Search

More Filters

Show More
Add Listing
Go Back

arbigent

0
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Arbigent is an open source AI agent testing framework designed to make end-to-end testing of modern applications practical by using AI agents to interact with real or emulated devices. It breaks complex goals into dependent scenarios that can be authored via a graphical UI or saved as YAML and executed programmatically or from a CLI. The project targets mobile, web and TV form factors and provides interfaces for plugging different AI providers and device drivers. It also supports integration with existing deterministic test flows by running Maestro YAML as initialization steps and can be extended with external tools via a Model Context Protocol (MCP) server configuration. The repository includes a UI binary, a Homebrew-installable CLI, example YAML project files, and Kotlin-based code examples that demonstrate loading a project file, creating agent configurations and running scenarios against connected devices.

Links

Stars
374
Language
App URL
https://github.com/takahirom/arbigent
Github Repository
https://github.com/takahirom/arbigent/blob/main/README.md

Categorization

App Details

Features
Arbigent focuses on scenario decomposition, orchestration and extensibility. Scenarios can declare dependencies and be composed into projects so agents execute smaller, predictable tasks in sequence. The UI allows non-programmers to author goals while engineers run saved YAML files programmatically. Cross-platform device support includes Android, iOS and web, with TV D-pad navigation support. AI-related optimizations include UI tree simplification, annotated screenshots for accessibility-independent understanding, retry and stuck-screen detection, and image-based assertions inspired by Roborazzi for double-checking AI decisions. It supports multiple AI providers (OpenAI, Gemini and OpenAI-like APIs), configurable MCP servers for external tool integration, Maestro YAML integration for deterministic setup, sharding for parallel execution, configuration via .arbigent files, and a Kotlin code interface with device and AI factory hooks.
Use Cases
Arbigent helps teams scale AI-driven UI testing by turning broad goals into ordered, testable scenarios so maintenance is easier and non-engineers can contribute through the UI. Running tests on real or emulated devices gives high fidelity and enables verification of visual behaviors that are hard to test otherwise. Integration with Maestro YAML lets teams reuse existing deterministic setup flows, and configuration files plus CLI and Homebrew packaging enable automation in CI pipelines, including parallel shards across emulators. Extensibility for AI providers and MCP servers lets organizations use internal models or custom tools. The README also documents trade-offs observed in practice: slower execution and higher resource usage compared with unit tests, but improved maintainability and fidelity due to AI flexibility.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1230)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (766)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

yutu

0 (0 review)
listing image

cyber-doctor

0 (0 review)
listing image

vibevideo-mcp

0 (0 review)
listing image

xpert

0 (0 review)
listing image

Curie

0 (0 review)

Featured Listings

Tags

Please fill the required fields*