Memory Search

When to Use

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

3-Layer Workflow (ALWAYS Follow)

Step 1: Search - Get Index with IDs

search

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

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

• 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

timeline

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

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

depth_before + 1 + depth_after

• 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

get_observations

get_observations(ids=[11131, 10942])

get_observations

• 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

Saving Memories

save_memory

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

• text

  (string, required) - Content to remember

• title

  (string, optional) - Short title, auto-generated if omitted

• project

  (string, optional) - Project name, defaults to "claude-mem"

Examples

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

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

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

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