AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Data Processing/
unstract
unstract logo

unstract

Active·★ 7.4k·AGPL-3.0·Updated 2026-11-06
★ Essential★ Trending

Unstract uses LLMs to extract structured JSON from documents (PDFs, images, scans) based on natural-language prompts, and lets you deploy the result as an API or an ETL pipeline. It is aimed at teams in finance, insurance, healthcare and KYC or compliance. The README's comparison says that instead of writing regex and per-vendor templates you write a prompt once, a new document type takes minutes in Prompt Studio, and any provider (OpenAI, Anthropic, Bedrock, Ollama) can be plugged in.

Key pieces are Prompt Studio for defining extraction schemas, API deployment (send a document over REST, get JSON back), an ETL pipeline that pulls documents from sources such as S3, MinIO, Google Cloud Storage, Azure Blob, Google Drive, Dropbox or SFTP and loads them into a warehouse, an MCP server for agents such as Claude, and an n8n node. To run it locally you need Linux or macOS, Docker and Docker Compose, Git and at least 8 GB of RAM, then clone the repository and run `./run-platform.sh`. A managed cloud and an enterprise edition with SSO and role-based access control are offered, and the open-source code is AGPL-3.0.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-07.

License
AGPL-3.0
Latest release
v0.203.0 · 2026-11-06
Last commit
2026-11-06
Contributors
30
Forks
753
Open issues and PRs
122
First published
2024-02-21

Source: GitHub, npm and PyPI public APIs.

#Document Extraction#LLM Applications#Data Structuring#ETL Pipeline#API Deployment#Prompt Engineering#Unstructured Data
$ Install
$ git clone https://github.com/Zipstack/unstract.git && cd unstract && ./run-platform.sh
↗ Visit site★ GitHub
01

Features

01Prompt Studio: Define document extraction schemas with natural language.
02API Deployment: Send a document over REST API, get JSON back.
03ETL Pipeline: Pull documents from a folder, process them, load to your warehouse.
04MCP Server: Connect to AI agents (Claude, etc.) via Model Context Protocol.
05n8n Node: Drop into existing automation workflows.
02

Why choose it

+Define extraction with a natural-language prompt instead of regex or per-vendor templates.
+Deploy as a REST API or an ETL pipeline reading from S3, Google Cloud Storage, Azure Blob, Drive, Dropbox or SFTP.
+Works with several LLM providers including OpenAI, Anthropic, Bedrock and local Ollama.
+Also offers an MCP server and an n8n node, and starts locally with one script.
03

Trade-offs

!Running it locally needs Docker, Docker Compose and at least 8 GB of RAM, and the default login in the README is a demo username and password you should change.
!Extraction relies on LLM calls, so accuracy and cost depend on the model and documents; outputs need validation for finance or compliance use.
!The open-source code is AGPL-3.0, and SSO and enterprise RBAC are part of the cloud and enterprise offering.
04

Maintenance check

ActiveChecked: 2026-11-03
Last commit
2026-11-02
Commits, last 90 days
100+
Releases, last 90 days
30
Latest release
v0.200.0 (2026-11-01)
Open issues
134
Recent issues with at least one comment
0/1
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 8, 1, 9, 8, 9, 6, 10, 16, 8, 18, 19, 3

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #414 About access unstract web from other computer25 comments · 2024-06-21
  • #595 fix: [ISSUE] "Error fetching data and indexing: [Errno 2] No such file or directory: '/data/INFILE.pdf'" in API workflow execution17 comments · 2024-08-19

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

Docker
Deployment
Verified via docs
Linux
OS
Verified via docs
macOS
OS
Verified via docs
Python
Runtime
Verified via docs
LLM Providers
Integration
Verified via docs
ETL Connectors
Integration
Verified via docs
06

Quick start

1
$ git clone https://github.com/Zipstack/unstract.git
2
$ cd unstract
3
$ ./run-platform.sh
07

Use cases

↳Finance & Banking automation
↳Insurance automation
↳Healthcare automation
↳KYC/Compliance data extraction
↳Income Tax forms data extraction
08

Alternatives

⚡Top VS:
VSTrendRadar★63.5k→VSOpenMetadata★15.7k→VSFinanceToolkit★5.5k→VSexcel-mcp-server★4.3k→
TrendRadar logo
TrendRadar★ 63.5k
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。
VSCompare→
OpenMetadata logo
OpenMetadata★ 15.7k
OpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
VSCompare→
FinanceToolkit logo
FinanceToolkit★ 5.5k
Transparent and Efficient Financial Analysis
VSCompare→
excel-mcp-server logo
excel-mcp-server★ 4.3k
A Model Context Protocol server for Excel file manipulation
VSCompare→
FinnewsHunter logo
FinnewsHunter★ 1.5k
FinnewsHunter: Multi-agent financial intelligence platform powered by AgenticX. Real-time news analysis, sentiment fusion, and alpha factor mining.
VSCompare→
retentioneering-tools logo
retentioneering-tools★ 944
Python toolkit, MCP server, and agent skills for reproducible, auditable clickstream and event log analytics. Helps AI agents, data scientists and analysts build, validate, and cross-check product analytics, quantitative UX, customer journeys, graph-based user flows, behavioral segmentation, A/B tests, process mining models, Markov chain simulation
Xberg (Kreuzberg successor) logo
Xberg (Kreuzberg successor)★ 9.6k
A Rust-based document extraction framework, continuing Kreuzberg under a fresh version line. The reviewed Python package extracts PDF text, tables and configured OCR, with per-input batch errors.
VSCompare→
rust-sdk logo
rust-sdk★ 4.1k
The official Rust SDK for the Model Context Protocol
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
Zipstack /
unstract
↗

Extract structured JSON from documents with LLM prompts, as an API or ETL pipeline

7.4k753AGPL-3.0
Last commit2d ago
StatusActive
CategoryData Processing
Contributors30
Latest releasev0.203.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.