minimax

一个工具 = MiniMax 全部多模态能力：DSH 纯文本模型看图/画图/生视频/说话/唱歌/翻唱/搜索/查额度 | One mmx_bridge tool = all MiniMax multimodal (VLM/image/video/speech/music/cover/search/quota) for DeepSeek Harness (DSH)

DSH plugin: floating MiniMax Token Plan usage bubble in the Web UI

Guide Dog for DSH — MiniMax multimodal plugin: image/video/music/speech generation & vision tools, voice mode, voice input. Real-time call mode implemented: streaming voice conversation, unified floating UI, adaptive prompts, zh/en i18n. Accessibility features planned for testing & rollout. Featured in the dsh-recommend plugin registry.

DSH (DeepSeek Harness) plugin: MiniMax Token Plan usage in Settings

Harness-kernel mesh for DeepSeek Harness: kimi/grok/codex/minimax model routes (L1), distilled subagent recipes (L2) and kernel_run/kernel_status/kernel_switch tools.

Mini-Agent written in DSH form: the mini-agent tool surface re-registered as native DeepSeek Harness tools.

🎬AI-Powered Director: MiniMax-H3 Video Generation Plugin Directed by DeepSeek-Harness. 🤖More than Prompting. 🪄Canvas UI.

DeepSeek Harness ??????:MiniMax H3(easyframe ??)??/????/???/????/????,??????? + ???????MiniMax H3 video generation plugin for DeepSeek Harness.

该仓库暂未提供项目说明。

明眸 VisionBridge - 自研视觉桥：瞎子模型收图时自动调用视觉模型识别

Multi-provider quota, balance and Token-cost dashboard for DeepSeek Harness Web.

DeepSeek Harness plugin: MiniMax Coding Plan quota monitor with progress bars in sidebar

Vision for DeepSeek Harness agents — paste images in the Web composer, delegate reads to Kimi/MiniMax vision routes on isolated contexts; zero image bytes in the main session

DSH plugin: auto reasoning_effort (low/high/max) per turn via MiniMax complexity scorer + token ledger + per-reply metadata label

DeepSeek Harness 文生图插件：基于 MiniMax image-01 生成图片，注册 image-gen 工具