ExAI — AI Assistant Plugin for Minecraft

ExAI brings an LLM-powered, in-game AI assistant to your Minecraft server. It answers player questions with a community-curated knowledge base, using RAG (vector retrieval + LLM) for grounded, server-specific replies. Everything happens inside a chest GUI — no command memorization required.

Features

• Chest GUI assistant — players talk to the AI through a clean menu, no chat spam.
• Public chat response — auto-replies to questions in public chat by keyword triggers (configurable, with cooldown).
• Knowledge base with review workflow — players submit Q&A via a written book → OP approves/rejects in GUI → approved entries enter the vector store.
• RAG retrieval — DashScope text-embedding-v3 (1024-dim) for semantic search; configurable similarity threshold.
• Reward system — Vault currency + custom item rewards for approved submissions.
• OP tools — chat history viewer, knowledge base editor, per-record edit-and-promote.
• Flexible storage — choose between MySQL or pure local YAML files via storage.type; zero database setup required for small servers.
• i18n — built-in zh_CN / en_US, hot-reloadable.
• LLM backend — OpenAI-compatible API (default Aliyun DashScope / Qwen, easy to swap to OpenAI, DeepSeek, etc.).

Commands & Permissions

Command Description /exai opengui Open the assistant GUI /exai question Send a question to a player (OP) /exai reload Reload config (OP) /exai help Show help Permission node: exai.op (knowledge review).

Quick Setup

1. Drop ExAI.jar into plugins/.
2. Start the server once → edit plugins/ExAI/config.yml:
3. Choose storage.type: yml (default, no DB) or mysql.
4. If mysql, fill in MySQL credentials.
5. Fill in your LLM API key (llm.apiKey).
6. Adjust assistant name / language / rewards.
7. (Optional) Edit plugins/ExAI/knowledge.yml to seed your knowledge base.
8. /exai reload.

Storage modes

• yml (default)
• mysql

Requirements

• Spigot/Paper 1.12.2 or compatible
• Java 8+
• MySQL 5.7+ — only if storage.type: mysql
• Vault — optional, for currency rewards
• An OpenAI-compatible LLM endpoint + embedding endpoint