Terminal
Terminal/Skill
Searches an agent's memory files by meaning as well as keywords, running locally with no API keys.
By Letta
Works with
npx skills add letta-ai/skills --skill memfs-searchSemantic search over your memory filesystem. Useful when Grep isn't enough — finding conceptually related blocks, discovering forgotten reference files, or answering "what do I know about X" across all memory.
First time only. Run the setup script to create the index and generate embeddings:
bash <SKILL_DIR>/scripts/memfs-search.sh setup
This creates a QMD collection over $MEMORY_DIR, adds context annotations, and embeds all .md files. First run downloads ~2GB of local GGUF models to ~/.cache/qmd/models/.
For installation, embedding model options, and troubleshooting: references/qmd-setup.md.
Three tiers. Pick based on what you know about your query:
| You have... | Use | Command | Speed |
|---|---|---|---|
| An exact term or phrase | keyword | search | ~0.3s |
| A vague concept ("what do I know about X") | semantic | vsearch | ~2s cold, <1s warm |
| No idea, need the best results | hybrid | query | ~3s cold, <1s warm |
S="bash <SKILL_DIR>/scripts/memfs-search.sh"
# Keyword — fast, use first
$S search "lettabot architecture"
# Semantic — conceptual, use when keyword misses
$S vsearch "how does the user feel about code reviews"
# Hybrid — best quality, uses keyword + vectors + reranking
$S query "projects cameron is working on"
Always start with keyword search. Only escalate when it misses. Hybrid is 10x slower than keyword.
All commands accept output flags forwarded to QMD:
$S search "topic" --json # structured (for processing)
$S search "topic" --files # file paths only (pipe into Read)
$S search "topic" --full # full document, not snippet
$S search "topic" -n 15 # more results (default: 5)
--json returns an array of objects with file, score, snippet, and context fields.
Fetch a specific file or batch of files without searching:
# Single file
qmd get "system/human/identity.md" -c memory --full
# Batch by glob
qmd multi-get "reference/projects/*" -c memory
Don't wait to be asked. Search memory when:
$S search "topic" --files tells you instantly./init or memory reorg — verify coverage. Search for key concepts and confirm they're stored somewhere.After bulk memory changes (e.g. after /init, reorganization, creating many files):
bash <SKILL_DIR>/scripts/memfs-search.sh reindex
Check index health:
bash <SKILL_DIR>/scripts/memfs-search.sh status
searching-messages skill.