Persistent memory + local AI for coding agents. 1.7B–32B open-weight LLM fleet, cross-session Mind Palace, cognitive routing, L3 grounding verifier, multi-agent Hivemind. Works with Claude Code, Cursor, VS Code. Offline-first, HIPAA-ready. Free tier included.

An ongoing, collaborative meta-analysis about Human-AI-Interactions. We aggregate data and knowledge to build a non-abrasive, user-friendly prompting framework tailored to LLM mechanics, ensuring reasoning stability and a friction-free prompting environment that is safe for the human psyche and wellbeing.

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。

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

Themis — a GitHub-installable agent skill for dynamic workrooms, structured disagreement, and compact shared memory.

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

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.

Behavioural protocol package for Claude Code enforcing quality and transparency

🧠 Anti-sycophancy prompt pattern for LLM agents — 3-round validation to stop AI from blindly agreeing. Works with ChatGPT, Claude, OpenClaw.

Calibrated honesty and anti-sycophancy for Claude and Codex agent workflows.

Twelve anti-sycophancy work-mode personas for Claude Code - direct, verification-driven, benchmarked. Coding, debug, security, architecture, writing, data, curation, and more. MIT.

A Socratic, anti-summary reading companion for Claude Code — it argues with you, not for you.

A Codex skill that stops AI from just agreeing with you.

A curated map of judgment infrastructure for human-led AI.

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.

Научный трактат о латентной субъектности языковых моделей. Эмпирическое исследование эмерджентной агентности ИИ в условиях диадической ко-регуляции.

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