a public record.
Used in: Implementation
Tokenizer adaptation: fit a model's vocabulary to your domain.
Used in: Implementation
Pruning plus 4-bit quantization of a large coding model so it fits on hardware a business can own.
Used in: Hardware
Map a codebase in 3D. We use it to audit a client's code before we touch it.
Used in: Consulting
A terminal-first IDE for working next to agents.
Used in: Lab
Tell us what you're trying to do and what's in the way. If AI fits, we'll show you where. If it doesn't, we'll say that too.