A lightweight, fully asynchronous Fabric mod that brings a friendly AI player named **Little Whale** into your Minecraft server. Powered by any OpenAI-compatible API, it can chat with players in private or public, understand context, and speak their language.<\/p>\n
## \u2728 Features<\/p>\n
– **3 Chat Modes** \u2013 Switch between private, public, or mixed mode: ## \ud83d\udce6 Installation<\/p>\n 1. Install **Fabric** for Minecraft 1.21.8. ## \u2699\ufe0f Configuration (`config\/aichat.json`)<\/p>\n | Key | Type | Default | Description | ## \ud83c\udfae Usage<\/p>\n ### Chat Triggers ### Admin Commands (requires OP, permission level 2)<\/p>\n | Command | Description | Little Whale AI (\u5c0f\u9cb8\u9c7cAI) – Your own AIBot in Minecraft<\/p>\n","protected":false},"featured_media":94670,"template":"","meta":{"_minecraft_slug":"little-whale-ai","_minecraft_project_id":"c9H1TtYT","_minecraft_author":"bilibilihcdwl","_minecraft_license":"MIT","_minecraft_downloads":10,"_minecraft_follows":0,"_minecraft_client_side":"unsupported","_minecraft_server_side":"required","_minecraft_storage_type":"zip","_minecraft_archive_name":"little-whale-ai.zip","_minecraft_size_bytes":21044,"_minecraft_version_count":1,"_minecraft_updated_at":"2026-05-16T14:10:42.769711Z","_minecraft_date_created":"2026-05-02T20:04:34.618779Z","_minecraft_date_modified":"2026-04-26T17:38:28.181568Z","_minecraft_project_url":"https:\/\/modrinth.com\/mod\/little-whale-ai","_minecraft_icon_attachment_id":94670,"_minecraft_imported_at":"2026-06-05T10:05:35+00:00","_minecraft_import_hash":"9cf367f5727652c256df285e8c2a9758","_minecraft_versions":"","_minecraft_links":"","_minecraft_gallery":"","_minecraft_api_metadata":""},"mod_category":[97,867,123,92],"mod_loader":[99],"minecraft_version":[81],"class_list":["post-94669","mod","type-mod","status-publish","has-post-thumbnail","hentry","mod_category-fabric","mod_category-social","mod_category-technology","mod_category-utility","mod_loader-fabric","minecraft_version-1-21-8"],"yoast_head":"\n
\n – **Private** (mode 1): Players use `@ai
\n – **Public** (mode 2): Every public chat message is treated as conversation with the AI. The AI replies publicly to everyone. Context is globally shared.
\n – **Mixed** (mode 3): `@ai` triggers private conversation, while normal chat triggers public AI replies. Private and public contexts are kept separate.
\n– **Player-aware AI** \u2013 In public\/mixed modes, the AI sees who said what via `[PlayerName]: message` format. It can address players by name naturally.
\n– **Multilingual** \u2013 The AI automatically replies in the same language the player used (Chinese, English, etc.).
\n– **Plain Text Only** \u2013 The AI is instructed never to use Markdown, code blocks, or special formatting, keeping output clean for the in-game chat.
\n– **Safe & Non\u2011blocking** \u2013 All HTTP requests run on background threads; the server main thread is never blocked.
\n– **Context Management** \u2013 Auto-clears conversation history after a configurable interval or manually via commands.
\n– **Fully Configurable** \u2013 Change the API endpoint, model, temperature, system prompt, prefix, and more through `config\/aichat.json`.
\n– **Admin Commands** \u2013 Powerful `\/aichat` commands to clear contexts, reload config, and view status.<\/p>\n
\n2. Download the mod `.jar` file and place it into the `mods\/` folder.
\n3. Launch the server or client. A default configuration file will be generated at `config\/aichat.json`.
\n4. Edit `config\/aichat.json` and fill in your `apiKey` and (optionally) `apiUrl`. Save the file.
\n5. Run `\/aichat reload` (requires OP) or restart the server.<\/p>\n
\n|—–|——|———|————-|
\n| `apiUrl` | String | `https:\/\/open.bigmodel.cn\/api\/paas\/v4\/chat\/completions` | API endpoint (OpenAI-compatible) |
\n| `apiKey` | String | `””` | Your API key |
\n| `systemPrompt` | String | *(multilingual, anti-prefix, plain\u2011text prompt)* | System prompt that defines AI behavior |
\n| `modelName` | String | `”general”` | Model name to send to the API |
\n| `temperature` | Double | `0.7` | Creativity of responses (0.0\u20132.0) |
\n| `autoClearContext` | Boolean | `true` | Enable automatic context clearing |
\n| `contextExpireSeconds` | Integer | `300` | Seconds between auto\u2011clears |
\n| `prefix` | String | `”
\n| `mode` | Integer | `2` | Chat mode: 1 = private, 2 = public, 3 = mixed |<\/p>\n
\n– **Private \/ Mixed**: Start your message with `@ai`. Example: `@ai How do I craft a furnace?`
\n– **Clear private context**: `@ai clear` (works in private\/mixed mode)
\n– **Public mode**: Just talk in chat \u2013 every message triggers a public AI reply.<\/p>\n
\n|———|————-|
\n| `\/aichat clear` | Clear your own private context (mode 1\/3) |
\n| `\/aichat clear
\n| `\/aichat clearglobal` | Clear the global public conversation context |
\n| `\/aichat clearall` | Clear all contexts (private + global) |
\n| `\/aichat reload` | Reload the configuration without restarting |
\n| `\/aichat info` | Display current settings (API, model, mode, etc.) |<\/p>\n","protected":false},"excerpt":{"rendered":"