knowyoubetter
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@knowyoubettershould I use Redis or Memcached for caching?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
knowyoubetter
一个 MCP 插件:agent 没把握时向用户提问(3-5 个候选 + 正反理由),记住你的选择(本地 embedding),下次遇到相似问题自动按你的偏好作答——越用越懂你,问得越来越少。
工具
工具 | 用途 |
| 低置信度时向用户提问;命中高度相似历史时直接返回历史答案(source=history) |
| 两阶段模式下记录用户对 pending 的选择 |
| 开始任务时查询相关历史偏好 |
客户端支持 MCP elicitation 时(如 Claude Code)会直接弹出原生选择框;否则自动降级为两阶段:agent 展示候选 → 用户回答 → agent 调 record_choice。
表单里固定提供两个额外选项:「我有别的想法」(在补充说明里写下自定义答案,按原文记录)和「换一批候选」(关闭本次提问并返回 source=rethink,agent 换角度重新生成候选后再问)。两阶段模式下用户可直接说出自己的想法,或让 agent 以 choice="__rethink__" 调 record_choice 关闭本次提问。
Related MCP server: MCP Memory
安装(Claude Code)
claude mcp add knowyoubetter -- node /absolute/path/to/knowyoubetter/dist/index.jsCursor / 其它 host 在各自 MCP 设置中配置同等命令即可。开发模式可用 npx tsx src/index.ts。
数据
默认目录
~/.knowyoubetter(KNOWYOUBETTER_DATA_DIR覆盖):knowyoubetter.db、config.json、models/首次运行自动下载多语言 embedding 模型(q8 量化版,约 135MB),默认从 ModelScope 镜像拉取(
KYB_EMBEDDING_HOST可覆盖,如指回https://huggingface.co);离线时提问功能不受影响,历史检索降级,联网后下次启动自动补齐配置项:
embeddingModel、autoAnswerThreshold(默认 0.90)、recallMinSimilarity(默认 0.40)、maxHistoryInAsk(默认 3)
开发
npm install
npm test # 单测 + 集成(跳过真实模型)
npm run test:real # 真实 embedding 模型测试(首次下载模型)
npm run typecheck:tests # 类型检查测试与配置(含 vitest.config.ts)
npm run build
npx @modelcontextprotocol/inspector node dist/index.js # MCP Inspector 手动验收This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Cloud-hosted MCP server for durable AI memory
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
An MCP memory server. One memory your agents share — across models, devices and apps.
MCP server for AI dialogue using various LLM models via AceDataCloud
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that gives AI assistants the ability to remember user information (preferences, behaviors) across conversations using vector search technology.11MIT
- -licenseNot gradedqualityNot gradedmaintenanceAn MCP server that gives AI assistants (like Cursor, Claude, Windsurf) the ability to remember user information across conversations using vector search technology.-
- FlicenseNot gradedqualityDmaintenanceMCP server that dynamically extracts and manages user memory from LLM conversations, enabling consistent personalization across different models.7-

style-memory-mcpofficial
AlicenseAqualityBmaintenanceA tiny local MCP server that learns a user's conversational style, catchphrases, dialect markers, emoji habits, tone preferences, and concrete collaboration preferences without storing private memories.151MIT