mem-search
Scannednpx machina-cli add skill EconLab-AI/Ultrabrain/mem-search --openclawMemory 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 termlimit(number) - Max results, default 20, max 100project(string) - Project name filtertype(string, optional) - "observations", "sessions", or "prompts"obs_type(string, optional) - Comma-separated: bugfix, feature, decision, discovery, changedateStart(string, optional) - YYYY-MM-DD or epoch msdateEnd(string, optional) - YYYY-MM-DD or epoch msoffset(number, optional) - Skip N resultsorderBy(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 aroundquery(string, optional) - Find anchor automatically if anchor not provideddepth_before(number, optional) - Items before anchor, default 5, max 20depth_after(number, optional) - Items after anchor, default 5, max 20project(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 fetchorderBy(string, optional) - "date_desc" (default), "date_asc"limit(number, optional) - Max observations to returnproject(string, optional) - Project name filter
Returns: Complete observation objects with title, subtitle, narrative, facts, concepts, files (~500-1000 tokens each)
Saving Memories
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 remembertitle(string, optional) - Short title, auto-generated if omittedproject(string, optional) - Project name, defaults to "ultrabrain"
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
Source
git clone https://github.com/EconLab-AI/Ultrabrain/blob/main/plugin/skills/mem-search/SKILL.mdView on GitHub Overview
Mem-search scans ultrabrain's persistent memory store across past sessions to surface what happened before. It follows a three-step workflow (search -> timeline -> fetch) to efficiently locate relevant observations before pulling full details. Use it to answer questions like 'did we already solve this?' or review prior work for continuity.
How This Skill Works
1) Use the search MCP tool to get IDs for past work (query, limit, project, type, date). 2) Run timeline to gather surrounding context around anchors or queries. 3) Fetch full details for filtered IDs with get_observations (prefer 2+ IDs per call). Optional: save important findings with save_memory for future reference.
When to Use It
- Did we already fix this?
- How did we solve X last time?
- What happened last week?
- Review past sessions for a feature's history before continuing
- Audit decisions or changes before a release
Quick Start
- Step 1: Search for past work with search(query='authentication', limit=20, project='my-project')
- Step 2: Use timeline to gather context around relevant IDs: timeline(anchor=11131, depth_before=3, depth_after=3, project='my-project')
- Step 3: Fetch full details for filtered IDs: get_observations(ids=[11131, 10942])
Best Practices
- Always start with a search to build a compact list of IDs before fetching details.
- Use type, obs_type, and date range filters to narrow the scope.
- Never fetch full details without filtering first to save tokens.
- Use the Timeline step to provide context around anchors before fetching.
- Save key findings with save_memory to enrich future queries
Example Use Cases
- 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')
- Save a memory for future reference: save_memory(text='Auth architecture improvement identified', title='Auth Architecture', project='my-project')
