knowledge-agent

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Knowledge Agent

知识Agent

Build and query AI-powered knowledge bases from claude-mem observations.

基于claude-mem的观测记录构建并查询AI驱动的知识库。

What Are Knowledge Agents?

什么是知识Agent？

Knowledge agents are filtered corpora of observations compiled into a conversational AI session. Build a corpus from your observation history, prime it (loads the knowledge into an AI session), then ask it questions conversationally.

Think of them as custom "brains": "everything about hooks", "all decisions from the last month", "all bugfixes for the worker service".

知识Agent是经过筛选的观测语料库，可整合到对话式AI会话中。你可以从自己的观测历史构建语料库，对其进行启动（将知识加载到AI会话中），然后以对话方式向其提问。

你可以把它们看作自定义的「大脑」：比如「所有关于hooks的内容」、「上个月的全部决策」、「worker服务的所有bug修复记录」。

Workflow

工作流程

Step 1: Build a corpus

步骤1：构建语料库

text

build_corpus name="hooks-expertise" description="Everything about the hooks lifecycle" project="claude-mem" concepts="hooks" limit=500

Filter options:

```
project
```
— filter by project name
```
types
```
— comma-separated: decision, bugfix, feature, refactor, discovery, change
```
concepts
```
— comma-separated concept tags
```
files
```
— comma-separated file paths (prefix match)
```
query
```
— semantic search query
```
dateStart
```
/
```
dateEnd
```
— ISO date range
```
limit
```
— max observations (default 500)

text

build_corpus name="hooks-expertise" description="Everything about the hooks lifecycle" project="claude-mem" concepts="hooks" limit=500

筛选选项：

```
project
```
— 按项目名称筛选
```
types
```
— 逗号分隔的类型，可选值：decision、bugfix、feature、refactor、discovery、change
```
concepts
```
— 逗号分隔的概念标签
```
files
```
— 逗号分隔的文件路径（前缀匹配）
```
query
```
— 语义搜索查询词
```
dateStart
```
/
```
dateEnd
```
— ISO格式的日期范围
```
limit
```
— 最大观测记录数（默认500）

Step 2: Prime the corpus

步骤2：启动语料库

text

prime_corpus name="hooks-expertise"

This creates an AI session loaded with all the corpus knowledge. Takes a moment for large corpora.

text

prime_corpus name="hooks-expertise"

该操作会创建一个加载了全部语料库知识的AI会话。如果语料库较大，需要等待一段时间。

Step 3: Query

步骤3：查询

text

query_corpus name="hooks-expertise" question="What are the 5 lifecycle hooks and when does each fire?"

The knowledge agent answers from its corpus. Follow-up questions maintain context.

text

query_corpus name="hooks-expertise" question="What are the 5 lifecycle hooks and when does each fire?"

知识Agent会基于其语料库进行回答，后续提问会保留上下文。

Step 4: List corpora

步骤4：列出所有语料库

text

list_corpora

Shows all corpora with stats and priming status.

text

list_corpora

展示所有语料库的统计数据和启动状态。

Tips

使用提示

Focused corpora work best — "hooks architecture" beats "everything ever"
Prime once, query many times — the session persists across queries
Reprime for fresh context — if the conversation drifts, reprime to reset
Rebuild to update — when new observations are added, rebuild then reprime

聚焦的语料库效果最佳 — 「hooks架构」这类定向语料的效果远好于「全部历史内容」
一次启动，多次查询 — 会话会在多次查询之间保留
重新启动以获得全新上下文 — 如果对话偏离了方向，重新启动即可重置上下文
重建以更新内容 — 新增观测记录后，先重建语料库再重新启动即可

Maintenance

维护操作

Rebuild a corpus (refresh with new observations)

重建语料库（用新的观测记录刷新内容）

text

rebuild_corpus name="hooks-expertise"

After rebuilding, reprime to load the updated knowledge:

text

rebuild_corpus name="hooks-expertise"

重建完成后，重新启动以加载更新后的知识：

Reprime (fresh session)

重新启动（全新会话）

text

reprime_corpus name="hooks-expertise"

Clears prior Q&A context and reloads the corpus into a new session.

text

reprime_corpus name="hooks-expertise"

清除之前的问答上下文，将语料库重新加载到新的会话中。