COR Brief
Join Beta
AI Tools›Data & Analytics›Morphik Core
Data & Analytics

Morphik Core

Morphik Core is a source-available toolset designed for developers to ingest, search, transform, and manage unstructured and multimodal documents, including visually rich formats such as diagrams and schematics. It supports both deep and shallow search capabilities and is optimized for building AI applications that require accurate retrieval over complex document types without losing context during parsing. The tool provides a self-hosted API server, a web-based Morphik Console for file uploads and interactive querying, and supports integration through the Model Context Protocol (MCP). The platform includes a Docker-based setup with PostgreSQL/pgvector for storage and Ollama for running local AI models. It offers features such as rules-based ingestion, cache-augmented generation, role-based access control (RBAC), and multi-tenancy to support agentic retrieval-augmented generation (RAG) applications. Morphik Core is free for personal and indie use or commercial use under $2,000/month gross revenue, with paid licensing required beyond that threshold.

Updated Jan 24, 2026freemium
Visit Morphik Core ↗Visual Guide
Overview

Morphik Core is a self-hosted, source-available toolset for managing and searching unstructured and multimodal documents optimized for AI applications.

Pricing
$0
Category
Data & Analytics
Company
Visual Guide
Interactive PresentationOpen Fullscreen ↗
Key Features
01
Supports ingestion of documents in their native formats, enabling search over complex diagrams, schematics, and datasheets without losing context to parsing.
02
Provides both deep and shallow search capabilities for effective retrieval and transformation of multimodal data.
03
Includes Docker configuration with PostgreSQL/pgvector for storage and Ollama for running local AI models such as nomic-embed-text and llama3.2.
04
Offers a web-based Morphik Console at http://localhost:3000 for uploading, viewing, and querying data, alongside a self-hosted API server with documentation at http://localhost:8000/docs.
05
Supports the Model Context Protocol (MCP), role-based access control, and multi-tenancy to facilitate agentic retrieval-augmented generation applications.
06
Allows configuration of models, hosts, ports, and features such as reload mode through a dedicated configuration file.
Real-World Use Cases

AI Application Development

Developers building AI applications that require accurate search and storage over unstructured and multimodal documents including diagrams and datasheets.

Knowledge Centralization

Businesses centralizing technical and domain-specific knowledge for reliable AI agents to query complex document types.

Quick Start
1
Clone Repository
Run git clone https://github.com/morphik-org/morphik-core.git and cd morphik-core. Ensure Docker, Docker Compose, at least 10GB disk space, and 8GB+ RAM are available.
2
Initial Setup
Run docker compose up --build to download models, initialize PostgreSQL/pgvector, and start services. This process takes approximately 5-10 minutes.
3
Access API
Access the API documentation at http://localhost:8000/docs or check server health at http://localhost:8000/health.
4
Run Web UI
Ensure the server is running, install npm, navigate to the ui-component directory, run npm run dev, then access the UI at http://localhost:3000.
5
Subsequent Runs
Start the server with docker compose up and stop it with docker compose down.
📊

Strategic Context for Morphik Core

Get weekly analysis on market dynamics, competitive positioning, and implementation ROI frameworks with AI Intelligence briefings.

Try Intelligence Free →
7 days free · No credit card
Pricing
Model: freemium
Free Plan
$0
  • 200 pages per month
  • 3 Research-Agent calls per month
  • Shared GPU ingestion queue
Pro Plan
$59
  • Details on additional limits not specified in available data

Self-hosted use is free for personal or indie use and commercial production under $2,000/month gross revenue; commercial use beyond this requires a paid key. Licensed under Business Source License 1.1 with relicensing to Apache 2.0 after 4 years.

Assessment
Strengths
  • Supports self-hosting via Docker or direct install, keeping data local.
  • Handles multimodal documents natively, embedding full pages for accurate search without parsing loss.
  • Free for personal and commercial use under $2,000/month revenue with easy model configuration.
  • Includes console UI, API documentation, and Model Context Protocol for querying without coding.
  • Stores data persistently in Docker volumes and local directories for documents and logs.
Limitations
  • No full support for self-hosted deployments; relies on guides and Discord community for assistance.
  • Initial Docker setup downloads large AI models requiring 10GB disk space and good internet connection, taking 5-10 minutes.
  • Commercial use over $2,000/month revenue requires a paid key; free cloud plan quotas are limited.