Skip to main content
Unlike search_audio and deep_search which operate on a single file, search_memory searches across every transcription Augent has ever stored. No file path needed. One query, every file. Two modes:
  • keyword (default): literal substring matching. Fast, exact.
  • semantic: meaning-based search using embeddings. Finds content even when the exact words don’t match.

​
Example: keyword mode

Request: 
{
  "query": "dopamine"
}
Response: 
{
  "query": "dopamine",
  "mode": "keyword",
  "results": [
    {
      "title": "Huberman Lab - How To Focus",
      "file_path": "/Users/you/Downloads/Huberman Lab - How To Focus.webm",
      "start": 1024.3,
      "end": 1031.7,
      "text": "...**dopamine** is not about pleasure. It's about motivation and the pursuit of reward, not the reward itself...",
      "timestamp": "17:04"
    }
  ],
  "match_count": 1,
  "total_segments": 3200,
  "files_searched": 47
}

​
Example: semantic mode

Request: 
{
  "query": "how sleep affects muscle recovery",
  "mode": "semantic"
}
Response: 
{
  "query": "how sleep affects muscle recovery",
  "mode": "semantic",
  "results": [
    {
      "title": "Dr. Peter Attia - Drive Ep 87",
      "file_path": "/Users/you/Downloads/Dr. Peter Attia - Drive Ep 87.webm",
      "start": 2145.8,
      "end": 2153.2,
      "text": "...your body does most of its tissue repair between 2 and 4 AM during deep sleep. Skip that window and you're training for nothing...",
      "timestamp": "35:45",
      "similarity": 0.8134
    }
  ],
  "total_segments": 4200,
  "files_searched": 47,
  "model_used": "all-MiniLM-L6-v2"
}

​
Example: CSV export

Request: 
{
  "query": "remote work",
  "output": "~/Desktop/remote-work.csv"
}
When output is provided and results exist, a CSV file is written and csv_path is added to the response: 
{
  "query": "remote work",
  "mode": "keyword",
  "results": [...],
  "match_count": 8,
  "csv_path": "/Users/you/Desktop/remote-work.csv"
}
The CSV contains clean columns (Source, Timestamp, Snippet) with bold markers stripped.

​
Parameters

ParameterRequiredDefaultDescription
queryYes—Search query. A word/phrase for keyword mode, or natural language for semantic mode
modeNokeywordkeyword for literal matching, semantic for meaning-based search
top_kNo10Maximum number of results to return
outputNo—File path to save results (.csv or .xlsx)
context_wordsNo25Words of context per result. Use 150 for full evidence blocks. Semantic mode only
dedup_secondsNo0Merge matches within this many seconds. Use 60 for Q&A. Semantic mode only

​
Notes

search_memory operates entirely on what’s already stored. No transcription runs. If you haven’t transcribed any files yet, it returns zero results.
Keyword mode is fast — it scans segment text directly. Semantic mode computes embeddings on first use (then cached). Default to keyword unless you need meaning-based matching.
Also available via CLI: augent memory search "query" with --semantic and --top-k flags.