unstract
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
Turning PDFs, scans and images into structured JSON with natural-language prompts, deployed as an API or an ETL pipeline into a warehouse.
AGPL-3.0 licensing is a problem for how you distribute your own product.
About 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.
Copy the value of ENCRYPTION_KEY from backend/.env or platform-service/.env to a secure location.
Destinations: Snowflake, Amazon Redshift, Google BigQuery, PostgreSQL, MySQL, MariaDB, SQL Server, Oracle
unstract is an open-source project written primarily in Python, with 7.3k stars on GitHub. It was last updated in September 2026.
unstract vs. the alternatives
All 26 alternatives →| Record | Stars | Pricing | ||
|---|---|---|---|---|
| unstractthis listing | 7.3k | Python | AGPL-3.0 | Open source |
| firecrawl | 186k | TypeScript | AGPL-3.0 | Open source |
| Scrapling | 84k | Python | BSD-3-Clause | Open source |
| TrendRadar | 63k | Python | GPL-3.0 | Open source |
| BettaFish | 42k | Python | GPL-2.0 | Open source |
| khoj | 38k | Python | AGPL-3.0 | Open source |
