Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and grounded calibration for Claude Code and beyond
Latest release v1.13.42 · 9 Sept 2026
3 files for Cursor, Claude Code, GitHub Copilot, Codex and OpenCode: cursorrules, empirica copilot-instructions.md, empirica AGENTS.md — 6,962 tokens loaded in every session.
.github/copilot-instructions.md A 4,732 tok AGENTS.md A 513 tok .cursorrules A 1,717 tok These files are EmpiricaAI/empirica's own configuration — they tell Cursor, Claude Code, GitHub Copilot, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.