Fewer subscriptions.
More vibe-coding.

Open-source tools & agent skills to build the things you’re paying for.

Analyze PDF layout, extract content, and convert documents through a web interface or REST API.

Added 2026-10-07
Replaces
GitHub

What you can build

  • Code an intake tool that submits scanned PDFs for OCR and saves extracted text alongside each original file’s identifier.
  • Build a converter that takes table HTML from document analysis and outputs CSV files for spreadsheet review.
  • Use extracted table-of-contents data to create a web reader with chapter links into the original PDF.
  • Make a review page that pairs source Markdown with translated files from the service’s translation ZIP output.
  • Create a review queue that checks returned page segments for missing expected element types, such as titles or tables.

Try this prompt

Build a small PDF intake and review application around this service’s documented REST API. Accept a PDF and an intake identifier, submit it for analysis, and show the returned page segments and extracted text alongside the original-file reference. Add a review flag when expected content types are absent, and export a JSON review record. Preserve the original PDF and raw service response; do not assume undocumented response fields or add external integrations.

Get started

  1. Check requirements

    Install Docker Desktop 4.25.0 or newer, or Docker Engine 20.10+ with Docker Compose 2.0+. Python 3.10+ is listed for local development.

  2. Start the service

    Follow the repository’s Quick Start and use its Make `start` target or the documented `just start` alternative. GPU support is optional; NVIDIA Container Toolkit is required for GPU use.

  3. Choose an interface

    Open the documented Gradio web UI at localhost:7860 or use the REST API at localhost:5060. The README’s API Reference documents analysis, text extraction, and table-of-contents endpoints.

License & notes

Apache-2.0The software is Apache-2.0 licensed and may be used commercially subject to its license obligations. Hosting and compute are your responsibility; model downloads and storage require local resources. GPU support is optional, and CPU processing is documented. Translation uses Ollama models, which require additional local or hosted compute. No dollar prices are provided.

  • Analysis can require substantial disk space for models and dependencies; the README lists 10 GB and 2 GB RAM minimums. GPU is optional, and CPU processing is documented as slower.
  • Translation requires an available Ollama model and an output file for ZIP responses. Translation quality depends on the selected model.
  • The README describes table and formula extraction, but extraction quality and downstream CSV conversion require validation on your documents.
  • Apache-2.0 permits commercial use; redistribution requires a license copy, notices, and prominent notices for modified files.

Ollama

Project182.4K

Run open models on your machine and connect them to applications through a REST API.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

D3

Project113.8K

A low-level JavaScript toolkit for custom, data-driven graphics in SVG, Canvas, and HTML.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Supabase

Project111.2K

Build Postgres-backed apps with authentication, APIs, realtime, storage, and functions.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Whisper

Project110.1K

Build speech transcription, language identification, and translation workflows with an open-source model.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Playwright

Project97.2K

Build cross-browser end-to-end tests and browser automation scripts with one API.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Puppeteer

Project95.7K

Build JavaScript workflows that control Chrome or Firefox.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Uptime Kuma

Project92.2K

Self-hosted checks for websites, network services, DNS, containers, and push monitors.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

PaddleOCR

Project90.7K

Build OCR and document-parsing workflows that turn images and PDFs into structured data.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Mermaid

Project90.6K

Create editable diagrams from Markdown-inspired text for documentation and JavaScript applications.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Syncthing

Project89.2K

Synchronize files between two or more computers, then adapt local workflows around those folders.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Netdata

Project80.8K

Open-source, real-time infrastructure monitoring with per-second metrics, anomaly detection, and alerting.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Hoppscotch

Project80.6K

Develop APIs with reusable requests, collections, environments, and response tests.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Grafana

Project77.1K

Query, visualize, and alert on telemetry across data sources.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Tesseract OCR

Project76.8K

An open-source OCR engine for extracting text from images and building document workflows.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Apache Superset

Project75.1K

Explore SQL data, build visualizations, and create dashboards with an extensible open-source BI platform.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

reveal.js

Project72.4K

An open-source HTML presentation framework for building browser-based slide decks.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Vaultwarden

Project68.6K

Self-hosted Bitwarden-compatible server for personal and organization password vaults.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Docling

Project68.5K

Convert diverse documents and media into structured content for tools you build.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Apache ECharts

Project67.5K

Build interactive, customizable charts for browser applications.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

AnythingLLM

Project66.8K

Build a desktop or self-hosted AI workspace for document chat, agents, and recurring tasks.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Docusaurus

Project66.4K

Build and customize websites for project documentation, blogs, and support pages.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Prometheus

Project66.4K

Collect, query and alert on metrics from your services and systems.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Traefik

Project65.1K

An HTTP reverse proxy and load balancer that updates service routes from infrastructure providers.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

FFmpeg

Project64.8K

Build workflows for inspecting, converting, filtering, and streaming audio and video.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Scrapy

Project64.6K

Build Python crawlers that extract structured data from websites.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Memos

Project63.6K

A self-hosted Markdown timeline for capturing, finding, and selectively sharing notes.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Coolify

Project62.7K

Deploy applications, databases, and services on servers you control.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

PocketBase

Project61.3K

A self-hostable Go backend with embedded SQLite, realtime subscriptions, and built-in user and file management.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Pi-hole

Project61.2K

Self-hosted DNS sinkhole for blocking unwanted content across a network.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Penpot

Project60.8K

Design and prototype digital products with collaboration, open formats, and programmable workflows.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Plane

Project60.5K

Open-source project management for issues, cycles, modules, roadmaps, and team documentation.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Rclone

Project60.2K

Copy, sync, check, mount, and serve files across local storage and cloud providers.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Build application search with full-text, semantic, or hybrid retrieval.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Odoo

Project54.9K

A modular suite of open-source business apps that can be combined into an ERP.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

PDF.js

Project54K

Build web-based PDF viewers and custom document workflows on an HTML5 PDF rendering platform.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

DBeaver

Project52K

A cross-platform desktop client for querying, inspecting, and moving database data.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Huginn

Project50K

Build self-hosted agents that monitor the web, process events, and take actions.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Explore business data with visual questions and SQL, then turn analysis into interactive dashboards.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

LocalAI

Project49.4K

Run AI models on your own hardware and access text, vision, and audio capabilities through a unified API.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide

Slidev

Project49K

Create developer-focused presentations from Markdown, with code demos, interactive components, presenter tools, and export options.

Added 2026-10-07
Replaces
GitHub

Open the guide for build ideas and setup.

Open guide
Show more

Submit project