把零散的 Token Plan、Coding Plan、大模型 API 额度聚合成一个虚拟 Plan，一键接入 Claude Code、Claude Desktop App、OpenClaw、OpenCode 等工具 —— 省钱！省 Token！完全本地运行！ Bundle your scattered Token Plan, Coding Plan, and LLM API quotas into a single virtual Plan, and plug it into Claude Code, Claude Desktop App, OpenClaw, OpenCode, and more.

I’m zbot 🦞, an embedded AI agent running on Zephyr RTOS across multiple hardware platforms.

把小米 MiMo 全模态能力(对话/图像/视频/TTS/声音克隆)封装成 stdio MCP Server,Claude Code 与 Codex 可直接调用

ComfyUI nodes for Batch Image Captioning + various Vision-Language (VL) models, including InternVL3.5, Xiaomi MiMo-VL, LiquidAI LFM2-VL, Kwai Keye-VL, AIDC-AI Ovis2.5 and Ovis-U1. Models: Ovis2.5-2B, Ovis2.5-9B, Keye-VL-8B-Preview, MiMo-VL-7B-RL-GGUF, LFM2-VL-450M, LFM2-VL-1.6B, Ovis-U1-3B, Ovis2.5-2B, Ovis2.5-9B, InternVL3_5-1B/2B/4B/8B/14B/38B

OpenClaw TTS Provider for Xiaomi MiMo (mimo-v2-tts)

Local Xiaomi MiMo API / Token Plan profile switcher for Claude Code.

🏪 Multi-agent AI assistant for Indonesian UMKM. Riset kompetitor → strategi harga → konten → CS auto-reply. Powered by Xiaomi MiMo.

Minimal framework for building MiMo-orchestrated multi-tool crypto agents — open-source distillation of mycrypto.vimfuture.cc

Agent skill for multi-speaker meeting & podcast transcription — FunASR (Paraformer/SenseVoice/Whisper) + MiMo-V2.5-ASR + CAM++ speaker diarization + LLM cleanup. 99 languages, GPU & CPU. Works with Claude Code and any SKILL.md-compatible agent.

An AI Agent prototype for turning course transcripts, study notes, and long-form learning materials into structured review assets, summaries, Q&A cards, and self-test questions.

MiMo AI Studio 对话导出工具 | Export conversations from Xiaomi MiMo AI Studio

Intelligent multi-model cost router — auto-delegates AI tasks between Xiaomi MiMo (cheap) and premium models (Claude/GPT). Built for MiMo Orbit 100T program.

从 130k+ stars 的 GitHub repo 中精选的论文写作 prompt — 每个场景多个候选，按排名对比，复制即用

PromptForge — privacy-first prompt engineering studio. Run one prompt across many OpenAI-compatible models in parallel (Xiaomi MiMo, OpenAI, DeepSeek, Groq, Ollama), compare side-by-side, and use one model as a judge. Next.js 16 + React 19 + TypeScript + Tailwind CSS 4.

A modern, privacy-first AI chat playground for any OpenAI-compatible API (Xiaomi MiMo, OpenAI, DeepSeek, Groq, Ollama, ...). Built with Next.js 16, React 19, TypeScript, Tailwind CSS 4.

Multi-model LLM playground with tool calling — MiMo v2.5 / MiMo 100T / Claude / GPT-5 / Gemini / DeepSeek. Next.js 16 + React 19 + Tailwind v4.

Adaptive coding tutor — Socratic multi-agent reviewer powered by Xiaomi MiMo. Untuk pelajar Indonesia.

A modern, privacy-first AI chat playground for any OpenAI-compatible API (Xiaomi MiMo, OpenAI, DeepSeek, Groq, Ollama, ...). Built with Next.js 16, React 19, TypeScript, Tailwind CSS 4.

LOBBER: A BETTER CLAW FOR BETTER PEOPLE. VERY CUTE WE LOVE HIM. I MADE THIS SO I CAN ARGUE WITH MANAGEMENT ABOUT HOW BAD AND OR MAYBE GOOD AGENTS ARE SO I HAD SOME SORT OF EXPERIENCE AND IT GOT OUT OF HAND.

A CLI developer tool for running custom evaluation suites to OpenAI-compatible APIs (MiMo, Claude, GPT, etc.), outputting Markdown research reports + JSON traces. Useful for developers who want to benchmark models before production. Suitable for Data/Research + Dev tools, and a natural fit using the MiMo API + Hermes Agent workflow.