Agent access
Loofah is your personal knowledge vault for notes, research, decisions, and meeting content. We recommend the loof CLI for agents that can run shell commands. It gives your agent one interface for searching, reading, and saving knowledge, with structured JSON output.
Start with the skill
Section titled “Start with the skill”Copy the skill installation prompt into your agent. It installs the instructions for using the CLI and asks the agent to remember Loofah as your personal knowledge vault, using the skill through loof whenever you want to save or retrieve knowledge.
The skill and the CLI are separate: your agent also needs the loof executable available in its environment. The prompt checks CLI and vault access and explains any remaining setup. Once ready, follow CLI for agents for command examples.
Choose an interface
Section titled “Choose an interface”Both interfaces work on the same vault. A session may be a recorded meeting or a standalone note containing research, decisions, project context, or material brought in from another tool.
| Interface | Use it when | Output |
|---|---|---|
| CLI (recommended) | The agent can run shell commands; supports reading and writing | JSON with --json, or readable terminal output |
| MCP (optional) | You want a read-only connection, or your client supports MCP but cannot run shell commands | Structured tool results and resources |
A reliable workflow
Section titled “A reliable workflow”- List recent sessions or search with a short phrase.
- Take the session ID from the result. Do not guess it.
- Read session details before fetching a transcript.
- Fetch the transcript only when the notes and summaries are not enough.
- When the user asks to keep new work, create a session with clear authorship, useful tags, and the source artifact when appropriate.
The skill follows this workflow through the CLI, even when MCP is connected. MCP remains available when you explicitly choose it or your agent cannot run the CLI; it cannot save or edit notes.
Every vault also carries a copy of the vault guide for agents at its root as AGENTS.md, so agents that land in the folder without this documentation still learn the layout and the rules.
What each interface can write
Section titled “What each interface can write”Use these interfaces instead of crawling the vault. They apply the same rules for canonical notes, summaries, speaker names, and transcript rendering.
MCP cannot write: no MCP tool creates or edits a note, action item, or session. The CLI can: sessions new creates a standalone note, sessions note --set and --append edit a note body, sessions attach keeps a source file with the note, import turns an audio file into a new session, and transcribe replaces a session’s transcript. sessions export writes only to the file you pass with --output, and replaces an existing file only when --force is passed. Agents creating sessions must always pass --author <agent-name> so the note is marked as not written by the vault owner.
Bring knowledge in from other tools
Section titled “Bring knowledge in from other tools”The CLI is intentionally source-agnostic. If an agent is authorized to read a document, research result, issue tracker, knowledge service, or generated deck, it can turn the useful content into Markdown and store it as a new session. There is no separate importer to build for every source.
For example, after researching a topic or extracting the important findings from a deck, an agent can run:
loof --json sessions new --title "Research: customer onboarding" --note findings.md --tag research --author claude-codeloof --json sessions attach SESSION_ID onboarding-research.pdfThis keeps the synthesized note searchable while preserving the source artifact beside it. The agent must still follow the source tool’s permissions and should only write when the user asks it to.