Search awesome repositories

Open-source simulation harness for testing AI agents. Simulate LLM and tool calls to test edge cases, failure paths, and agent logic without live API calls.

Standalone MCP tools for browser scanning, page inspection, and Playwright reproduction. Local workflow with no QualityMax account required.

Enable and disable tests directly from a Google Spreadsheet — no code changes required.

Assertions for non-deterministic AI text. Drop into pytest, get a Trust Score + HTML report. Free-first: rules, local embeddings, then your own LLM judge.

A CI gate for testing AI prompts and preventing regressions.

Drive an iOS simulator over HTTP. 479 lines of Swift, no WebDriverAgent.

Vision-enabled AI steps for Playwright tests. Bring your own LLM: OpenAI, Claude, Gemini or TestChimp.

A library that records a program's external inputs — database, HTTP, clock, randomness — and replays them, so any past run can be reproduced and debugged exactly.

Catch silent failures in agent workflows by verifying real system state

Valid, invalid, and edge-case JSON test cases for parsers, validators, editors, APIs, syntax highlighting, and error handling.

VertaaUX CLI — UX, accessibility, and conversion audits from the terminal (npm: @vertaaux/cli)

Postal code formats, validation regexes and 9,000 real sample codes for 31 countries. Every regex verified against the samples in CI. Zero dependencies.