← Back to context

Comment by vardhan1237

6 hours ago

Hi HN,

I built PaperPilot because I was frustrated by the privacy trade-offs of modern PDF utilities.

Whenever you need to split, merge, compress, or sign a confidential document (tax forms, legal contracts, medical paperwork) using online tools, your files are transmitted to a third-party server. Most "free" tools retain copies or run in closed-source cloud environments.

PaperPilot is a 100% zero-cloud, local-first engine written in pure Rust (built on top of lopdf, pdf-writer, and image). 0 bytes are ever sent to an external server.

Key aspects of the project:

1. Penta-Interface Architecture: Instead of building just another web app or CLI, the same core Rust operations run across 5 surfaces: - Terminal CLI: High-throughput local processing and bash scripting. - Local Desktop App: Native cross-platform GUI built with Tauri 2 and Svelte 5. - Client-Side Web: Runs 100% inside your browser via WebAssembly (https://usepaperpilot.com/). - REST / Gateway API: Standalone local daemon (localhost:7823) for local microservices. - Model Context Protocol (MCP): Connects local AI agents (Claude Desktop, Cursor, OpenCode) directly to local PDF tools so LLMs can inspect, redact, and sign PDFs on disk without cloud upload.

2. Capabilities (75+ Tools): - Standard operations: Merge, split, rotate, reorder, burst, booklet imposition, and N-up grid. - Privacy & Compliance: Local PII regex redaction (SSNs, cards, emails), metadata striping, and digital signature verification. - Document Extraction: PDF to structured Markdown tables (no coordinate loss), PDF to JSON, and pure-Rust layout analysis. - Offline RAG: Embedded vector store (libsql_vector) with an actionable visual citation canvas.

3. Performance & License: - Average operation latency is ~20ms to 130ms. - 100% Free and Open Source under the Apache 2.0 license.

The GitHub repository is at https://github.com/KrushnaVardhanReddy/PaperPilot and the browser-based WASM sandbox is live at https://usepaperpilot.com/.

I’d love to hear your feedback on the architecture, performance benchmarks, and any edge-case PDF formats we should test against!

Is there anything in this project that was not already easily available with command line tools?

  • Yes, it's wasm. So you can run it in any browser. Super useful when no cli. Example on friend phone

    • who doesn't need to merge and compress bunch of pdfs on a friend phone on a saturday morning

    • Yeah, it has to be a friend phone as mine has command line via ssh (and tailscale).