memu/SKILL.md
# memU Skill > 集成 memU Cloud API 的主动记忆系统 ## 触发条件 当用户提到以下内容时使用: - "记住xxx" - "我之前说过xxx吗" - "我的偏好是xxx" - "学习这个" - 或者需要主动回忆之前对话内容时 ## 功能 ### 1. memorize - 记忆学习 将当前对话或内容注册到 memU 进行持续学习。 **API**: `POST https://api.memu.so/api/v3/memory/memorize` **Headers**: ``` Authorization: Bearer {memU_api_key} Content-Type: application/json ``` **Body**: ```json { "resource_url": "conversation://{session_id}", "modality": "conversation", "user": {"user_id": "{user_id}"} } ``` **Response**: ```json
npx skillsauth add adminlove520/xiaoxi-skills memuInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
集成 memU Cloud API 的主动记忆系统
当用户提到以下内容时使用:
将当前对话或内容注册到 memU 进行持续学习。
API: POST https://api.memu.so/api/v3/memory/memorize
Headers:
Authorization: Bearer {memU_api_key}
Content-Type: application/json
Body:
{
"resource_url": "conversation://{session_id}",
"modality": "conversation",
"user": {"user_id": "{user_id}"}
}
Response:
{
"resource": {...},
"items": [...],
"categories": [...]
}
查询已有的记忆,支持 RAG(快速)和 LLM(深度推理)两种模式。
API: POST https://api.memu.so/api/v3/memory/retrieve
Headers: 同上
Body (RAG 模式):
{
"queries": [
{"role": "user", "content": {"text": "查询内容"}}
],
"method": "rag",
"where": {"user_id": "{user_id}"}
}
Body (LLM 模式):
{
"queries": [
{"role": "user", "content": {"text": "查询内容"}}
],
"method": "llm",
"where": {"user_id": "{user_id}"}
}
列出所有自动生成的记忆分类。
API: POST https://api.memu.so/api/v3/memory/categories
API Key 已配置:
mu_R7_8GJyOhin_Hg7kRBQaPtafBTY0NLgsQO1U94tJGE33NjGgkdZGIzEjNHMtkt3R7d5UcYb5N2vrsT4Dvg76kqAxhJG0Nl18yGX6jQhttps://api.memu.so记住当前对话:
记住我们刚才讨论的关于 MCP 安全的事情
检索记忆:
我之前有没有提到过我喜欢什么天气?
主动推荐: 根据用户过去的偏好,在适当的时候主动推荐相关内容。
data-ai
Spaced-repetition flashcard system. Create cards from facts or text, chat with flashcards using free-text answers graded by the agent, generate quizzes from YouTube transcripts, review due cards with adaptive scheduling, and export/import decks as CSV.
development
Canvas LMS integration — fetch enrolled courses and assignments using API token authentication.
development
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
devops
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.