Jonex
An enterprise AI knowledge platform that combines a multimodal document- and video-parsing engine with an ontology-driven knowledge graph, vector and graph indexing, and source-grounded retrieval.
Jonex is an end-to-end enterprise AI knowledge platform that turns raw documents, video and other content into reusable knowledge services. It combines an all-in-one multimodal parsing engine with an AI-ready knowledge engine, where an ontology layer compiles domain reasoning into the knowledge base before retrieval begins, and connects data ingestion, multimodal parsing, domain knowledge compilation, vector and graph indexing, source-grounded retrieval, feedback loops, and business applications into one governed system.
It is deployed with Docker Compose, which builds and starts the platform, database, object storage, and an LLM gateway; separate environment files configure the platform, a bundled RAG/embedding/parsing component, an MCP server, and several frontend applications. At least one OpenAI-compatible LLM and embedding provider must be configured to run it.
It requires Docker Engine or Docker Desktop with Compose v2 and Buildx, and make on macOS or Linux.