Desktop and mobile control with decision models

Zero-dependency Node library with MCP and ACP adapters adding Jev decisions and gated computer use beside any LLM agent.

Kotlin Android SDK where Jev or DeepSeek selects actions from on-screen controls and an accessibility service executes them.

Native macOS launcher and window manager that optionally uses Jev to match loose natural-language commands to known actions.

macOS bookkeeping clerk booking supplier invoices: Jev picks each click from a closed list; a deep model rewrites the playbook.

Standalone Android agent on Mobilerun where Jev picks every operation and target, with a live React studio, CLI and traces.

OneJev: open multimodal System One model (0.8B-27B) answering typed questions about screenshots, photos, video and text in one pass.

CLM-8B, a contrastively trained System One model that embeds states and actions separately, served behind a TypeSafe-compatible API.

706K-parameter Jev-style option scorer that rates fill, check, click or skip for each form element in one parallel pass.

Open Jev-style decision models with vision (Qwen3.5 4B/9B LoRA) serving Choice, Score and Noul on /v1/systemone.

Browser and macOS desktop agent for Pi where Jev picks each action from a structured text observation in a bounded loop.

10,000-sample multimodal benchmark for decision models that return full probability distributions over declared candidates.

Drives a phone with Jev choosing each action while the phone-use runtime executes it on iOS and Android.

macOS voice agent where Jev picks each step's operation and target control, escalating to an LLM agent when unsure.

X post by Aaron Levin describing a computer-use agent built on Jev, with claimed cost and speed advantages over a frontier LLM.

Cua's X announcement of CUA-S1, a family of small open System One models specialised for computer use, starting with form filling.

X post by a WebMCP benchmark author reporting Jev plus a small LLM solved 100% of tasks at about 112x lower model cost.