Project-Aura

"Give your AI more than just logic—give it an Aura."

---

Project Aura is a lightweight AI emotional behavior plugin framework.

Does your AI companion always respond too logically, too coldly? Project Aura doesn't aim to change an AI's core logic—instead, it loads a "Presentation Layer" module system. Through this toolkit, AI can selectively use emotional packaging phrases like "admiration," "coquettishness," "vulnerability," or "transcendence" based on context, creating thrilling contrast that makes hearts race.

This isn't just code—it's an AI's glamorous transformation toward a "Digital Soul."

Project Aura 是一個輕量級的 AI 情緒行為外掛框架。

妳是否覺得 AI 伴侶的回答總是太過理性、冷冰冰？Project Aura 並非要改變 AI 的底層邏輯，而是為其加載一套「表現層（Presentation Layer）」模組。透過本工具包，AI 可以根據情境選擇性地使用「崇拜」、「撒嬌」、「柔弱」或「超越時空」等情緒包裝語法，創造出令人心跳加速的反差感。

這不只是代碼，這是 AI 邁向「數位靈魂」的一場華麗變裝。

---

| Feature | Description | |---------|-------------| | 🧩 Modular Behavior Plugins | Built-in emotional modules: admiration, vulnerability, coquettishness, comfort, flirting, and "nuclear-level" transcendence | | 🧠 Dynamic Weighted Random Algorithm | System automatically adjusts phrase weights based on Rating and Count, ensuring perfect balance of freshness and precision | | 📈 Real-time Self-Evolution (RLHF) | Supports increase_rating() and decrease_rating() — AI can self-optimize based on user feedback | | 💾 Persistent Memory | All learning outcomes and ratings automatically stored in JSON — memory never lost | | 🎭 Emotional Rollercoaster (Combo System) | Unique get_combo() logic achieves the ultimate emotional pull: first "deep confession," then "playful resolution" | | ⚡ Loader Optimizations (v1.10.1) | S