mem-search

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Memory Search

内存搜索

Search past work across all sessions. Simple workflow: search -> filter -> fetch.

搜索所有会话中的历史工作内容。简单工作流：搜索 -> 筛选 -> 获取。

When to Use

使用场景

Use when users ask about PREVIOUS sessions (not current conversation):

"Did we already fix this?"
"How did we solve X last time?"
"What happened last week?"

当用户询问过往会话（非当前对话）相关内容时使用：

"我们已经修复过这个问题了吗？"
"上次我们是怎么解决X问题的？"
"上周发生了什么？"

3-Layer Workflow (ALWAYS Follow)

三层工作流（必须严格遵循）

NEVER fetch full details without filtering first. 10x token savings.

绝对不要在未筛选的情况下直接获取完整详情。这样能节省10倍的token消耗。

Step 1: Search - Get Index with IDs

步骤1：搜索 - 获取带ID的索引

Use the

search

MCP tool:

search(query="authentication", limit=20, project="my-project")

Returns: Table with IDs, timestamps, types, titles (~50-100 tokens/result)

| ID | Time | T | Title | Read |
|----|------|---|-------|------|
| #11131 | 3:48 PM | 🟣 | Added JWT authentication | ~75 |
| #10942 | 2:15 PM | 🔴 | Fixed auth token expiration | ~50 |

Parameters:

```
query
```
(string) - Search term
```
limit
```
(number) - Max results, default 20, max 100
```
project
```
(string) - Project name filter
```
type
```
(string, optional) - "observations", "sessions", or "prompts"
```
obs_type
```
(string, optional) - Comma-separated: bugfix, feature, decision, discovery, change
```
dateStart
```
(string, optional) - YYYY-MM-DD or epoch ms
```
dateEnd
```
(string, optional) - YYYY-MM-DD or epoch ms
```
offset
```
(number, optional) - Skip N results
```
orderBy
```
(string, optional) - "date_desc" (default), "date_asc", "relevance"

使用

search

MCP工具：

search(query="authentication", limit=20, project="my-project")

返回结果： 包含ID、时间戳、类型、标题的表格（每条结果约50-100个token）

| ID | Time | T | Title | Read |
|----|------|---|-------|------|
| #11131 | 3:48 PM | 🟣 | Added JWT authentication | ~75 |
| #10942 | 2:15 PM | 🔴 | Fixed auth token expiration | ~50 |

参数说明：

```
query
```
（字符串）- 搜索关键词
```
limit
```
（数字）- 最大结果数，默认20，上限100
```
project
```
（字符串）- 项目名称筛选条件
```
type
```
（字符串，可选）- 可选值为"observations""sessions"或"prompts"
```
obs_type
```
（字符串，可选）- 多个值用逗号分隔：bugfix、feature、decision、discovery、change
```
dateStart
```
（字符串，可选）- 格式为YYYY-MM-DD或时间戳（毫秒）
```
dateEnd
```
（字符串，可选）- 格式为YYYY-MM-DD或时间戳（毫秒）
```
offset
```
（数字，可选）- 跳过前N条结果
```
orderBy
```
（字符串，可选）- 排序方式，默认"date_desc"，可选"date_asc""relevance"

Step 2: Timeline - Get Context Around Interesting Results

步骤2：时间线 - 获取目标结果的上下文信息

Use the

timeline

MCP tool:

timeline(anchor=11131, depth_before=3, depth_after=3, project="my-project")

Or find anchor automatically from query:

timeline(query="authentication", depth_before=3, depth_after=3, project="my-project")

Returns:

depth_before + 1 + depth_after

items in chronological order with observations, sessions, and prompts interleaved around the anchor.

