KnowMine — Personal Knowledge Base for AI Agents
Save notes, decisions, and insights. Search them later by meaning, not keywords.
KnowMine is a remote MCP server that gives your AI agent a personal knowledge base with semantic search. Your agent can save knowledge entries during conversations and retrieve them later using natural language queries. All data is stored per-user with full isolation.
Setup
1. Get your API key
Sign up at knowmine.ai, go to Settings → MCP, and copy your key.
2. Connect
Remote MCP server — no Docker or local install needed.
CODEBLOCK0
For OpenClaw:
CODEBLOCK1
Tools (11)
Knowledge CRUD
| Tool | What it does |
|---|
| INLINECODE0 | Save a note, insight, dev log, article, or reflection. Auto-generates title and tags. |
| INLINECODE1 |
Search your knowledge base by meaning. Supports type and tag filters. |
|
get_knowledge | Get full content of one entry by ID. |
|
update_knowledge | Edit title, content, type, or tags of an entry. |
|
delete_knowledge | Remove an entry. |
|
get_related_knowledge | Find entries related to a given entry by semantic similarity. |
|
list_folders | List your folders and recent entries in each. |
Memory
| Tool | What it does |
|---|
| INLINECODE7 | Save a decision, lesson, insight, or preference from a conversation. |
| INLINECODE8 |
Search past memories by natural language. Filter by type. |
Analysis
| Tool | What it does |
|---|
| INLINECODE9 | Generate a user profile summary based on your knowledge. Exportable as a system prompt. |
| INLINECODE10 |
Analyze your knowledge for patterns — frequent topics, recurring themes. |
Example Usage
Save a decision during work:
CODEBLOCK2
Find it later in a new session:
CODEBLOCK3
Search across all knowledge:
CODEBLOCK4
How It Works
- - Search: pgvector semantic similarity on PostgreSQL (not keyword matching)
- Embeddings: OpenAI text-embedding-3-small, auto-generated on save
- Protocol: MCP over Streamable HTTP
- Auth: API key via Bearer token
- Data isolation: Each API key maps to one user account
- Network: All requests go to
knowmine.ai only (no third-party data sharing) - Rate limit: 60 requests/minute
Source Code
Built by
YIING99KnowMine — AI代理的个人知识库
保存笔记、决策和见解。通过语义而非关键词进行搜索。
KnowMine是一个远程MCP服务器，为您的AI代理提供具有语义搜索功能的个人知识库。您的代理可以在对话过程中保存知识条目，并在之后使用自然语言查询进行检索。所有数据按用户存储，完全隔离。
设置
1. 获取您的API密钥
在knowmine.ai注册，进入设置→MCP，复制您的密钥。
2. 连接
远程MCP服务器——无需Docker或本地安装。
服务器URL: https://knowmine.ai/api/mcp
传输方式: Streamable HTTP
认证头: Authorization: Bearer <您的KNOWMINEAPIKEY>
对于OpenClaw：
bash
npx clawhub@latest install knowmine
工具（11个）
知识CRUD
| 工具 | 功能 |
|---|
| addknowledge | 保存笔记、见解、开发日志、文章或反思。自动生成标题和标签。 |
| searchmy_knowledge |
按语义搜索您的知识库。支持类型和标签筛选。 |
| get_knowledge | 按ID获取单条条目的完整内容。 |
| update_knowledge | 编辑条目的标题、内容、类型或标签。 |
| delete_knowledge | 删除条目。 |
| get
relatedknowledge | 通过语义相似度查找与给定条目相关的条目。 |
| list_folders | 列出您的文件夹及每个文件夹中的最近条目。 |
记忆
| 工具 | 功能 |
|---|
| savememory | 保存对话中的决策、经验、见解或偏好。 |
| recallmemory |
通过自然语言搜索过往记忆。可按类型筛选。 |
分析
| 工具 | 功能 |
|---|
| getsoul | 基于您的知识生成用户画像摘要。可导出为系统提示词。 |
| getinsight |
分析您的知识模式——常见主题、重复出现的议题。 |
使用示例
工作中保存决策：
save_memory: 新项目选择PostgreSQL而非MongoDB——需要ACID事务，且团队熟悉SQL
在新会话中查找：
recall_memory: 新项目的数据库决策
→ 返回包含完整上下文的PostgreSQL决策
跨所有知识搜索：
searchmyknowledge: 部署策略
→ 返回按相关性排序的匹配笔记，即使原始条目中从未使用部署一词
工作原理
- - 搜索：基于PostgreSQL的pgvector语义相似度（非关键词匹配）
- 嵌入：OpenAI text-embedding-3-small，保存时自动生成
- 协议：基于Streamable HTTP的MCP
- 认证：通过Bearer令牌的API密钥
- 数据隔离：每个API密钥映射到一个用户账户
- 网络：所有请求仅发送至knowmine.ai（无第三方数据共享）
- 速率限制：60次请求/分钟
源代码
由
YIING99构建
