Search Results for "desktop text"

PenEcho is an open-source shared canvas that makes handwriting, equations, diagrams, and spatial context part of an AI conversation. Users can draw with pressure-sensitive ink, erase, pan, zoom, type formatted text, and arrange ideas across a large virtual workspace. The application sends focused visual regions to an API, Codex CLI, or Claude CLI and converts model responses into editable canvas commands. AI output can include text, formulas, plots, mixed drawings, erasures, and declarative animations. Sparse tile rendering keeps the 20,000-by-20,000 logical canvas efficient without allocating one enormous bitmap. ...

MAI-UI is a cutting-edge open-source project that implements a family of foundation GUI (Graphical User Interface) agent models capable of interpreting natural language and performing real-world GUI navigation and control tasks across mobile and desktop environments. Developed by Tongyi-MAI (Alibaba’s research initiative), the MAI-UI models are multimodal agents trained to understand user instructions and corresponding screenshots, grounding those instructions to on-screen elements and generating sequences of GUI actions such as taps, swipes, text input, and system commands. Unlike traditional UI frameworks, MAI-UI emphasizes realistic deployment by supporting agent–user interaction (clarifying ambiguous instructions), integration with external tool APIs using MCP calls, and a device–cloud collaboration mechanism that dynamically routes computation to on-device or cloud models based on task state and privacy constraints.

OpenHuman is an open-source personal AI assistant built to operate as a daily-life agent rather than a simple chatbot. It focuses on a private, desktop-first experience with a friendly interface, onboarding flows, and a persistent assistant that can remember context over time. The project connects to common productivity tools, gathers fresh information from integrations, and organizes user knowledge into a local memory system. It also includes practical agent tools such as web search, web fetching, file access, coding utilities, voice input, text-to-speech, and model routing. ...

...This approach bypasses expensive vision-based models and provides faster, cheaper automation with fine-grained interaction capabilities (for example, tapping buttons, typing text, navigating screens).