LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
Unstract turns information in documents such as PDFs, images, and scans into structured JSON by using natural-language extraction prompts. It is for teams that need document data in databases or automated pipelines, and its catalogue add-ons connect the platform to coding agents and workflow tools.
Latest release v0.202.0 · 3 Nov 2026
4 files for Claude Code: adapter-ops, connector-ops, worktree, csp-check .
.claude/skills/adapter-ops/SKILL.md C 71 tok .claude/skills/connector-ops/SKILL.md C 62 tok .claude/skills/worktree/SKILL.md A 44 tok .claude/skills/csp-check/SKILL.md A 96 tok These files are Zipstack/unstract's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.