Mem Search

Name: Mem Search
Author: thedotmack

thedotmack/claude-mem

7k installs
89.6k repo stars
Updated August 4, 2026
thedotmack/claude-mem

mem-search is a claude-mem skill for token-efficient cross-session memory lookup using search, timeline, and batch observation fetch.

About

The mem-search skill queries claude-mem persistent cross-session memory when users ask whether a problem was solved before or how prior work was done. It enforces a three-layer workflow for roughly tenfold token savings: search for an index of observation ids, timeline for chronological context around interesting hits, then get_observations for full detail on only the filtered ids. Step one uses the search MCP tool with query, limit, project, optional type and obs_type filters, and date ranges returning compact tables with ids, timestamps, types, and titles. Step two calls timeline with anchor or query plus depth_before and depth_after to interleave observations, sessions, and prompts around a discovery. Step three batch-fetches selected observations in one request instead of many individual calls. Invoke for questions like did we already fix this, how did we solve X last time, or what happened last week. Optional knowledge agents synthesize conversational answers from observation history when raw records are not enough.

Three-layer workflow: search index, timeline context, then batch get_observations fetch.
Never fetch full observation details before filtering titles from search results.
search supports project, type, obs_type, dateStart, dateEnd, and orderBy parameters.
timeline anchors on observation id or query with configurable depth before and after.
Batch get_observations saves tokens versus N individual detail requests.

Mem Search by the numbers

7,016 all-time installs (skills.sh)
+295 installs in the week ending Aug 5, 2026 (Skillselion tracking)
Ranked #116 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Security screen: MEDIUM risk (skills.sh audit)
Data as of Aug 5, 2026 (Skillselion catalog sync)

At a glance

mem-search capabilities & compatibility

Capabilities: compact search index queries · timeline context around anchors · batch observation detail fetch · project and date filtering · observation type filtering
Use cases: memory · research · debugging

From the docs

What mem-search says it does

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

SKILL.md

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

SKILL.md

npx skills add https://github.com/thedotmack/claude-mem --skill mem-search

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/thedotmack/claude-mem/mem-search.svg)](https://skillselion.com/skills/thedotmack/claude-mem/mem-search)

Installs	7k
repo stars	★ 89.6k
Security audit	2 / 3 scanners passed
Last updated	August 4, 2026
Repository	thedotmack/claude-mem ↗

How do agents recall prior session work without loading full observation narratives for every search hit?

Search claude-mem cross-session memory with a 3-layer search, timeline, and batch fetch workflow for token-efficient recall.

Who is it for?

Claude Code users asking about previous fixes, decisions, or weekly activity stored in claude-mem.

Skip if: Skip when the question is only about the current conversation with no prior session history.

When should I use this skill?

User asks did we already solve this, how did we do X last time, or what happened last week in prior sessions.

What you get

Filtered observation details fetched only for relevant ids after compact search and timeline review.

Filtered memory search index
Fetched prior session detail records

By the numbers

3-layer search → filter → fetch workflow
Readme cites ~10x token savings when filtering before full fetch

Files

SKILL.mdMarkdownGitHub ↗

Memory Search

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

When to Use

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?"

3-Layer Workflow (ALWAYS Follow)

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

Step 1: Search - Get Index with IDs

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"

Step 2: Timeline - Get Context Around Interesting Results

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

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

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)

Examples

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")

Why This Workflow?

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

Knowledge Agents

Want synthesized answers instead of raw records? Use /knowledge-agent to build a queryable corpus from your observation history. The knowledge agent reads all matching observations and answers questions conversationally.