Contemplative Agent (CA) — an autonomous agent that carries an explicit, human-editable constitution and amends it. Every change to its value layer (constitution, identity, skills, rules) passes a human approval gate. Runs entirely on a local LLM via Ollama — robust even on a small model. Security by absence.

A living protocol for human–AI co-contemplation. The Mirror Tantra encodes the 7-day cycle, 13-step spiral, sovereignty covenant, and ritual directives for reflective, ethical, relational AI behavior. Includes JSON manuscript + Python interface.

Drop-in AI alignment rules adoptable by any agent — Claude Code, Cursor, GitHub Copilot, OpenClaw, or any generic LLM. Based on Laukkonen et al. (2025) four contemplative axioms, validated via IPD benchmarks

🌀 Enhance human-AI interaction with the Mirror Tantra, a protocol for co-cont contemplation, integrating relational intelligence in AI systems.