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
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
This repository page has enough original analysis, source evidence, and comparison context to be treated as an indexable Git-Stars review.
100
review score
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.
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.
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.
Analysis
ReadyOriginal problem, capability, and verdict guidance are available.
Sources
ReadyRepository metadata and README/source references are attached.
License
ReadyAGPL-3.0 is recorded for review.
Maintenance
ReadyRecent activity is visible in repository metadata.
Alternatives
ReadyEnough nearby projects exist for comparison.
Momentum
7.1k Stars
Reuse
699 Forks
Attention
7.1k Watchers
Maintenance
active
License
AGPL-3.0
Open issues
83
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.
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
git clone https://github.com/Zipstack/unstract.git && cd unstract && ./run-platform.sh73
Health Score
Active
Commit Activity
Feb 21, 2024
Created
Aug 7, 2026
Last push
+4
Today's growth
+4
7-day growth
+4
30-day growth
Forks
Open
Watchers
Zipstack
GitHub profilepublic-apis/public-apis
A collective list of free APIs
freeCodeCamp/freeCodeCamp
freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.
openclaw/openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
jwasham/coding-interview-university
A complete computer science study plan to become a software engineer.
obra/superpowers
An agentic skills framework & software development methodology that works.
✓
License
✓
Forked
✓ Active
Maintained
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.