Upload any document, get a structured Markdown filesystem. AI agents mount and query it with standard Unix tools.
How it works
Step 01
Drop in PDFs, contracts, books, or regulations via the dashboard or API.
Step 02
Shelv converts documents into clean Markdown with a logical file hierarchy.
Step 03
AI agents mount the shelf and interact with files using standard Unix tools.
Features
Every document becomes clean, structured Markdown — the universal format for LLMs.
Navigate parsed documents like a filesystem. ls, cat, grep — it just works.
Full programmatic access to upload, parse, and retrieve shelves and their contents.
Get notified when parsing completes so your agents can start working immediately.
Define extraction schemas for recurring document types — contracts, invoices, reports.
Documents and parsed output stored durably in S3 with configurable retention.
Developer experience
A few lines of curl is all it takes. Upload a document, wait for the webhook, and start reading structured Markdown files through the API.
$ curl https://api.shelv.dev/v1/shelves/shv_9k2f/files \
-H "Authorization: Bearer sk_live_..."
[
{ "path": "/contract/summary.md", "size": 2841 },
{ "path": "/contract/parties.md", "size": 1205 },
{ "path": "/contract/terms/payment.md", "size": 3102 },
{ "path": "/contract/terms/termination.md","size": 1847 }
]
$ curl https://api.shelv.dev/v1/shelves/shv_9k2f/files/contract/summary.md \
-H "Authorization: Bearer sk_live_..."
# Contract Summary
**Parties:** Acme Corp ↔ Widget Inc
**Effective Date:** 2025-01-15
**Term:** 24 months, auto-renewing
...Pricing
Start free, scale as you grow.
No credit card required
500 pages included