Morphik Core

A self-hosted multimodal retrieval engine that searches visual documents with ColPali and connects to AI applications through an API or MCP.

Morphik Core is a retrieval engine for developers building AI applications around documents whose meaning depends on charts, diagrams, or page layout. It brings document search and structured extraction into one platform.

Visual document search: Search PDFs, images, and videos using techniques such as ColPali, with whole-page representations that retain visual context.
Structured extraction: Pull information and metadata from documents, including labels, classifications, and bounding boxes.
Knowledge graphs: Explore relationships in stored knowledge through graph views.
Application connections: Use the Python SDK, REST API, or MCP to connect retrieval to applications, Claude, and Open Web UI, with data integrations for Google Suite, Slack, and Confluence.
Shared knowledge access: Support multiple tenants and control access through roles or rules written in natural language.

The browser console lets users upload files, connect data sources, search, and chat with documents. Its interface can also sit inside another application with custom branding.

You can self-host Morphik Core on your own infrastructure, including through Docker, or use its hosted service. It supports on-premises deployment and cloud environments such as AWS, GCP, and Azure. Self-hosted support is limited to installation guidance and community help.

MCP Servers and Agent Skills Chat With Your Documents Document Parsing for LLMs RAG Frameworks and Pipelines Docker Web MCP Multi-user access Multimodal input RAG Role-based access Semantic search

Nobody has claimed Morphik Core yet

Work on Morphik Core? Claim this page with an email at dev.morphik.ai. Morphik Core gets the verified checkmark, and you can upgrade the listing.

Want more people to find it? Promote it

Something wrong or outdated on this page?

Logotyper

Got an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.

Start your project

Similar to Morphik Core

View all tools

Flexible GraphRAG

Self-hosted GraphRAG platform for document search and AI chat. Supports Ollama, vLLM and cloud APIs, with an Apache 2.0 license.

200Updated 4 days agoApache-2.0

Docker · Web#Hybrid search#Knowledge graphs#LLM tracing

Flexible GraphRAG is a self-hosted platform for teams building document search and AI chat that use both text and relationships between entities. It extracts knowledge graphs from documents and combines graph retrieval with vector similarity and full-text search. You can run it standalone or in Docker. It's open source under Apache 2.0.

AI Search and Deep ResearchChat With Your DocumentsDocument Parsing for LLMsMCP Servers and Agent SkillsRAG Frameworks and Pipelines

haiku.rag

A local-first document search tool answers questions with page-level citations, uses Ollama by default, and connects to AI assistants through MCP.

658Updated 1 day agoMIT

Docker · Web#Code execution#Hybrid search#MCP

haiku.rag lets you search your own documents and ask questions with answers you can check against the original pages. It's for people building a private document library or giving an AI assistant access to their files.

Chat With Your DocumentsMCP Servers and Agent SkillsRAG Frameworks and Pipelines

LightRAG

8 videos

A self-hosted RAG framework that combines knowledge graphs and vector retrieval to answer document questions with local or hosted models.

40.7KUpdated 18 hours agoMIT

macOS · Windows · Linux · Docker · Web#Knowledge graphs#LLM tracing#Multimodal input

LightRAG is a self-hosted framework for developers building AI assistants that answer questions across documents. It connects related facts across files, including material where relationships matter, such as legal and financial records.

Chat With Your DocumentsDocument Parsing for LLMsRAG Frameworks and Pipelines

NVIDIA RAG Blueprint

A self-hosted RAG framework answers questions about your documents using NVIDIA NIM models, with multimodal extraction and optional agentic search.

823Updated 2 weeks agoApache-2.0

Docker · Web#Agent Skills#Guardrails#Hybrid search

NVIDIA RAG Blueprint is a reference framework for developers building AI question answering over enterprise data. It retrieves relevant material from your documents to ground answers and can cite the retrieved sources.

Chat With Your DocumentsDocument Parsing for LLMsRAG Frameworks and Pipelines

OpenRAG

1 video

Self-hosted AI document search and chat built on Langflow, OpenSearch, and Docling, with editable workflows and an Apache 2.0 license.

4.7KUpdated 3 days agoApache-2.0

Docker · Web#Hybrid search#MCP#Multi-agent workflows

OpenRAG is a self-hosted platform for searching documents and asking questions about them through an AI chat interface. It brings Langflow, OpenSearch, and Docling together for developers and teams that want a document knowledge base with control over its retrieval workflows. It's open source under Apache 2.0 and supports self-managed deployment with Docker or Podman.

AI Search and Deep ResearchAI Workflow AutomationChat With Your DocumentsMCP Servers and Agent SkillsRAG Frameworks and Pipelines

RESTai

A self-hosted AI platform for document assistants and agents, with Ollama and vLLM support, cloud model connections and an OpenAI-compatible API.

518Updated 3 months agoApache-2.0

Linux · Docker · Web#Knowledge graphs#MCP#Multi-user access

RESTai is a self-hosted AI platform for developers and teams building document assistants, agents and AI services for other applications. Its web interface manages projects with separate models, prompts and tools, plus a chat playground for testing them.

Agent FrameworksAI Workflow AutomationChat With Your DocumentsMCP Servers and Agent SkillsRAG Frameworks and Pipelines