unstract

Overview

LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows

unstract is a well-established open-source skill with growing adoption, maintained by Zipstack with 6,675 GitHub stars. It targets the Integration layer of the agent stack — where reusable skills, MCP servers, and tool integrations accelerate production workflows.

Tagged with ai-agents, data-engineering, document-ai, generative-ai, idp, json-extraction, and more, this skill fits naturally into modern agent architectures that combine LLMs, tools, and memory.

Key Features

• Pre-built connectors for popular SaaS and developer tools
• Webhook and event-driven triggers for agent workflows
• OAuth and API key management patterns
• Bidirectional sync between agents and external systems
• Error handling and retry logic for flaky third-party APIs
• Documentation and examples for common integration paths

Use Cases

• Sync CRM updates from sales conversation summaries
• Create Jira tickets from support agent escalations
• Post Slack digests from nightly research agent runs
• Bridge Notion wikis into RAG knowledge bases

Integration

Primary integration surface: Agent frameworks (LangChain, LangGraph, CrewAI, custom loops).

Implementation language: Python — check the repo for package install instructions.

Official homepage: https://unstract.com

Most skills support environment variables for API keys and configurable endpoints.

For MCP servers, add the server config to your client JSON and restart the host application.

Who It's For

Developers building integration-heavy agent features who want open-source building blocks.

Teams standardizing on MCP or shared tool libraries across multiple agent products.

Indie hackers and startups optimizing time-to-ship for agent MVPs.

Technical evaluators comparing alternatives before committing to a stack.

Getting Started

1. Clone or install from https://github.com/Zipstack/unstract.
2. Read the README for prerequisites (Node, Python, Docker, API keys).
3. Import the package into your agent framework and register tools.
4. Run the provided example or quickstart script to verify connectivity.
5. Iterate on prompts and tool schemas using the project's test utilities.
6. Pin versions in production and monitor upstream releases for breaking changes.

Community & Trust Signals

6,675 GitHub stars indicate broad community interest.

License: AGPL-3.0. Verify compatibility with your product's distribution model.

Last repository activity: June 2026.

Review open issues and PR velocity to gauge maintainer responsiveness.

Star and watch the repo to track releases and security advisories.

Topics