testing

llm-echo 0.5a0 release adds a -o thinking 1 option to help test against LLM 0.32a0 and higher. This plugin provides a fake echo model for automated testing.

Opslane is a new tool that lets developers test Claude-generated code changes in a real browser by reading specs, building acceptance criteria, and running tests against a local dev server.

LangChain published a post explaining how they automated testing of their documentation to ensure technical accuracy for both humans and AI coding agents.

The article discusses the growing importance of reliability, security, and user protections as AI models become more capable and personalized.

Tophat by Shopify is a tool that lets you test mobile CI builds on any device without building locally.

Mitchell Hashimoto introduces Tripwire, a Zig library that injects failures to test error recovery paths, with zero runtime cost when disabled.

AutoDev is an AI-driven software development framework that automates complex engineering tasks, such as code and test generation, within a secure Docker environment. It achieves high performance on the HumanEval dataset by enabling autonomous planning and execution of intricate software engineering tasks.

This GitHub repository offers a boilerplate project for GenLayer, featuring an example intelligent contract with LLM integration, including tests, linting, and a Next.js frontend.

Laura Modiano of OpenAI France shares insights on what great AI founders do differently: continuously test, listen to customers, iterate quickly, and treat AI as core to solving real problems rather than just a strategy.

Insomnia is an open-source, cross-platform API client for GraphQL, REST, WebSockets, SSE, gRPC and other HTTP protocols, offering local, Git, and cloud sync storage options.

Puppeteer is a JavaScript library that provides a high-level API to control Chrome/Chromium over the DevTools Protocol, commonly used for browser automation, web scraping, and testing.

Cypress is a fast, easy, and reliable end-to-end testing framework for anything that runs in a browser, available as an open-source project on GitHub.

pytest is a mature Python testing framework that makes it easy to write simple tests while scaling to support complex functional testing for applications and libraries.