Parameters:

```
anchor
```
(number, optional) - Observation ID to center around
```
query
```
(string, optional) - Find anchor automatically if anchor not provided
```
depth_before
```
(number, optional) - Items before anchor, default 5, max 20
```
depth_after
```
(number, optional) - Items after anchor, default 5, max 20
```
project
```
(string) - Project name filter

使用

timeline

MCP工具：

timeline(anchor=11131, depth_before=3, depth_after=3, project="my-project")

或者通过查询自动定位锚点：

timeline(query="authentication", depth_before=3, depth_after=3, project="my-project")

返回结果： 按时间顺序排列的

depth_before + 1 + depth_after

条记录，包含锚点前后的observations、sessions和prompts内容。

参数说明：

```
anchor
```
（数字，可选）- 作为中心的observation ID
```
query
```
（字符串，可选）- 若未提供anchor，则通过查询自动定位锚点
```
depth_before
```
（数字，可选）- 锚点之前的记录数，默认5，上限20
```
depth_after
```
（数字，可选）- 锚点之后的记录数，默认5，上限20
```
project
```
（字符串）- 项目名称筛选条件

Step 3: Fetch - Get Full Details ONLY for Filtered IDs

步骤3：获取 - 仅为筛选后的ID获取完整详情

Review titles from Step 1 and context from Step 2. Pick relevant IDs. Discard the rest.

Use the

get_observations

MCP tool:

get_observations(ids=[11131, 10942])

ALWAYS use
get_observations
for 2+ observations - single request vs N requests.

Parameters:

```
ids
```
(array of numbers, required) - Observation IDs to fetch
```
orderBy
```
(string, optional) - "date_desc" (default), "date_asc"
```
limit
```
(number, optional) - Max observations to return
```
project
```
(string, optional) - Project name filter

Returns: Complete observation objects with title, subtitle, narrative, facts, concepts, files (~500-1000 tokens each)

查看步骤1的标题和步骤2的上下文，挑选相关的ID，舍弃无关的。

使用

get_observations

MCP工具：

get_observations(ids=[11131, 10942])

当需要获取2条及以上observations时，务必使用
get_observations
——单次请求对比N次单独请求更高效。

参数说明：

```
ids
```
（数字数组，必填）- 要获取的observation ID列表
```
orderBy
```
（字符串，可选）- 排序方式，默认"date_desc"，可选"date_asc"
```
limit
```
（数字，可选）- 返回的最大observations数量
```
project
```
（字符串，可选）- 项目名称筛选条件

返回结果： 完整的observation对象，包含标题、副标题、叙述内容、事实、概念、文件（每条约500-1000个token）

Saving Memories

保存内存

Use the

save_memory

MCP tool to store manual observations:

save_memory(text="Important discovery about the auth system", title="Auth Architecture", project="my-project")

Parameters:

```
text
```
(string, required) - Content to remember
```
title
```
(string, optional) - Short title, auto-generated if omitted
```
project
```
(string, optional) - Project name, defaults to "claude-mem"

使用

save_memory

MCP工具存储手动记录的observations：

save_memory(text="Important discovery about the auth system", title="Auth Architecture", project="my-project")

参数说明：

```
text
```
（字符串，必填）- 要保存的内容
```
title
```
（字符串，可选）- 简短标题，若省略则自动生成
```
project
```
（字符串，可选）- 项目名称，默认为"claude-mem"

Examples

示例

Find recent bug fixes:

search(query="bug", type="observations", obs_type="bugfix", limit=20, project="my-project")

Find what happened last week:

search(type="observations", dateStart="2025-11-11", limit=20, project="my-project")

Understand context around a discovery:

timeline(anchor=11131, depth_before=5, depth_after=5, project="my-project")

Batch fetch details:

get_observations(ids=[11131, 10942, 10855], orderBy="date_desc")

查找近期的bug修复记录：

search(query="bug", type="observations", obs_type="bugfix", limit=20, project="my-project")

查找上周的工作内容：

search(type="observations", dateStart="2025-11-11", limit=20, project="my-project")

了解某一发现的上下文：

timeline(anchor=11131, depth_before=5, depth_after=5, project="my-project")

批量获取详情：

get_observations(ids=[11131, 10942, 10855], orderBy="date_desc")

Why This Workflow?

为什么采用此工作流？

Search index: ~50-100 tokens per result
Full observation: ~500-1000 tokens each
Batch fetch: 1 HTTP request vs N individual requests
10x token savings by filtering before fetching

搜索索引： 每条结果约50-100个token
完整observation： 每条约500-1000个token
批量获取： 1次HTTP请求对比N次单独请求
通过先筛选再获取，节省10倍的token消耗