Skip to main content
AdOpenFree logoPromote your productReach more potential users and drive product growth and revenue.Advertise
Favicon of PaperPilot

PaperPilot

Free Listing

PaperPilot is a local AI copilot for documents: a pure-Rust PDF and document toolkit with MCP, CLI, browser, desktop, and local REST surfaces. Files stay on your machine.

Visit KrushnaVardhanReddy/PaperPilot

Overview

PaperPilot is a PDF and document toolkit written in Rust. The same engine runs as an MCP server for coding agents, a CLI for batch workflows, a browser/WASM tool, a Tauri desktop app, and a local REST API. It supports operations such as merging, splitting, OCR, compression, page layout, extraction, and security analysis. Its stated design goal is local processing: files are processed on the machine or in the browser rather than uploaded to a cloud service.

Key Features

  • One Rust core shared across MCP server, CLI, browser/WASM, desktop app, and local REST API surfaces.
  • PDF organization and layout: merge, split, rotate, delete, reorder, extract pages, booklet imposition, N-up grids, and poster tiling.
  • Optimization and extraction: lossy compression, stream deduplication, structured text, detected Markdown tables, and pure-Rust OCR.
  • Security and analysis tools: watermarking, signature validation and removal, PII scanning, deep sanitize, and malformed-input fuzzing.
  • Office data conversion: Excel to JSON and Excel to CSV.
  • MCP-compatible local stdio server for clients such as Codex, Claude Code, Kimi Code, Pi, Claude Desktop, and Cursor.

Use Cases

  • Give coding agents and MCP clients local PDF merge, split, OCR, and compression tools.
  • Run batch or scripted document workflows through the CLI.
  • Use zero-install browser tools for local PDF operations without uploading files.
  • Call document operations from Python, Node, or n8n through the local REST API.

Getting Started

  • Download paperpilot-mcp from Releases, add it to claude_desktop_config.json under mcpServers.paperpilot.command, restart Claude, then try a prompt such as 'Merge these two PDFs and compress the result.'
  • Build from source with cargo build --release -p paperpilot-cli -p paperpilot-mcp -p paperpilot-gateway.
  • For the desktop app, run pnpm install and pnpm tauri dev in apps/desktop.
  • Use CLI commands such as paperpilot merge --inputs doc1.pdf doc2.pdf --output merged.pdf.

Deployment & Requirements

  • Rust 1.75 or newer is required for source builds.
  • Node.js and pnpm are required for the desktop app.
  • The project states no Chromium, C++ runtime, or cloud calls are required.

Before You Adopt

  • License: Other. Review its terms before using, modifying, or distributing the project.
  • The current documented feature set is v0.6, which signals an early-stage release.
  • The project emphasizes privacy by keeping document processing local to the user's machine.
  • Building the desktop app adds Node.js and pnpm as external toolchain dependencies.

Comments

Sign in to leave a comment.

More like PaperPilot

Favicon of GBrain

GBrain

Free ListingStars: 31.9K

A controllable shared memory layer for AI agents

MCP Servers & Tool Connectors

GBrain is a self-hostable memory layer for AI agents that stores sourced facts, supports corrections, and offers keyword, semantic, graph, and optional cited synthesis retrieval.

Favicon of HA-MCP

HA-MCP

Free ListingStars: 5.6K

Configure and automate Home Assistant with AI

MCP Servers & Tool Connectors

HA-MCP is a Model Context Protocol server that lets AI assistants like Claude and ChatGPT interact with Home Assistant. It supports device control, state queries, automations, dashboards, history, backups, and more through natural language.

Favicon of PipesHub

PipesHub

Free ListingStars: 4K

Open-source, permission-aware context for AI agents

MCP Servers & Tool Connectors

PipesHub is an open-source context layer for AI agents that turns company knowledge from connected business systems into permission-aware search and cited answers, with self-hosted deployment and SDK/MCP access.