Unstract is an open-source project built for developers and data engineers.

Does Unstract have a free plan?

Yes — Unstract is open source under the AGPL-3.0 license and free to use.

What platforms does Unstract run on?

Unstract runs on the web and API. It can also be self-hosted.

Is Unstract still maintained?

The GitHub repository shows 133 commits in the last 90 days.

Who develops Unstract?

Unstract is developed by Unstract Community.

When did Unstract launch?

Unstract first shipped in 2024.

Is Unstract open source?

Yes — Unstract is open source under the AGPL-3.0 license, developed on GitHub.

Back to the index

Unstract

Name: Unstract
Author: Unstract Community

unstract.comInfrastructure

Unstract is an open-source platform that enables users to extract structured data from unstructured documents using large language models. It offers a no-code interface, API endpoints, and flexible deployment options, supporting use cases like invoice and table extraction for developers and data teams.

Open SourceAGPL-3.0WebAPISelf-hostedCloud-managed

Visit unstract.com

6.7kstars

630forks

10features

2024since

Overview

10 features

Unstract is an AI project. It focuses on automating accurate extraction of structured data from unstructured documents using AI. Unstract is an open-source project aimed at developers and data engineers. Unstract is open source under the AGPL-3.0 license. It runs on the web and API, and it can be self-hosted.

It is developed by Unstract Community, and it first shipped in 2024. Development happens publicly on GitHub with 6.7k stars and 133 commits in the last 90 days. Among its 10 catalogued features are document extraction, no-code interface, and API integration. It exposes integrations via an MCP server and a public API.

Summary written by a language model from the project’s public pages.

Document extraction
No-code interface
API integration
Human-in-the-loop
ETL pipelines
Prompt engineering
Table extraction
Invoice extraction
Bank statement extraction
Flexible deployment

Built with & integrations

Framework

WordPress

Hosting

Cloudflare

AI providers

multiple

Connectors

MCPAPI

Runs on

BrowserAPI-onlySelf-hostedCloud-managed

Detected from

WordPress: /wp-content/ in the HTML · /wp-json/ in the HTML · /wp-includes/ in the HTML
Cloudflare: cf-ray header · cf-cache-status header

Trust & compliance

License

AGPL-3.0

Verified signals

HTTPSOpen SourceFree tierGitHub · ★ 6.7kActive maintenance

Indexing history

What PulseGate has recorded for this listing

Indexed3 Jul · 15:28 UTC
What we learned building a multi-agent PDF table extractor verified against its public source
Source: PulseGate · Open
Indexed1 Jul · 04:32 UTC
We Split PDF Table Extraction Across 6 Agents and a Codegen Step verified against its public source
Source: PulseGate · Open

Frequently asked questions about Unstract

What does Unstract do?: Unstract focuses on automating accurate extraction of structured data from unstructured documents using AI. It is catalogued under AI on PulseGate.
Who is Unstract for?: Unstract is an open-source project built for developers and data engineers.
Does Unstract have a free plan?: Yes — Unstract is open source under the AGPL-3.0 license and free to use.
What platforms does Unstract run on?: Unstract runs on the web and API. It can also be self-hosted.
Is Unstract still maintained?: The GitHub repository shows 133 commits in the last 90 days.
Who develops Unstract?: Unstract is developed by Unstract Community.
When did Unstract launch?: Unstract first shipped in 2024.
Is Unstract open source?: Yes — Unstract is open source under the AGPL-3.0 license, developed on GitHub.

At a glance

Pricing: Open Source
Platforms: Web
Languages: English
Open source: Yes · ★ 6.7k
License: AGPL-3.0
Built for: developers and data engineers
Model: Open source
Solves: Automating accurate extraction of structured data from unstructured documents using AI.

Registered as

GitHub: Zipstack/unstract

Developer

Unstract Community

Community-driven

GitHub

Open source

View on GitHub

Stars: 6,680
Forks: 630
Open issues: 88
Last commit: 30 Jun 2026
Commits 90d: 133
Contributors: 28
Authorship: Community-driven
Default branch: main
Latest release: v0.177.5 · 30 Jun 2026

Index record

Identity confidence: Medium · 68
Indexed: 1 Jul 2026
Lifecycle: Alive
Last seen: 3 Jul 2026

Identity audit (12)

Slug: we-split-pdf-table-extraction-across-6-agents-and-a-codeg-unstract-com
Lifecycle last checked: 8 Aug 2026
Verification state: Indexed for public listing
Listing state: Listed: yes
Index status: Included in index
Latest evidence snapshot: 3 Jul 2026
Timeline basis: Indexed-at chronology. This listing's first-seen date was written by the catalog backfill, not observed here, so it is not treated as a sighting.
Name from: Written by a language model from the project's public pages.
Category from: Assigned by a language model.
Summary from: Written by a language model from public pages.
Languages from: Detected by a language model, checked against the page's own declaration.
Canonical URL: https://unstract.com/

Ship this? Send a correction — no account, and you get a link to follow it.

Similar projects

Closest matches by what these projects do

PDFStractpdfstract.com