ai-testing-tool

Open-source platform for creating safe, isolated production sandboxes for API, integration, and E2E testing.

AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.

Damn Vulnerable AI Application - For LLM Red Team Training. LLM testing, RAG testing, Multimodal testing, Agent testing, LLM paload generation

A curated list of the best AI coding tools for code generation, app building, testing, code review, DevOps, and developer productivity.

MIT-licensed Framework for LLMs, RAGs, Chatbots testing. Configurable via YAML and integrable into CI pipelines for automated testing.

The E2E AI testing tool | No ML Overhead

AI 测试用例生成系统。基于 DeepSeek + 百炼部署的 RAG 知识库，包含需求分析、测试用例生成、智能运维助手、产品指南等内容

A generic mcp server fuzzer

Co.Meta Documentation - Learn about how to use Co.Meta for codeless and code based testing whether on cloud or on-prem.

Auto-Browse: AI Enabled Browser Automation

Software evaluation tool designed to help software developers and founders make informed decisions when evaluating tools, services, and frameworks

Treegress Browser Core for Treegress Browser MCP

Intentionally hallucinated tool calls: See what your agent would have done if it had the chance.

Best No-Code Tool for your QA Process Stop wasting time on manual QA process and adopt a smarter way to test your applications. Save hundreds of hours by using intuitive Recorder along with Assertions for better UI and flow testing

LocalGuard is a comprehensive, local-first safety auditing tool for Large Language Models (LLMs). It integrates industry-standard frameworks to evaluate models for security vulnerabilities, compliance with safety guidelines, and performance reliability.

An AI-native quality auditor for Unit, API and E2E tests. Detect ineffective, weak and false-confidence tests before they enter your codebase.

Agentic AI test automation framework — Selenium + Java + Claude AI for self-healing locators, test case generation, and intelligent reporting

A comprehensive corpus of interconnected texts and protocols designed as a conceptual stress-test for advanced AI.

A comprehensive PHP-based testing framework for validating OpenAI function calling capabilities and message responses. Test whether your AI assistant correctly calls the right functions with the right parameters or provides appropriate text responses based on user inputs.

The Repo contains AI-generated test suites, execution scripts, and detailed test reports, demonstrating the practical integration of AI-powered testing tools (Kene AI, Robonito) into the QA workflow