Document Indexing with QMD
Your ClawOps bot includes a document index powered by QMD. QMD lets your OpenClaw assistant search files and memory before it asks an AI model to answer, which keeps responses faster and reduces the amount of context sent to the model.
Open it from Dashboard -> Content -> Documents.
What QMD indexes
The exact collections can vary by bot and installed companions, but a typical ClawOps instance can include:
- Agent memory, session notes, daily logs, and context the assistant writes down.
- Agent learnings, rules your assistant has learned from previous mistakes or preferences.
- Previous conversations, searchable session transcripts when enabled by OpenClaw memory.
- User files, markdown and text files saved in
~/files. - Companion collections, specialist memory, such as Entertainment Buddy taste profiles.
- Your own collections, folders you ask the bot to index.
The dashboard shows the live collection names returned by qmd status.
The Documents panel
The status card shows:
- Collections, how many named QMD collections are registered, plus their names.
- Documents, how many files are currently indexed.
- Last Indexed, when the index was last refreshed.
- Auto-indexing active, whether ClawOps can see recent automatic indexing activity.
Use Update Now when you have just added files and want them searchable immediately.
How indexing works
QMD has two layers:
- Keyword index, fast text search for exact and close matches.
- Embeddings, semantic search for meaning-based matches.
ClawOps keeps the index fresh automatically. The dashboard can also trigger a full refresh, which runs the QMD update and embedding steps on your VPS.
Add a collection
Ask your bot naturally:
Index all markdown files in ~/my-notes
Your assistant can register that folder as a QMD collection so future questions can search it. Markdown and text files work best because they are easy for QMD and the model to quote, summarize, and reason over.
Search indexed documents
You can ask broad questions:
Search my docs for information about AI models
Or ask direct questions:
What’s in my workspace about configuration?
Your assistant searches QMD first, then sends the relevant snippets to the active AI model. This is more efficient than loading an entire folder or long document into context.
Files vs Documents
The Files tab is for browsing, previewing, downloading, and deleting files saved on your VPS.
The Documents tab is for the searchable QMD index. A file can exist in Files before it has been indexed. If you need it searchable right away, click Update Now in Documents.
Privacy
The QMD index lives on your dedicated VPS. Search happens there first. When an AI model answers a question, it receives only the selected context your assistant sends along with the prompt.
That means QMD reduces token usage and limits unnecessary context sharing, but it does not make model calls disappear. The model still receives the relevant snippets needed to answer.
Troubleshooting
If a document is not showing up in search:
- Confirm the file is markdown or text.
- Confirm it is in a folder QMD indexes, such as
~/filesor a collection you added. - Click Update Now.
- Ask the bot to search for a specific phrase from the file.
- If the dashboard shows auto-indexing inactive, restart the gateway from Dashboard -> Settings and try again.
For files that you only need to download or preview, use the file browser instead.