mem search
- Repo stars 80,444
- Author repo claude-mem
- Domain
- Data
- Author-declared agents
- No explicit declaration found; this is not inferred or tested compatibility
- Static check
- 88 / 100 · heuristic scan, not runtime safety proof
- Runtime evidence
- Not run; no isolated runtime test evidence is currently recorded
- Author / version / license
- @thedotmack · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No explicit requirements detected
- Detected file/system behavior
-
- Read-only
- Network behavior
- External requests
- Install commands
- None (reference only)
Heads up: Tool permissions are not declared; actual access depends on the runtime.
# Step 2: Timeline - Get Context Around Interesting Results
timeline(anchor=11131, depth_before=3, depth_after=3, project="my-project") Use the `search` MCP tool: Returns: Table with IDs, timestamps, types, titles (~50-100 tokens/result) Parameters: `query` (string) - Search term `limit` (number) - Max results, default 20, max 100
Use the `timeline` MCP tool: Or find anchor automatically from query: 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
Review titles from Step 1 and context from Step 2. Pick relevant IDs. Discard the rest. Use the `get_observations` MCP tool: ALWAYS use `get_observations` for 2+ observations - single request vs N requests. Parameters: `ids` (array of numbers, required) - Observation IDs to fetch
# 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.
Listed in source order.
sections -> When to Use → 3-Layer Workflow (ALWAYS Follow) → Step 1: Search - Get Index with IDs → Step 2: Timeline - Get Context Around Interesting Results → Step 3: Fetch - Get Full Details ONLY for Filtered IDs → Examples
terms -> NEVER fetch full details without filtering first. 10x token savings. · Returns · Parameters · Find recent bug fixes · Find what happened last week · Understand context around a discovery · Batch fetch details · Search index
files/cmd -> search · query · limit · project · type · obs_type · dateStart · dateEnd
body sha256 -> a2b1708afa95
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
searchMCP tool: Returns: Table with IDs, timestamps, types, titles (~50-100 tokens/result) Parameters:query(string) - Search termlimit(number) - Max results, default 20, max 100Step 2: Timeline - Get Context Around Interesting Results
Use the
timelineMCP tool: Or find anchor automatically from query: Returns:depth_before + 1 + depth_afteritems in chronological order with observations, sessions, and prompts interleaved around the anchor. Parameters:anchor(number, optional) - Observation ID to center aroundStep 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_observationsMCP tool: ALWAYS useget_observationsfor 2+ observations - single request vs N requests. Parameters:ids(array of numbers, required) - Observation IDs to fetch