Havuz

Fresh, throwaway Windows machines for testing your apps: an MCP server and CLI that automate Windows Sandbox

Blocks Claude Code and Codex from ending a turn when code changed and no test passed after the last change.

:dog: The open-source Gauge CLI. Hillclimb your Skills, CLI, SDK, MCP, API, or Docs to make something agents want.

Does the model pick the right tool? Tool-routing tests for your MCP server: run them on Claude and OpenAI models, see where each request lan

Claude Code plugin: quit babysitting Claude. Make it check its own work.

Simulator-free, headless SwiftUI checks for AI coding agents: render screens as accessibility trees and hot-reload views in ~2 s, without th

Make AI-written code production-ready, with proof. Agent skill for Claude Code, Codex, GitHub Copilot & Gemini CLI: locks behavior, finds bu

Your coding agent says done. Show the receipt. Evidence-first workflows, practical skills, and plugins for Claude Code and Codex.

See what your coding agent actually did. A desktop pal and notch for Claude Code, Codex, Cursor, Gemini CLI and any agent: test results read

Behavior-guardrail hooks for Claude Code: test-tampering + outbound-action guards

Agent Factory is an open-source studio for building, editing and chatting with AI agents. You build them from simple nodes: LLM calls, HTTP

Rebuild a local twin of your app on every push, replay approved business journeys, and report a GitHub check.

CI regression gate for MCP servers: run a golden set of tool calls, diff against a baseline, fail the build when outputs get worse

Best AI QA Evidence Recorder MCP Server for Automated Testing 2026

Agent Dispatcher, Claude Code ve Codex için görevle ilgili kod bağlamını bulup uzman yönergeleri ve doğrulama adımlarıyla sunar.

Neden yükseliyor · 9 günlük yaşında 52 yıldız ve 108 commit dikkat çekiyor; ancak farklı yazar sayısı 1. Bu, yoğun geliştirme ve erken ilgi gösterir, bağımsız benimseme veya olgunluk kanıtı değildir.

An agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.

A skill to stop your coding agent from telling you it works when the diff says otherwise.

gap-trap, coding agent kullanan repolara projeye özel kalite kuralları ve bu kuralları CI veya test sürecinde denetleyen gate'ler ekleyen bir agent skill'dir.

Neden yükseliyor · 14 günde 180 yıldız ve son 28 günde 34 commit, yeni projeye yönelik belirgin ilgiyi ve geliştirme hareketliliğini gösteriyor. Ancak proje çok genç ve farklı yazar sayısı 2; bu veriler yaygın benimsemeyi veya uzun vadeli sürdürülebilirliği kanıtlamıyor.

Redpen makes coding agents prove they are actually done.

A faster drop-in replacement for the Firebase Local Emulator Suite: keep your firebase.json, SDKs and ports, and get 40× faster writes, 10×

Generates a test suite from acceptance criteria, then converges code against it with an agent that never sees those criteria.

Verifiable multi-agent patch evaluation infrastructure

Git for your test database. Snapshot the databases behind a system under test, break them, put them back in seconds, and read their logs bes

Click does not replace Nx, Bazel, pytest, or Jest. It sits above existing verification tools and manages which verification evidence remains

EvalForge, AI evaluation sonuçlarını baseline karşılaştırmaları ve CI quality gate’leriyle değerlendirip standart rapor formatlarında yayımlar.

Neden yükseliyor · RAG evaluation sonuçlarını CI’da denetlenebilir kanıta ve release gate’lerine bağlama ihtiyacına odaklanıyor; repo 34 günde 211 yıldız almış. Ancak README bağımsız doğrulanmış downstream benimsemenin henüz bulunmadığını belirtiyor ve son 28 günde katkı tek yazardan gelmiş; ilginin gerçek kullanımın kanıtı olduğu söylenemez.

Architectural linting for Swift developers and coding agents

skilled: open-source agent skill evaluation CLI and MCP server for Codex and Claude Code. Test skills, detect regressions, and improve with

Behavioral testing for AI agents.

Keep your sensitive credentials out of the agents you build and the coding agent you use. Test any agent with planted fake keys, or see whic

Deterministic Wasm sandbox + dual-target C runtime for AI-in-the-loop embedded firmware — from ESP32 down to sub-$1 8-bit MCUs

AI-native HL7 v2 toolkit with generation, validation, HL7→FHIR conversion, MCP & Claude Code integration. Bringing healthcare interoperabil

Evidence-driven production readiness checklist for shipping web applications with confidence

ARTEMIS, doğal dil talimatlarını Android cihazlarda çalışan otomasyon ve test akışlarına dönüştüren bir araçtır.

Neden yükseliyor · 45 günde 10.390 yıldız ve son 28 günde 72 commit belirgin ilgi ve geliştirme aktivitesine işaret ediyor. Doğal dil tabanlı cihaz otomasyonunu MCP ile AI coding assistant'lara bağlaması, test ekipleri için güncel ve görünür bir kullanım alanı sunuyor. Ancak son 28 gündeki farklı yazar sayısının 2 olması, aktivitenin geniş bir katkıcı tabanına yayıldığını göstermiyor.

rook by TestMu AI: Agent Assurance from the terminal. Test how your AI agents actually behave across workflows, tools, and actions, and catc

Git-based test distillation for Codex agents: catch aggressively, commit reluctantly

Regression testing and configuration sweeps for RAG pipelines, with the statistics to know whether a change actually helped.

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.

Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-bound

EvalPort — The Open LLM Evaluation Standard. Portable test cases, graders, suites, and results across DeepEval, Promptfoo, Inspect AI, and m

Engineering-first OpenAI Codex guide: 14 modules, 9 installable skills, reproducible benchmarks, testing, review, orchestration, and a Livin

Self-hosted OpenAI-compatible mock server — test your LLM integrations without exposing your API key. By Axium.

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit p

🐱 Knocks over your AI agent's "done" claims with hidden retests, mutation gates, and executable acceptance contracts for Java. If it's hollo

Local API simulation and test evidence for AI-assisted development.

Snapshot testing for LLM apps and agents, built to run locally and block regressions in CI.

Skills for your skills. Create, test, audit, package, and visualize Agent Skill libraries—locally.

Claude Code skills that turn an AI agent into a meticulous QA engineer. Evidence or it didn't happen.

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Local-first repo maps for coding agents—ranked files, test routes, risks, CLI/MCP/GitHub Action, and public GitHub URLs.

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