ai-agent

paperless-ngx

Name: paperless-ngx
Author: paperless-ngx

A community-supported supercharged document management system: scan, index and archive all your documents

46,266 stars+195★ this week3,204 forksPythonUpdated 10/4/2026100% free · open source

What it does

Paperless‑ngx automatically scans, OCR‑processes, indexes and stores all your PDFs, images and docs in a searchable web UI.

When to use it

•You receive dozens of invoices, receipts or contracts each week and need a searchable archive without manual filing.
•Your team works remotely and you want a single, self‑hosted place to drop PDFs and instantly retrieve them by content.
•You need to automate document ingestion from a shared folder or email attachment and keep a compliance‑ready audit trail.

Ready-to-paste prompt

docker compose exec webserver paperless document add /usr/src/paperless/media/consume/invoice_2024_09_01.pdf --correspondent "Acme Corp" --tags "invoice,2024"

Heads up: The Docker containers run as the UID/GID you set in `.env` (PUID/PGID). If those IDs don’t have read/write permission on the host’s `./media` and `./consume` folders, imports will silently fail – make sure the directories are owned by the same user or set PUID/PGID to `0` for root (not recommended for production).

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/64d7fcbe-4694-43df-8920-b1571672690a && curl -fsSL https://workflowstacks.com/api/skills/64d7fcbe-4694-43df-8920-b1571672690a/claude-skill -o ~/.claude/skills/64d7fcbe-4694-43df-8920-b1571672690a/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How paperless-ngx works

Codeflow

Free to inspect

Paperless-ngx is a very large Python project (~109k lines across 628 code files, plus 158 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, GPL-3.0 license, has a test suite.

Size

Very large codebase

~109k lines · 628 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Python · Docker

No API keys detected

Python 62%TypeScript 30%HTML 7%SCSS 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
pyproject.toml
Dependencies and the commands it exposes
3
src/documents/__init__.py
Inside src/ — the main logic begins here

What's in each folder

src/Core code — the actual logic532 files

docs/Documentation51 files

src-ui/Folder706 files

docker/Deployment / infrastructure140 files

scripts/Helper scripts7 files

.github/CI / automation (GitHub Actions)25 files

.devcontainer/Editor / agent settings7 files

READMEHas testsDocumentedCI checksDocker readyGPL-3.0 licenseUpdated this month