PaperMind app icon

PAPERMIND  ·  MACOS  ·  APP STORE + DIRECT DOWNLOAD

Private AI for your documents.

Search, chat, and explore your files with a local AI workspace that never sends a byte to the cloud. Hybrid retrieval across 91+ formats, native OCR, and real citations — all running on your Mac.

Try Free for 14 Days See How It Works

macOS 12+  ·  Apple Silicon & Intel  ·  No account required

PaperMind app interface showing document search and AI chat
91+
File formats supported
4 OCR
Engines including macOS Vision
Hybrid
BM25 + Vector + Reranking
Zero
Data sent to the cloud
How It Works

Import. Search. Understand.

Three steps to turn any pile of documents into a searchable, conversational knowledge base.

1. Import

Drop a folder or pick files. PaperMind parses PDFs, Word docs, spreadsheets, presentations, code, images — 91+ formats. OCR kicks in automatically for scanned pages.

2. Search

Hybrid retrieval combines keyword precision with semantic understanding. Type a question or a phrase — PaperMind finds the right passages even when wording doesn't match.

3. Ask AI

Have a conversation grounded in your documents. PaperMind cites exact sources, so you always know where an answer came from. Use local models or your preferred cloud provider.

Format Coverage

If you can read it, PaperMind can index it

91+ document types parsed natively. No plugins, no converters, no excuses.

PDF DOCX XLSX PPTX Markdown HTML CSV EPUB YAML TOML JSON Source Code Images (OCR) Plain Text RTF + 75 more

Scanned documents? No problem. PaperMind ships with four OCR engines — including Apple's native Vision framework — so even photographed receipts, old contracts, and handwritten notes become searchable text.

Under the Hood

The most accurate desktop document AI

PaperMind doesn't just do vector search. It runs a full retrieval pipeline that rivals enterprise tools — on your laptop.

1
Hybrid Search
Your query hits both a BM25 keyword index and a dense vector store simultaneously. Results are merged via Reciprocal Rank Fusion for the best of both worlds.
2
HyDE + Query Expansion
PaperMind generates a hypothetical answer to your question and uses it to improve the vector search. Your original query is also expanded with related terms to cast a wider net.
3
Cross-Encoder Reranking
A dedicated reranking model scores every candidate passage against your query. The most relevant chunks rise to the top — dramatically improving precision.
4
Grounded Answer with Citations
The LLM receives only the highest-scoring passages as context and generates an answer with page-level source citations. You always know where the information came from.
Conversational AI

Chat with your entire library

Ask questions in plain language. PaperMind grounds every answer in your documents and cites the exact source.

You
What are the key findings on hybrid retrieval performance?
PaperMind
Based on your documents, hybrid retrieval (BM25 + dense vectors with RRF fusion) outperforms dense-only search by 23% on recall@10 and 18% on precision. The gains are most significant for domain-specific terminology where exact keyword matching catches what embeddings miss.
Research Paper, p.12 Literature Review, p.34
You
Does reranking improve those numbers further?
PaperMind
Yes. Adding a cross-encoder reranker on top of hybrid search pushes precision up another 11%, with the largest gains on ambiguous or multi-hop queries.
Research Paper, p.18

Works with Ollama (local), OpenAI, Anthropic Claude, and llama.cpp models.

Privacy

Your documents never leave your Mac

This isn't a marketing claim — it's how the architecture works.

Offline by Default

Parsing, OCR, embedding, indexing, and search all run on your machine. No internet needed. No cloud accounts. No telemetry.

Zero Data Collection

Apple's PrivacyInfo manifest confirms it: no tracking, no analytics, no collected data types. We don't know what you index and we don't want to.

Offline Licensing

License verification happens locally with a signed key — no phone-home, no activation servers. Works on air-gapped machines and behind firewalls.

Workspaces

One app, many knowledge bases

Create separate workspaces for different projects, clients, or research topics. Each workspace has its own index, settings, and chat history.

📚

Research Library

Papers, literature reviews, and study notes in one searchable collection.

⚖️

Case Files

Contracts, briefs, and precedents — instantly searchable with exact citations.

💼

Client Projects

Proposals, reports, and correspondence. Switch context in a click.

Available in 10+ languages: English, French, German, Spanish, Portuguese, Japanese, Korean, Italian, Dutch, Arabic, and Chinese.

Pricing

Pay once, own it forever

No subscriptions. No recurring charges. Start with a 14-day free trial.

Free Trial

$0

14 days, full access, no card required.

  • All features unlocked
  • All file formats
  • Hybrid retrieval + reranking
  • All OCR engines
Start Trial

Personal

$49 once

One-time purchase. Lifetime updates.

  • 3 workspaces
  • 500 documents per workspace
  • Dense retrieval
  • 2 LLM providers
  • Email support
Buy Personal
Best Value

Professional

$99 once

One-time purchase. Everything unlocked.

  • Unlimited workspaces
  • Unlimited documents
  • Hybrid retrieval + HyDE + reranking
  • All OCR engines
  • All LLM providers
  • All parsers & formats
  • Priority support
Buy Professional

Launch discount: 30% off for the first 500 customers. Also available on the Mac App Store.

FAQ

Common questions

No. Every document you import is processed, indexed, and stored entirely on your Mac. PaperMind works offline by default. The only time data leaves your machine is if you explicitly choose a cloud LLM provider (OpenAI, Anthropic) for the chat feature — and even then, only the relevant text chunks are sent, never full documents.
PaperMind supports Ollama for running local models (Llama, Mistral, Gemma, and more), llama.cpp for embedded GGUF models, and cloud providers including OpenAI and Anthropic Claude. You can switch models at any time — there's no lock-in.
Personal gives you 3 workspaces, 500 docs each, dense-only retrieval, and 2 LLM providers — great for individual use. Professional unlocks unlimited workspaces and documents, hybrid retrieval with HyDE and cross-encoder reranking, all 4 OCR engines, all LLM providers, and priority support. Both are one-time purchases.
Not at all. PaperMind is designed for non-technical users. Drop files in, search, ask questions — that's it. The advanced retrieval pipeline runs automatically behind the scenes. If you do want to get technical, there's an expert mode with a performance dashboard and fine-grained pipeline controls.
PaperMind is currently available for macOS (Apple Silicon and Intel). Windows and Linux builds are planned for a future release. Sign up for our newsletter to be notified when cross-platform support launches.
After 14 days, PaperMind locks access until you purchase a license. Your data and workspaces are preserved — nothing is deleted. Once you buy a license (Personal or Professional), everything unlocks immediately and you're set for life.

Ready to try PaperMind?

14-day free trial. No account, no credit card, no cloud.

Download on App Store Direct Download (.dmg)
macOS 12+ Apple Silicon & Intel 14-day trial No account required