A standalone, deterministic grounding playground for AI agents built on the Google Agent Development Kit (ADK) 2.0 and the Git-backed Open Knowledge Format (OKF) specification.

Local-first memory for AI agents: teach knowledge as Markdown Domains, capture learnings as Engrams. One Rust binary with MCP server, CLI and hybrid search.

Toolkit for turning Markdown docs bundles into validated OKF knowledge graphs, with a local studio, static site output, and agent-friendly CLI.

google-okf is a production-grade, open-source Python library designed to automatically connect to various enterprise data sources and convert them into the standard Google Open Knowledge Format (OKF).

BundleWalker is a hands-on exploration of how structured knowledge can move between tools, workflows, and AI agents. It combines the Open Knowledge Format (OKF) with Pydantic AI's typed agent model to investigate knowledge that is portable, inspectable, and explicit about its structure.

Use LangChain and your preferred model provider to generate and validate Open Knowledge Format (OKF) bundles

A fast, local CLI for turning a folder of Markdown files into a searchable, linked knowledge base.

Self-Contexting Hierarchy of AGENTS.md files using the OKF specifications by Google.