Agent models read the screen and take actions: click, fill in forms, navigate pages and operate applications. They automate routine work where a system has no convenient API. Evaluate reliability on your own scenarios, hardware needs, the license and how to limit the agent's access to sensitive data.
Diffusion language models: text is written in blocks and then refined rather than word by word, which speeds up generation. LLaDA2.2 can edit what it has written and targets agents. LLaDA-Image is a separate product.
Fully open desktop agents: weights, data and training code. They work on Windows, macOS and Linux; the latest Qwen-CUA controls a computer with ordinary clicks and keystrokes.
An Ant Group family for finding elements on screen and completing tasks in phone and computer interfaces. UI-Venus-2 was specifically trained to refuse dangerous actions.
Models for agentic development: they build their own plan and scaffolding for a task and execute it in the terminal. Fine-tuned from Qwen 3.5 and Gemma 4; work with Claude Code, OpenHands and similar tools.
Small Microsoft models for working in the browser: they look at the page and click, type and scroll. Designed to run directly on a work computer without the cloud.
A pair of small Tencent models based on Qwen3 that pick the right skill for an AI agent for a given request: the embedding model finds candidates, the reranker chooses the best one.
A French model family for controlling a browser and computer: precisely finds the right element on screen and handles multi-step tasks. The latest Holo3 and 3.1 are open under Apache 2.0.
A lightweight model for working with interfaces: finds buttons and fields by description and performs actions on the web and on a phone. ShowUI-π can drag with the mouse.
Models for controlling phones and computers from the Mobile-Agent project: they work with Android, Windows, macOS and the browser; version 1.5 has a reasoning mode.
Meituan's computer-control agent, trained on a large number of simulated tasks in desktop software. It outputs clicks and keyboard input.
One of the first open models for controlling an interface from a screenshot; its successor, AutoGLM-Phone, works in Android smartphone apps.
Compact Alibaba models for working in smartphone and computer interfaces: they find elements and complete multi-step tasks. The small size allows running on an ordinary GPU.
A model that looks at a screenshot and controls the mouse and keyboard itself: clicks, fills in fields, navigates menus. The first generation and 1.5-7B are open; UI-TARS-2 weights were not released.
Salesforce models for function calling and agents: they pick the right tool and fill in its parameters. Strong on benchmarks, but the license is non-commercial.
Breaks a screenshot down into buttons, fields and icons with labels so a regular language model can understand and control the screen. It does not click itself; it serves as the agent's eyes.
An agent model that plans actions both in an interface (buttons on screen) and for a robot (arm movements). For now more of a research base than a finished product.
Fine-tuned Llama 3 and Qwen 2.5 models from Nexusflow. Athene-V2-Agent is specially trained for function calling and agent scenarios. Commercial use is prohibited.
An open model can run on your own server: data stays in-house, there is no per-request fee, and the model can be fine-tuned on your documents.
