#testing

AI Agent Toolkit 2026: Smart Device Control for iOS & Android

Your coding agent says it works. Gopnik tries to prove it doesn't — against the code, the delivered revision, and the checks themselves.

Deterministic fake of the claude and codex CLIs. Test hooks and orchestrator integrations locally and in CI without an API key.

Black-box LiveKit voice agent testing: real WebRTC/SIP calls with an AI caller. Catch barge-in, noise, quiet-mic, and latency failures that text pytest misses. Forensic reports + MCP + lks CLI — no agent code changes.

Luciazero — make coding agents prove their work. Verification-first discipline for Claude Code + Codex CLI: 9-rule doctrine, 13 skills, risk-routed reviewer, fail-open hooks.

AI-powered codebase assertions. Write natural-language requirements in tests and let an AI agent inspect your project.

Audits what your Claude Code agent did against what it said — reads session logs and git, cites evidence, calls no model

A test & eval harness that makes an AI agent deterministic, testable, and observable — record/replay, trajectory evals, guardrails, traces

All-in-one Developer Studio & Desktop GUI for Bubble.io (DevOps, Schema, Dead Code Audit, AI Translation, Visual QA)

Checks whether a test-count claim is actually true - in a commit message, or in what your coding agent just told you. Runs the suite and compares. pytest, vitest, jest. Pre-commit hook, Claude Code plugin, or CLI. If no claim was made, it does nothing.

Deterministic governance and guardrails for autonomous AI coding agents. Features AST verification, evidence-based rule execution, and native MCP support for Antigravity and Claude Code.

Free local proof reports for AI-built apps and public PRs; $149 async outside proof audit.

AI Testing Agent

Turn failing pytest runs into structured repair reports: failure parsing, root-cause diagnosis, flaky detection, dry-run fix diffs, and an optional LLM layer. 把失败的 pytest 运行转化为结构化修复报告。

Claude Code QA agent with memory, plus a read-only MCP server (verdict-qa-mcp on PyPI): baseline → delta runs (NEW/REGRESSED), a fact harness so the model judges while the system measures, signed run history, flaky quarantine with expiry, and an exit-code release gate for CI. Ships six scored eval fixtures — misses published.

Behavioral fuzz-testing engine for AI agents — policy violations, tool-call verification, regression tests. Adapter #1: OpenAI Agents SDK.

Browser acceptance checks for agent-built web apps. Zero-key starter, CLI, MCP and GitHub Action; inspect explicit assertions and reports.

AI agent skill for TestRail REST API - zero dependencies, security-friendly alternative to MCP servers

AI Quality Engineering framework for evaluating LLM and RAG applications using automated prompt testing, hallucination detection, and AI evaluation metrics.

Claude Code skills for genuine property-based testing: discovery workflow, anti-patterns, Hypothesis & beyond.

Evidence-first verification for AI coding agents — prove what changed, what was tested, and what passed.

🔭 Exploratory UI testing for AI coding agents, over MCP. Works with Claude Code, Cursor, VS Code, Codex, Gemini CLI and more: a structured view of a running web app, always-on oracles, a network-level write policy, cross-run memory and a gap-checked report.

CI/CD evaluation infrastructure for tool-using, multi-step AI agents

Pytest fixtures for the fakellm mock OpenAI/Anthropic server

QA testing performed for the AI-powered Biz Card Scanner mobile application covering functional testing, UI validation, navigation flow, and bug reporting.

Find Rust test-oracle gaps before mutation testing: static RIPR evidence for CI, editors, and agents.

Shared engineering rules, agent instructions, API standards, Laravel/Next.js patterns, testing rules, and reusable project checklists for all AI-powered portfolio systems.

Practice project migrating prose-based AI enforcement rules into real, blocking Claude Code hooks — covers PreToolUse guards, Stop-hook content verification, LibreOffice hang prevention, and robust pass/fail parsing, each with a working test suite.

Headless Atari ST/STF parity toolkit for LLMs, Codex, Claude Code, and Go tests

Expert Ruby Rails RSpec Skill Files 2026 for AI Coding Agents - Best GitHub About

AI-powered QA Automation platform for log analysis, AI test case generation, and professional bug report creation using FastAPI, React, and Google Gemini AI.

OpenAI uyumlu inference endpoint'lerini test etmek için çapraz platform betikler: chat, model keşfi, TTFT'li yük testi ve embeddings sağlık paketi (Bash · PowerShell · Python, bağımlılıksız)

Provider-neutral evaluation runner for command-line AI agents.

Make web UIs controllable by browser agents without brittle selectors.

Behavioral cross-agent testing for agent skills — run a skill on Claude Code and Codex and assert deterministic outcomes.

AI-powered Quality Engineering Platform built with FastAPI, React, PostgreSQL, and Docker for requirement analysis, API test generation, and automation failure analysis.

Debug any product by USING it (living the full user cycle, all features, like a picky user) instead of green tests. Start interview (Goal+Benchmark), two modes: Solo and Agentic+ (delegate fixes to agents). Claude Code skill.

A thin, CI-gated evaluation gate for RAG & LLM systems — golden set, band-based pass/warn/fail gates, LLM-judge or heuristic scorers. pip install raggate

Do your agent pipeline's own checks catch planted faults? Measured on LangGraph, CrewAI and AutoGen: median 16.7%. One prompt-level change takes it to 55.0%. Pre-registered spec, Apache-2.0 harness, every raw trace published.

Skill de Claude Code que audita si tus pruebas sabrían ponerse rojas. Instalable como plugin desde el marketplace. La misma herramienta que el repositorio hermano, empaquetada para que la use tu asistente.