Unstract
Unstract is an open-source, no-code platform purpose-built for extracting data from unstructured documents using LLMs, w
Last Updated
2026-06-16
GitHub Stars
6,661
About Unstract
Our Verdict
A coding agent that is open-source and self-hostable backed by 6.7k GitHub stars. Unstract is an open-source, no-code platform purpose-built for extracting data from unstructured documents using LLMs, with high accuracy. Easily deploy API and ETL pipelines for your unstructured….
Features
Detailed Ratings
Pros & Cons
Pros
- Open-source — fully self-hostable and auditable
- Active community with 6.7k GitHub stars
- Git ### Run Locally
- Visit [http
Cons
- Requires technical setup; less hand-holding than managed alternatives
- Limited third-party reviews and benchmarks
Use Cases
Who Is It For?
Teams and individuals looking for software development automation who value open-source flexibility and control.
Frequently Asked Questions
What is Unstract?
Unstract uses LLMs to extract structured JSON from documents — PDFs, images, scans, you name it. Define what you want to extract using natural language prompts, and deploy as an API or ETL pipeline.
How much does Unstract cost?
Unstract is open-source and free to self-host. See https://github.com/Zipstack/unstract for installation instructions.
Is Unstract open source?
Yes — Unstract is open source with 6.7k stars. The source code is on GitHub at https://github.com/Zipstack/unstract.
Who should use Unstract?
Teams and individuals looking for software development automation who value open-source flexibility and control.
Related Agents
500 AI Agents Projects
The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries
E2B
E2B Gives AI Agents Secure Computers with Real-World Tools
Front End Checklist
Trusted front-end quality rules for humans and AI agents
Open Design
Open Design is the official open-source, local-first Claude Design alternative