Terminal
Terminal/Skill
Migrates deprecated Letta Filesystem documents into git-backed markdown memory (MemFS) as searchable chunks.
By Letta
Works with
npx skills add letta-ai/skills --skill letta-filesystem-to-memfsUse this skill when a user wants the old Letta Filesystem behavior: upload documents, chunk them, attach them to an agent, and let the agent search/open them.
MemFS is not the same product. It is git-backed markdown memory. To mimic the old workflow, use the bundled CLI:
documents/<corpus>/<doc>/chunks/.system/filesystem/<corpus>.md.# Set this to the skill directory shown in the skill load header.
SKILL_DIR="/path/to/letta-filesystem-to-memfs"
# From any directory. MEMORY_DIR should point at the target agent's memfs repo.
uv run --with pymupdf \
"$SKILL_DIR/scripts/letta_fs_to_memfs.py" ingest \
--memory-dir "$MEMORY_DIR" \
--corpus product-docs \
--source ./docs/ \
--source ./guide.pdf \
--source https://arxiv.org/pdf/2310.08560
cd "$MEMORY_DIR"
git status --short
git diff --stat
Search the chunk corpus lexically:
uv run "$SKILL_DIR/scripts/letta_fs_to_memfs.py" search \
--memory-dir "$MEMORY_DIR" \
--corpus product-docs \
"memory hierarchy" \
-n 5
Semantic search with QMD. The CLI creates a corpus-scoped QMD collection over chunk files only:
uv run "$SKILL_DIR/scripts/letta_fs_to_memfs.py" qmd setup \
--memory-dir "$MEMORY_DIR" \
--corpus product-docs
uv run "$SKILL_DIR/scripts/letta_fs_to_memfs.py" qmd query \
--memory-dir "$MEMORY_DIR" \
--corpus product-docs \
"memory hierarchy" \
-n 5
Use qmd reindex after changing corpus files, and qmd search / qmd vsearch when you specifically want keyword-only or vector-only search.
The ingest script writes:
system/filesystem/<corpus>.md
Pinned index and operating instructions for the corpus.
documents/<corpus>/manifest.md
Corpus manifest.
documents/<corpus>/<doc-slug>/manifest.md
Per-document metadata and chunk table.
documents/<corpus>/<doc-slug>/chunks/chunk-0001.md
Chunk content with frontmatter metadata.
documents/<corpus>/chunks.jsonl
Machine-readable chunk export for custom indexing or debugging.
| Old Filesystem | MemFS mimic |
|---|---|
folders.create | --corpus <name> creates documents/<corpus>/ |
folders.files.upload | letta_fs_to_memfs.py ingest --source <file-or-directory-or-url> |
| OCR/chunk/embed job | Extract + chunk locally; qmd setup / qmd reindex for semantic search |
agents.folders.attach | Enable MemFS, then review and sync repo changes when appropriate |
open_file | Read chunk markdown files by path |
grep_file | rg or letta_fs_to_memfs.py search |
search_file | letta_fs_to_memfs.py qmd query over the corpus chunk collection |
system/filesystem/<corpus>.md for the small always-visible index only.system/; it will bloat the prompt.system/, usually under documents/<corpus>/....--source recursively ingests supported files (.pdf, .md, .txt, .json, .csv, .html, .xml).--glob / --exclude for messy directories. Defaults exclude .git, node_modules, .venv, and __pycache__.--max-download-mb 100; set 0 for unlimited.qmd subcommands when the user needs semantic search over many chunks.uv run --with pymupdf "$SKILL_DIR/scripts/letta_fs_to_memfs.py" ingest --help
uv run "$SKILL_DIR/scripts/letta_fs_to_memfs.py" search --help
uv run "$SKILL_DIR/scripts/letta_fs_to_memfs.py" qmd setup --help
uv run "$SKILL_DIR/scripts/letta_fs_to_memfs.py" qmd query --help
Compatibility wrappers remain for older examples:
uv run --with pymupdf "$SKILL_DIR/scripts/ingest_documents.py" --memory-dir "$MEMORY_DIR" --corpus docs --source ./docs
uv run "$SKILL_DIR/scripts/search_corpus.py" --memory-dir "$MEMORY_DIR" --corpus docs --query "refund policy"
The ingest script uses PyMuPDF when it sees a PDF. Run it with uv run --with pymupdf ....
For scanned PDFs or complex tables, use the tools/extracting-pdf-text skill first, then ingest the extracted markdown/text file with this skill.
See references/design.md for design notes and edge cases.