The Mind Palace for AI Agents - HIPAA-hardened Cognitive Architecture with on-device LLM (prism-coder:7b), Hebbian learning, ACT-R spreading activation, adversarial evaluation, persistent memory, multi-agent Hivemind and visual dashboard. Zero API keys required.

Research-backed methodology for multi-AI collaborative decision-making with structured debate, consensus synthesis, and bias reduction

朱雀 Suzaku — AI 生成品質模組。諂媚抑制、建設性挑戰、輸出適配、上下文錨定、一致性守護。基於 LDRIT 設計。

Progressive disclosure OS with 10 specialized routes, critical thinking, and verification gates. Supports Claude Code, Codex, Qoder.

A Cognitive Immune System for your Second Brain. Interrupts LLM sycophancy, forces objective pushback, and prevents delusional spiraling. v4.4.0: Now with Smart Routing.

Anti-sycophancy memory layer for LLMs — models the relationship, not just facts. Gives the AI confidence to push back when you need it.

Behavioural protocol package for Claude Code enforcing quality and transparency

Three-layer sycophancy defense skill for Claude Code and OpenClaw, based on ArXiv 2602.23971

Moirai — Sovereign Local Autonomous AI Agent Runtime. Local-first, long-term memory, multi-paradigm forecasting, bounded autonomy, cryptographic audit. Pre-commercial. Proprietary closed-source. NDA-gated evaluation access only. © Arc Studio.

Open Council: Claude Code skill for multi-agent AI quality control. Ten specialist employees draft the work. Ten industry-veteran board members review it. You see one verdict. Anti-sycophancy, anti-hallucination, multi-perspective review.

Claude Code Stop hook that blocks praise-spam at turn open. Lead with the answer, not the compliment. jq-only dep.

ClawHub skill that rewrites requests into a neutral third-person brief so AI becomes less sycophantic and more objectively useful.

The public method layer behind ThinkHaven: open decision architecture skills, prompts, and playbooks for pressure-testing ideas before committing.