Quick answers.

Leapable gives your AI (Claude Code, Cursor, Cline, etc.) a local knowledge base it can search. You ingest your documents — PDFs, notes, transcripts, anything — and your AI can then answer questions with cited passages from them. It runs locally on your machine via Docker; your data never leaves your device unless YOU publish a database to the marketplace.

No. You install it once (one-click .dmg / .exe / .deb), connect it to your AI (one command), then just talk to your AI. The How to use page has copy-paste prompts for every common task.

Realistic. Installer: ~3 minutes. Docker image pull: ~5 minutes (one-time). Connect AI: 30 seconds. Create a database and ingest 10 markdown files: ~2 minutes. First query: instant. PDFs take longer because of OCR (~1 page per second on cloud).

Anything that speaks the Model Context Protocol (MCP). Confirmed working: Claude Code, Cursor, Cline, Continue, Claude Desktop, Warp. If a new client supports MCP, Leapable will work with it.

50 queries per month, unlimited local processing of .md and .txt files, local embeddings + cross-encoder reranking, full semantic search, and free-tier content on the marketplace. No credit card required.

1 credit = 5¢ face value. It covers 1 query to any expert on the marketplace OR up to 5 pages of cloud OCR (for PDFs and images). OCR billing rounds up — a 6-page doc is 2 credits, a 24-page doc is 5 credits.

Subscribers get monthly credits included AND 50% of unused credits roll over at cycle reset. One-off packs are exactly face-value (5¢/credit) with no rollover. If you query regularly, a plan is meaningfully cheaper.

Yes. Upgrades take effect immediately — Stripe prorates the billing, and we grant prorated bonus credits for the rest of the cycle. Downgrades also take effect immediately, with unused time from the higher plan credited to your next invoice. Your current credit balance is untouched; the smaller monthly grant just applies on the next cycle reset.

Yes. Cancellation takes effect at the end of the current billing period — you keep access until then. No refunds on partial months. One-off credit packs never expire so long as you remain an active account.

All payments go through Stripe. We never see or store your card number. Stripe supports every major card, Apple Pay, Google Pay, and several regional methods. The "Secure Stripe" lockup on every checkout page is real — click it to verify.

No, unless you (a) ingest PDFs or images that need OCR — those pages go to our serverless GPU worker for text extraction then return — or (b) you explicitly publish a database to the marketplace. Pure text files (.md, .txt) never leave your machine; embeddings are computed on your local CPU / GPU.

They're uploaded to a temporary storage bucket (Fly Tigris), processed by our RunPod serverless GPU worker (marker-pdf + Chandra OCR), the extracted text is returned to your Docker container, and the worker's storage is wiped. We don't store your PDFs or OCR output on our infrastructure.

Yes. Ask your AI: "delete the <name> leapable database and all its documents, chunks, embeddings, and provenance." It's a single tool call and it's permanent. You can also delete individual documents.

Ask your AI: "back up the <name> database to ~/backups/". Or use leapable_db_backup directly. The backups include all documents, chunks, embeddings, and provenance.

PDF, DOCX, PPTX, XLSX, TXT, MD, HTML, EPUB, images (PNG/JPEG/TIFF — OCR'd), and more. Basically anything with text. 18 formats officially supported; others may work via fallback.

In practice, hundreds of thousands of documents. The local SQLite + vector store scales well. Query latency stays under ~200ms on 100k+ chunk corpora on a modern laptop.

Leapable runs BM25 keyword search + nomic-embed-text semantic search + a ms-marco cross-encoder reranker, all locally. Beats single-method search by a wide margin. Every answer cites the exact chunk + page it came from, so you can verify.

Yes — every retrieval carries the source document, the page number, and the exact chunk. Your AI can include citations inline. In the web dashboard, citations are clickable and open the original document at that page.

Yes — ask your AI for a cross-database search. It calls leapable_search_cross_db which semantic-matches across everything you've ingested and returns results ranked by relevance with the originating database.

Yes. Any database you've built can be published to the marketplace. You choose free or paid, per-query pricing, and an optional monthly paywall. Leapable keeps 30%, you keep 70%.

Stripe Connect. You onboard once (takes ~5 minutes — ID, bank, tax). We pay out monthly on the 1st, $10 minimum. Your Creator Studio dashboard shows holding, reserve (5% / 60-day hold), and payout history.

Same as every payment processor — it covers chargebacks and refunds. After 60 days with no disputes, it releases to your holding balance automatically.

Yes. Each database can have its own per-query credit price (0–20 credits, N=0 means free/open-source). Optionally bolt on ONE paywall per database (e.g. $29/mo unlimited access).

Check the Docker container is up: open your terminal and run curl http://localhost:4100/health. If that fails, restart the Leapable app. If it succeeds, restart your AI client and confirm the MCP is configured.

Common causes: (1) you're on free tier and hit the monthly quota — check your credit balance; (2) the PDF is password-protected — remove the password first; (3) the file is corrupted. Ask your AI: "retry failed docs in {name}".

Tell your AI: "rebuild embeddings for {name}". It'll re-embed the whole corpus against the latest model version.

Platform subscription = the monthly fee, regardless of usage. Credits are consumed per query/OCR page. If you want to stop being billed, cancel your subscription from Account & Plan. Unused credits stay on your account.

The How to use page has step-by-step prompts. For anything not covered, email support@leapable.ai — we answer within 24h.