On-device model
d1 decisions
An on-device decision provider built from LiquidAI’s d1-omni-600M. It generates no tokens: given bounded page state and screenshots, it returns a choice, a probability of yes, or an ordinal score.
Why it matters
Many agent steps are really questions with a few possible answers. Answering them with probabilities instead of generated text is faster, and a calibrated “I’m not sure” is safer than a confident guess.
How it runs
A bidirectional encoder with six full-attention layers, served in the browser through WebGPU (hardware WebGPU with buffer limits of at least 128 MiB). The browser build stores FP16 weights and computes in FP32; against the FP32 release it agrees on all 144 test decisions, with a largest probability difference of 0.010.
d1 page-state data also trains Compass VLD, which now takes priority for automatic decisions once it is downloaded.
Models
-
d1-browser-decision-fp32FP32 release, from LiquidAI d1-omni-600M 42 downloads · 0 likes -
d1-browser-decision-fp16FP16 weights for WebGPU in the browser 191 downloads · 0 likes
Caveats
- Experimental, and optional in WebBrain’s settings.
- No blog post covers d1 yet; these details come from WebBrain’s model documentation.