AI can what?

THE SOFTWARE & AGENT ENVIRONMENT INDEX

Web software
& agent resources.

Explore 20 source-reviewed Web software, environment, and evaluation resources, with original code, author evidence, papers, and practical limits.

202 entries56 games / worlds35 websites111 appsSources reviewed · 2026-10-16

Explore the directory

Suggest a project ↗

This platform has 10 author-reported AI software showcases and 10 environment or evaluation resources. Platform tags can describe an application, environment target, or interface dataset; use the resource type to distinguish them.

Combine keywords; put an exact phrase in double quotes.

20 entriesSource review ≠ runtime verification
ProjectTypeUsePlatformEvidence / reviewed
AgentNet (OpenCUA)Dataset + benchmark

Cross-platform computer-use demonstrations from the OpenCUA project, accompanied by recording tools and an offline action-matching evaluator.

Apps TrainingEvaluation Windows, macOS, Linux, Web Original source ↗
Audio Step SequencerSoftware made with AI

An AI-generated browser drum sequencer with a sixteen-step grid, tempo and swing controls, saved patterns and WAV export code.

Apps Showcase Web Original source ↗
EffectCraftSoftware made with AI

An alpha Rust motion-graphics and compositing app that combines layers, keyframes and effects, with native project files and documented Lottie/media export.

Apps Showcase Windows, macOS, Linux, Web Original source ↗
FilmCraftSoftware made with AI

An alpha Rust video editor with a multitrack timeline, trimming, titles, color and audio controls, plus documented media-export and timeline-interchange paths.

Apps Showcase Windows, macOS, Linux, Web Original source ↗
GUI-WorldDataset + benchmark

A GUI video dataset and offline benchmark for understanding interface content, changes and operation sequences across desktop, mobile, web and XR recordings.

Apps TrainingEvaluation Web, macOS, Windows, iOS, Android Original source ↗
GUIAct (GUICourse)Dataset + benchmark

The released navigation component of GUICourse: screenshot/action data for single-step and multi-step website tasks and Android interactions.

Apps TrainingEvaluation Web, Android Original source ↗
LightCraftSoftware made with AI

An alpha Rust photo library and RAW developer with catalog organization, nondestructive adjustments, masking and image-export workflows.

Apps Showcase Windows, macOS, Linux, Web Original source ↗
OmniACTDataset + benchmark

A screenshot-to-action-program dataset pairing desktop and web task instructions with UI images, target annotations and reference PyAutoGUI scripts.

Apps TrainingEvaluation Web, macOS, Windows, Linux Original source ↗
Online WhiteboardSoftware made with AI

A generated browser drawing app with pen and eraser tools, color choices and PNG image export.

Apps Showcase Web Original source ↗
OS-Atlas DataDataset

A cross-platform GUI grounding pretraining corpus combining newly captured desktop/web interfaces with reused mobile and web datasets.

Apps Training Windows, macOS, Linux, Android, Web Original source ↗
OSWorld 2.0Environment + benchmark

A distinct 108-task computer-use benchmark for long-horizon workflows spanning Ubuntu desktop applications and web services.

Apps Evaluation Linux, Web Original source ↗
PdfCraftSoftware made with AI

An alpha Rust PDF workbench for viewing, searching, annotations, forms and page organization, with native applications and command-line tools.

Apps Showcase Windows, macOS, Linux, Web Original source ↗
PhotoCraftSoftware made with AI

An alpha Rust image editor with layered documents, masks, brushes, editable type, adjustments and PSD/PSB import and saving.

Apps Showcase Windows, macOS, Linux, Web Original source ↗
ScreenSpotDataset + benchmark

A screenshot-based GUI grounding benchmark that asks a model to locate the control named by an instruction across mobile, desktop and web interfaces.

Apps Evaluation Web, macOS, Windows, iOS, Android Original source ↗
TheAgentCompanyEnvironment + benchmark

A self-hosted simulated software company where agents use internal web services, files, code and conversations with simulated coworkers to complete workplace tasks.

Apps Evaluation Web Original source ↗
Tiny KanbanSoftware made with AI

A generated browser app for moving task cards between Todo, Doing and Done, with local persistence, search and work-in-progress limits.

Apps Showcase Web Original source ↗Browser observation recorded
VectorCraftSoftware made with AI

An alpha Rust vector editor with paths, shapes, text, layers and native/SVG/PDF document workflows, distributed as desktop and WebAssembly builds.

Apps Showcase Windows, macOS, Linux, Web Original source ↗
VibeTunnelSoftware made with AI

A terminal-session manager with a native Mac app and browser interface for viewing output and interacting with running shells remotely.

Apps Showcase macOS, Linux, Web Original source ↗
VideoGUIDataset + benchmark

Instructional-video GUI benchmark data for creative software, separating high-level planning, subtask planning and individual mouse/keyboard actions.

Apps Evaluation Windows, Web Original source ↗
WorldGUIDataset + benchmark

Desktop and web workflow benchmark data with varied starting states, plus a public Windows agent implementation for planning and self-correction.

Apps Evaluation Windows, Web Original source ↗

Software, environments, and benchmarks.

Showcases document software made with AI. Environments support interaction. Benchmarks define evaluation tasks; datasets provide training or evaluation material. Resource types and development provenance are labeled separately.

Follow every entry back to its evidence.

We record original links, review dates, and known limits. Demos and code belong to their upstream projects. Read our method ↗