Privacy and advertising choices

Git-Stars uses essential storage for site operation. Optional analytics and ad-measurement scripts stay disabled unless you accept them; partners such as Google may then use cookies or similar identifiers where required. Privacy Policy

LogoGit-Stars
Top StarsTrendingAI AgentsDaily PicksViral ReposInsights
LogoGit-Stars

Discover top GitHub projects with real rankings and AI insights

GitHub
Built withLogo of Git-StarsGit-Stars
Rankings
  • Top Stars
  • Trending
  • AI Agents
  • Daily Picks
  • Explore
Resources
  • Insights
  • Editorial Policy
About
  • About
  • Contact
Legal
  • Privacy Policy
  • Terms of Service
© 2026 Git-Stars. All Rights Reserved.
UN

Zipstack/unstract

AI Agent

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

7.1k Stars699 Forks83 Open Issues7.1k WatchersPythonAGPL-3.0
AI AgentLLM ToolAutomationData ToolMCP Server
Review Readiness

This repository page has enough original analysis, source evidence, and comparison context to be treated as an indexable Git-Stars review.

100

review score

Indexable review
Decision Snapshot

Problem solved

Unstract eliminates the need for manual regex patterns and vendor-specific templates by using LLMs to handle document variations. It abstracts away the complexity of building custom LLM pipelines, offering a unified interface for multiple LLM providers and deployment options, thus reducing development time from days to minutes.

Deployment reality

The available setup signal starts with: git clone https://github.com/Zipstack/unstract.git && cd unstract && ./run-platform.sh. Treat this as a starting point, then ask Codex or Claude to inspect the README, environment variables, runtime version, and deployment target before production use.

Commercial use

The recorded license is AGPL-3.0. This is a useful commercial-use signal, but teams should still verify license text, dependencies, model/API terms, and trademark constraints.

Capability ceiling

Developers can build document processing systems that extract specific fields (e.g., invoices, IDs, medical records) into JSON, deployable via REST APIs or integrated into ETL workflows. It supports integration with AI agents via MCP and automation tools like n8n, enabling use cases in finance, insurance, healthcare, and compliance. The platform's ceiling includes handling diverse document types with minimal code, scaling via managed cloud, and extending to complex multi-step extraction pipelines.

Source and compliance noteLast synced: Aug 8, 2026

Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.

Original GitHub sourceMethodologyEditorial Policy
Editorial Evaluation

Zipstack/unstract is tracked as a Python project in the AI Agent, LLM Tool, Automation, Data Tool, MCP Server area. This evaluation combines public GitHub metadata, category signals, short source summaries, and Git-Stars editorial rules rather than copying project documentation.

Momentum check: the repository has 7.1k total stars, with +0 today, +91 this week, and +0 this month. These growth windows help distinguish durable adoption from short-lived visibility spikes.

Maintenance check: current activity is Active; the latest push was 15 days ago, and the open issue queue is 83, about 1.16% of total stars. Treat this as an adoption signal, not a substitute for engineering due diligence.

Adoption check: 699 forks and 7.1k watchers suggest how often the project is reused or followed. License signal: AGPL-3.0. Always verify license compatibility before commercial or internal use.

Practical fit: this project is most relevant when you need AI prototypes, LLM workflows, and agent-style applications. Be cautious when you need a legal review, security audit, or production SLA.

Source check: Git-Stars currently has 2 explicit source reference(s) for this report and a recent growth signal of 91. Follow the original GitHub repository for final install, security, and release information.

Evidence Checklist

Analysis

Ready

Original problem, capability, and verdict guidance are available.

Sources

Ready

Repository metadata and README/source references are attached.

License

Ready

AGPL-3.0 is recorded for review.

Maintenance

Ready

Recent activity is visible in repository metadata.

Alternatives

Ready

Enough nearby projects exist for comparison.

Best For
  • AI prototypes, LLM workflows, and agent-style applications
  • Python teams evaluating ecosystem-native tooling
  • use cases where recent maintenance matters
Avoid When
  • you need a legal review, security audit, or production SLA
Adoption Signals

Momentum

7.1k Stars

Reuse

699 Forks

Attention

7.1k Watchers

Maintenance

active

License

AGPL-3.0

Open issues

83

Overview

Unstract is a platform that uses LLMs to extract structured JSON data from unstructured documents such as PDFs, images, and scans. It allows users to define extraction schemas using natural language prompts and deploy them as APIs or ETL pipelines. It is designed for teams in finance, insurance, healthcare, and KYC/compliance.

Key Features

- Prompt Studio: Define document extraction schemas with natural language. - API Deployment: Send a document over REST API and get JSON back. - ETL Pipeline: Pull documents from a folder, process them, and load to a warehouse. - MCP Server: Connect to AI agents via Model Context Protocol. - n8n Node: Integrate with existing automation workflows.

Tool Positioning

AI Agent

Agent frameworks, autonomous workflows, and tool-use systems

LLM Tool

Libraries and tools for LLM apps, RAG, prompts, and evals

Automation

Workflow automation, integration glue, and orchestration

Data Tool

Databases, data pipelines, ETL, analytics, and vector search

MCP Server

Model Context Protocol servers, clients, and integrations

Quick Start
git clone https://github.com/Zipstack/unstract.git && cd unstract && ./run-platform.sh
View on GitHub Project Homepage
Project Activity

73

Health Score

Active

Commit Activity

Feb 21, 2024

Created

Aug 7, 2026

Last push

Source Trail

GitHub repository metadata

metadata

GitHub README

readme_summary

Star History

+4

Today's growth

+4

7-day growth

+4

30-day growth

Aug 7, 2026Aug 8, 2026
Community Health
699

Forks

83

Open

7.1k

Watchers

Owner
UN

Zipstack

GitHub profile
Topics & Language
Pythonai-agentsdata-engineeringdocument-aigenerative-aiidpjson-extractionllmmcp-serverocrpdf-extractionprompt-engineeringstructured-output
Ecosystem & Usage
GitHub Repository Project Website
Alternatives & Comparison

public-apis/public-apis

A collective list of free APIs

460k

freeCodeCamp/freeCodeCamp

freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

454k

openclaw/openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

386k

jwasham/coding-interview-university

A complete computer science study plan to become a software engineer.

359k

obra/superpowers

An agentic skills framework & software development methodology that works.

273k
License
AGPL-3.0
CreatedFeb 21, 2024
Last pushAug 7, 2026
Last syncedAug 8, 2026
Repository Standards

✓

License

✓

Forked

✓ Active

Maintained

AI AnalysisAnalyzed by Git-Stars

Problem Solved

Unstract eliminates the need for manual regex patterns and vendor-specific templates by using LLMs to handle document variations. It abstracts away the complexity of building custom LLM pipelines, offering a unified interface for multiple LLM providers and deployment options, thus reducing development time from days to minutes.

Capabilities

Developers can build document processing systems that extract specific fields (e.g., invoices, IDs, medical records) into JSON, deployable via REST APIs or integrated into ETL workflows. It supports integration with AI agents via MCP and automation tools like n8n, enabling use cases in finance, insurance, healthcare, and compliance. The platform's ceiling includes handling diverse document types with minimal code, scaling via managed cloud, and extending to complex multi-step extraction pipelines.

Bottom Line

Unstract is ideal for teams needing rapid, flexible document-to-data extraction without building custom LLM infrastructure. It is less suitable for those with very simple, fixed-format documents or those requiring full control over the underlying LLM pipeline. The key trade-off is convenience and speed versus potential dependency on a platform and LLM costs.

Full AI Analysis