Test and eval harness for LLM-generated UI. Samples N generations, renders in headless Chromium, checks fidelity + a11y + layout, LLM-as-judge scoring, regression gates for CI.

0 stars 0 forks 0 watchers TypeScript MIT License
accessibility ai-sdk axe-core bun ci evals gemini generative-ui gpt llm llm-as-judge llm-evaluation llmops openai playwright quality-assurance testing typescript ui-testing visual-regression
2 Open Issues Need Help Last updated: Jul 14, 2026

Open Issues Need Help

View All on GitHub
Publish to npm about 3 hours ago
good first issue

Test and eval harness for LLM-generated UI. Samples N generations, renders in headless Chromium, checks fidelity + a11y + layout, LLM-as-judge scoring, regression gates for CI.

TypeScript
#accessibility#ai-sdk#axe-core#bun#ci#evals#gemini#generative-ui#gpt#llm#llm-as-judge#llm-evaluation#llmops#openai#playwright#quality-assurance#testing#typescript#ui-testing#visual-regression
good first issue

Test and eval harness for LLM-generated UI. Samples N generations, renders in headless Chromium, checks fidelity + a11y + layout, LLM-as-judge scoring, regression gates for CI.

TypeScript
#accessibility#ai-sdk#axe-core#bun#ci#evals#gemini#generative-ui#gpt#llm#llm-as-judge#llm-evaluation#llmops#openai#playwright#quality-assurance#testing#typescript#ui-testing#visual-regression