knox — OKF Bundle for Knowledge Graphs
OKF ✓ v0.1Knowledge Organizer for eXtended documents (KNOX). Python knowledge management tool that uses OKF v0.1 as its default output format. Supports ACP, MCP, RAG, vector search, and knowledge graphs.
Best for
- AI agents using the MCP protocol
- Knowledge graph and knowledge management systems
- RAG (Retrieval Augmented Generation) pipelines
What it does
- Knowledge Organizer for eXtended documents (KNOX).
- Python knowledge management tool that uses OKF v0.1 as its default output format.
- Supports ACP, MCP, RAG, vector search, and knowledge graphs..
How to use with AI agents
Step 1: Clone the repository
git clone https://codeberg.org/jr2804/knox
cd knoxStep 2: Point your AI agent at the bundle directory
# Claude Code
claude /path/to/knox# Cursor
cursor /path/to/knox# OpenCode
opencode /path/to/knoxMCP: This bundle supports the Model Context Protocol. Configure your MCP client to discover and load this bundle.
Frequently Asked Questions
Is knox OKF conformant?
Yes, knox is OKF conformant (version 0.1). This means it follows the Open Knowledge Format specification.
How do I install knox?
Clone the repository and point your AI agent at the bundle directory. The agent will automatically discover and load the OKF knowledge. No additional tools or SDKs are required.
What AI agents can use knox?
knox works with any AI agent that supports OKF bundles, including Claude Code, Cursor, OpenCode. Just point your agent at the bundle directory.
What are alternatives to knox?
Similar bundles include okf-tools, okf-agents, okfgen. Browse these for alternative approaches and feature sets.