Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
CUA-S1 (Cua)
Cua's family of small 'System 1' models for computer-use decisions (first profile: forms, Qwen3.5-4B adapters), plus a jev-use chooser in Cua Driver that can send closed-candidate choices to Jev or to S1.
github.com/trycua/cuaActive
trycua/cua (31k stars) pushed 2026-10-25, release cua-spaces-v0.16.0 the same day; CUA-S1 weights updated 2026-09-26. Show HN 2026-09-19 with 95 points. (checked 2026-10-25)
In The Jev ecosystem
Where it stands apart
- Which shared standard or format does it mainly build on? none of these (its own format or interface) (14% of 21 others)
- Which models answer its questions? Pick the first that applies. Jev or other models, your choice (14% of 21 others)
- What is the main thing it ships? model weights (19% of 21 others)
- Which question types does it handle? a subset or a different set (10% of 21 others)
- Does it train on Jev's outputs? (TypeSafe's customer agreement forbids using output to distill or build competing models.) it trains models, but not on Jev's outputs (21% of 19 others)
- Does it publish head-to-head numbers against Jev? benchmarks, but not against Jev (19% of 21 others)
What it shares with most of the community
- Is it actively maintained? active (62% of 21 others)
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (86% of 21 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? yes (52% of 21 others)
- Do you need an account to use it? no account (86% of 21 others)
- Who is it for? developers (95% of 21 others)
- Can you use it without a TypeSafe account? yes, no TypeSafe account involved (62% of 21 others)
- Are its answers typed values rather than generated text? (identity question) yes, typed answers only (67% of 21 others)
Nearest neighbors
- Laya 75% of 16 shared answers match
- Kev 69% of 16 shared answers match
- Gutsy 63% of 16 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-25 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) Source MIT; S1 adapters Apache-2.0; base model under its own license. | source 2026-10-25 |
| How is it mainly sustained? | company with a paid product, tier, or ads Cua sells hosted Cua Spaces. | source 2026-10-25 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes | source 2026-10-25 |
| Do you need an account to use it? | no account Local models; artifacts public on Hugging Face, download needs no token. | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | stands apart none of these (its own format or interface) Own cua.decision_choice_v1 format, with Jev adapters. | source 2026-10-26 |
| Which models answer its questions? Pick the first that applies. | stands apart Jev or other models, your choice jev-use can use Jev or the S1 model (--model s1). | source 2026-10-25 |
| What is the main thing it ships? | stands apart model weights Within a larger computer-use platform. | source 2026-10-25 |
| Which question types does it handle? | stands apart a subset or a different set Closed-candidate choice for UI actions. | source 2026-10-25 |
| Does it check whether its probabilities can be trusted? Pick the first that applies. | yes, it publishes calibration metrics (ECE, Brier, or similar) Model card reports ECE. | source 2026-10-25 |
| Where do the decisions run by default? | on your own hardware (CPU, Mac, or GPU) | source 2026-10-25 |
| Does it train on Jev's outputs? (TypeSafe's customer agreement forbids using output to distill or build competing models.) | stands apart it trains models, but not on Jev's outputs Synthetic GUI task data. | source 2026-10-25 |
| Can you use it without a TypeSafe account? | yes, no TypeSafe account involved | source 2026-10-25 |
| Are its answers typed values rather than generated text? (identity question) | yes, typed answers only | source 2026-10-25 |
| Does it publish head-to-head numbers against Jev? | stands apart benchmarks, but not against Jev | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/trycua/cua · read 2026-10-25
- GitHub · github.com/trycua/cua/blob/main/libs/cua-s1/MODEL_CARD.md · read 2026-10-25
- Web page · cua.ai · read 2026-10-25
RSS for this project · Its own release feed
Are you a maintainer? Claiming and correcting projects is coming soon.