LLM-backed site search that cites its sources or declines plainly. No-leak boundary, eval harness. Markdown → embed → retrieve → cited JSON.
-
Updated
Jun 27, 2026 - TypeScript
LLM-backed site search that cites its sources or declines plainly. No-leak boundary, eval harness. Markdown → embed → retrieve → cited JSON.
Grounded agentic legal RAG with deterministic orchestration, hybrid retrieval, answerability checks, citations, tracing, and offline evaluation.
AI-readable Markdown corpus and theory map for the Mekiki Framework T1–T3. Canonical scholarly sources are the paper DOIs.
Add a description, image, and links to the answerability topic page so that developers can more easily learn about it.
To associate your repository with the answerability topic, visit your repo's landing page and select "manage topics."