Turn Obsidian into Claude context

An Obsidian vault can be a deep knowledge base, but pasting one note at a time loses links, folder context, and the supporting notes around an idea. Riflet gives you a local workflow for packaging Obsidian vaults into one clean file for Claude Projects.

Why Obsidian needs preparation before Claude

An Obsidian vault can be a deep knowledge base, but pasting one note at a time loses links, folder context, and the supporting notes around an idea.

Claude is strong for long-form analysis, research synthesis, and project planning when the source material is organized clearly. The result depends heavily on how cleanly your source material is grouped, labeled, and filtered before it reaches the model.

Step-by-step workflow

Point Riflet at your vault folder and select the notes, MOCs, and project folders that should shape the answer.

  • Add Obsidian vaults as a Riflet source.
  • Select MOCs, project notes, evergreen notes, research summaries, source notes, and short instruction files that explain naming conventions.
  • Use filters to remove stale exports, generated files, and unrelated background material.
  • Export one Markdown or text bundle and use it in Claude Projects.

What to include

For this workflow, prioritize MOCs, project notes, evergreen notes, research summaries, source notes, and short instruction files that explain naming conventions. Add a short instruction file at the top if the AI needs naming conventions, project goals, or constraints.

A full-vault dump is rarely the best context. Curate topical folders, current notes, and project maps so the model does not spend tokens on unrelated daily notes.

Getting the bundle into Claude Projects

Claude Projects keeps uploaded material in Project knowledge. Open the project and add the bundle to Project knowledge, where it stays attached to every conversation in that project instead of being re-uploaded per chat. It accepts plain text, Markdown, PDF, and common document formats, so a Markdown or plain-text export from Riflet needs no further conversion.

Project knowledge shows a capacity indicator rather than a fixed file count. One well-structured bundle uses that capacity far more efficiently than a dozen overlapping uploads, because Claude never has to reconcile two copies of the same fact.

Updating means deleting the old entry and adding the new bundle. Keeping the project down to one file is what turns that into a ten-second job instead of an audit.

Token budget advice

Riflet lets you check the bundle against Claude Opus 5's 1,000,000-token context window before export. Keep room for your actual question and for the model's answer.

If the bundle is too large, remove files that merely repeat what another file already explains. Context quality usually beats context volume.

Honest limitation

Riflet does not push live updates into Claude. It creates the context file. When the source changes, re-export and upload the new bundle yourself.

Build your AI context file with Riflet

Select the sources that matter, check the token budget, and export one clean file for the AI you already use.

Download Riflet free

Frequently asked questions

Can I use this Obsidian to Claude bundle in more than one AI tool?

Yes. Riflet exports plain text or Markdown, so the same context file can be used in Claude, ChatGPT, Gemini, Perplexity, or a local model if that tool accepts pasted text or file uploads.

Does Riflet automatically update the AI after my files change?

No. Riflet is deliberately export-based. When your files change, reopen the workspace, let Riflet reapply the saved sources and filters, export a fresh bundle, and upload it where you want to use it.

How do I avoid giving Claude too much context?

Start with the decision or task, then include only the files that would help a smart human answer it. Use Riflet's token count to remove stale, duplicated, generated, or background-only files before exporting.

Do my files leave my computer when Riflet builds the bundle?

Riflet processes selected files locally. Your content leaves your machine only if you choose to paste or upload the exported bundle into an AI product.