unstract
LLM-Driven Extraction of Unstructured Data for API Deployments and ETL Pipeline Workflows
GraphCanon updated Oct 4, 2026 · GitHub synced Sep 20, 2026
56views this month
Decision brief
Unstract is a Python-driven tool for transforming unstructured data into structured formats using OCR, PDF extraction, and other techniques to integrate with APIs and ETL workflows under AGPL-3.0 license.
Good fit when
- You prioritize open-source contributions and require the flexibility of the AGPL-3.0 license.
- Your project involves complex, generative AI tasks like JSON extraction from unstructured documents.
Avoid when
- Your workflow strictly adheres to closed-source software management policies and requires proprietary control.
- Projects needing direct integration with commercial data processing services incompatible with AGPL-3.0 licensing.
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (1d since push)
- As of Sep 20, 2026
- Provenance
- Not a fork · Organization account
- As of Sep 20, 2026
- Security (OSV)
- No lockfile
- As of Oct 4, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install unstractSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A Python-based repository enabling the use of LLM-driven techniques for extracting structured data from unstructured sources like documents, employing OCR, PDF extraction, and more.
Capability facts
- Languages
- python
Source: github.language+pyproject.toml · Sep 20, 2026
Categories
Tags
README
System Requirements & Prerequisites Linux or macOS (Intel or M series) Docker & Docker Compose 8 GB RAM minimum Git Pull and run docker containers with a specific version tag. ./run platform.sh v v0.1.0 Build docker images locally as a specific version tag. ./run platform.sh b v...
For agents
This page has a .md twin and JSON over the API.