MAI-UI inference and evaluation code
Published MAI-UI grounding and navigation-agent implementations with inference demos and evaluation scripts.
Source-reviewed research and assets tagged with Tool integration.
Membership follows reviewed tags; it does not establish a dependency between neighboring records. Dates preserve source precision. Annotations retain their original language.
Published MAI-UI grounding and navigation-agent implementations with inference demos and evaluation scripts.
Portable agent instructions and integration tooling for local or cloud phone control through mobilerun-core.
An MCP server exposing mobile accessibility snapshots, screenshots and device interactions across real devices, simulators and emulators.
A framework that combines screenshots and accessibility state with agent tools for mobile-device tasks through command-line and Python interfaces.
An Android accessibility service that exposes UI-element inspection, device-control interfaces and screen feedback to mobile automation agents.
A maintained continuation of SikuliX that locates on-screen targets with image matching and OCR, drives desktop or Android interfaces, and exposes scripting and optional MCP interfaces.
The OpenAgents browser-control component, connecting a Chrome extension to a web agent and local chat platform for navigating sites and completing interface tasks.
Evaluation adapters and training guidance for OpenMobile-2 across Android emulators and browser-rendered mobile simulation.
Open-source library for generalist agents acting on an operating system's web, terminals, files and third-party apps, with the FRIDAY assistant, which takes custom tools and self-learns Excel tasks.
MCP server that lets LLM clients drive Playwright browsers through structured accessibility snapshots instead of screenshots, with opt-in vision, PDF and devtools capabilities.
Spreadsheet automation agent for Windows/Excel, with benchmark assets and a separately released headless Ubuntu evaluation backend.
A web-agent framework that explores sites, synthesizes reusable interaction APIs and builds a skill library for later tasks.
Training, evaluation and integration tooling for dialogue-guided web agents, including Llama fine-tuning workflows and BrowserGym examples built around WebLINX.
A browser library that labels interactive elements and their boxes for visual prompting, preserving element mappings that automation code can use to execute selected actions.
A Windows MCP bridge exposing application, window, keyboard and mouse operations plus native UI-state inspection for agents.
Showing 121–136 of 136 resources.
Get full records and evidence through the topic export manifest. Source records can be passed to the standard RAG and citation exporters after cloning the catalog.