100100 Ideas AI
Submit Tool

unstract

MCPOpen source

Open-source LLM platform to extract structured JSON from unstructured documents via API, ETL, or MCP.

7.1kAGPL-3.0

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

Pros

  • +Natural language prompt-based schema definition
  • +Multiple deployment options: API, ETL, MCP server, n8n node
  • +Supports various LLM providers (OpenAI, Anthropic, Bedrock, Ollama)
  • +Self-hostable with Docker Compose

Cons

  • −Requires Docker and 8GB RAM minimum
  • −Setup complexity for non-technical users
  • −AGPL-3.0 license may restrict commercial use

Target audience: Developers and data teams in finance, insurance, healthcare, and compliance needing to automate document data extraction.

Related tools

Other open-source tools that share tags with unstract.

headroom

MCPApache-2.0

Open-source context compression layer for AI agents, cutting tokens 60-95% for JSON and 15-20% for coding.

67k·LLM Ops·Open source