vision-llm
Eyes for AI coding agents 👁️ — render → perceive → report → fix → re-render. A machine-graded visual feedback loop (DOM/contrast/OCR-grounded + optional vision LLM) agents consume to self-correct before claiming done.
PyMidscene - Midscene.js 的 Python SDK 实现 | AI 驱动的自然语言 UI 自动化，告别选择器，用中文描述即可操作。与官方缓存格式完全兼容。
Audit French PEA (Plan d'Épargne en Actions) eligibility of ETFs by reading their KID with a vision LLM (Gemma 4 via Ollama Cloud). Pluggable LLM + KID source registry, versioned prompts, 13/13 eval baseline.
