Best rag OKF Bundles for AI Agents
Retrieval Augmented Generation (RAG) pipelines connect LLMs to external knowledge sources, but most RAG systems require complex embedding and vector database infrastructure. OKF bundles offer a simpler alternative: structured markdown documents that agents can load directly without any retrieval pipeline. These bundles are perfect for teams that want the benefits of RAG — grounded, up-to-date responses — without the operational complexity of managing a vector database.
Top rag OKF Bundles
obsidian-gemini-helper
OKF ✓AI chat, workflow automation, semantic search (RAG), LLM Wiki (OKF), and dashboards with reading memos powered by Google Gemini. Works on both desktop and mobile.
OKF RAG
OKF ✓OKF-based Retrieval-Augmented Generation system. Includes sample OKF bundles with index.md and concept files, plus RAG benchmarking against OKF-structured knowledge.
mnemos
OKF ✓Local-first MCP memory server for AI agents, with source citations and OKF/Markdown knowledge bases.
agentic-task-system
MCP server + CLI that turns the task manager you already use into persistent agent memory for Claude Code and any MCP client. Hybrid retrieval (RRF), no vector database. Adapters: TickTick, Obsidian, Notion, GitHub, Airtable, Google, OKF, Taskmaster, Beads.
docparse-rs
OKF ✓Pure-Rust document parsing for RAG/agents: PDF · DOCX · HTML · more → byte-deterministic, page+bbox-citable chunks. One binary, zero deps.
OKF_Studio_EGT
OKF ✓Transform institutional knowledge into Open Knowledge Format (OKF). OKF Studio ingests enterprise knowledge from multiple sources, structures it into portable OKF bundles, builds linked knowledge graphs, and makes knowledge reusable across LLMs, agents, and applications.
open-knowledge-format-starter
OKF ✓Ready-to-fork starter for an AI-maintained knowledge base on the Open Knowledge Format (OKF) v0.1 — Markdown + YAML frontmatter, with a Claude Code skill, conformance validator, and EN/TH docs.
edu_effect-okf
OKF ✓Use Effect v4 (beta) to create CLI tools and services that can parse, validate, ingest, query, and reason over OKF bundles, integrated with RAG (Retrieval-Augmented Generation) via ChromaDB
lore
OKF ✓Turn hard-won human experience into knowledge your AI agents can act on — a methodology (routing + Book-to-Skill + governance) above OKF. A production field report.
okf-ingest
OKF ✓Unified ingestion tool for Google's Open Knowledge Format (OKF): validate, load into a portable DuckDB catalog, and semantically search bundles — from R or Python.
okf-kit
A tiny, dependency-free toolkit for Open Knowledge Format (OKF) bundles: index, link, lint, and progressive-disclosure navigation over plain markdown. No database, no embeddings, no keys.
okf-tools
OKF ✓CLI and Python library for querying, navigating, and authoring Google Open Knowledge Format (OKF) bundles. Adds semantic search, link graph traversal, and agent-friendly progressive disclosure to plain markdown knowledge bases.
self-grow-wiki
OKF ✓FANUC RAG Knowledge Base — pluggable retrieval + SAG hybrid search + OKF concepts. 97.4% flywheel, 29ms avg. pip install rag-fanuc.
taiwan-building-code-rag-benchmark
An advanced AI knowledge retrieval architecture comparison (Hybrid RAG vs Graph RAG vs OKF-Wiki), benchmarked on the Taiwan Building Regulations dataset.
brain
OKF ✓A local-first AI knowledge platform powered by Ollama and Open Knowledge Format (OKF).
cite-citadel
LLM-maintained, fully-cited personal wiki in Open Knowledge Format — with an MCP server so an AI can search and read it.
gemini-okf-compiler
OKF ✓The Universal Open Knowledge Format (OKF) Ingestion Compiler. Convert PDF, DOCX, Markdown, and HTML into structured, cross-linked RAG context graphs using Google Gemini.
iMon
OKF ✓It's Mine or Nothing. Moon Escape: Reclaim Our Second Brains, Embrace Google OKF, Slay Every SaaS With Your Own Hands — Join Us.
memvault
OKF ✓memvault — local knowledge engine for AI agents: capture Codex/Claude/Gemini sessions, hybrid semantic+keyword retrieval, one MCP server for every harness, interactive graph, OKF export.
okf-convert
OKF ✓Convert Markdown files and web pages into a conformant Open Knowledge Format (OKF v0.1) bundle. Deterministic Python + optional LLM enrichment. Claude Code skill + standalone CLI.
okf-everything
OKF ✓It's Mine or Nothing. Moon Escape: Reclaim Our Second Brains, Embrace Google OKF, Slay Every SaaS With Your Own Hands — Join Us.
okf-operational-layer
OKF ✓Why an OKF knowledge base needs a metabolism, not just a body — the automation layer Google's spec leaves out. By Team Dub Labs.
okfgen
OKF ✓Turn any repo, database, or open-data portal into an AI-ready knowledge graph — one command, no LLM, no lock-in. Based on Google's OKF Spec
How to Choose a rag OKF Bundle
OKF Conformance
Conformant bundles follow the full specification and work across all OKF-compatible agents. Look for the OKF badge.
Maintenance
Check the last updated date. Recently updated bundles are more likely to work with current agent frameworks.
License
Most bundles use permissive licenses (MIT, Apache-2.0). Check the license field to ensure compatibility.
Agent Compatibility
Bundles with tags like claude-code, mcp, or cursor have specific agent integrations. Choose based on your primary agent.
Related Topics
Frequently Asked Questions
What is a rag OKF bundle?
A rag OKF bundle is a portable knowledge package in the Open Knowledge Format that AI agents can load and use. These bundles contain structured markdown documents with YAML frontmatter, organized around rag use cases. They work with Claude Code, Cursor, OpenCode, and any OKF-compatible agent — no SDKs, databases, or API keys required.
Which rag bundle is best for Claude Code?
The best rag bundle for Claude Code depends on your specific needs. The bundles above are ranked by GitHub stars — a good proxy for community adoption. Look for bundles with OKF conformance status and recent updates. Claude Code natively supports OKF bundles, so any conformant bundle will work out of the box.
Are these bundles free?
Yes, all OKF bundles on BundleDex are free and open source. They are hosted on public GitHub repositories and can be cloned, forked, and used without any licensing fees or API keys. Just git clone the repository and point your AI agent at the directory.
Don't see what you're looking for? Browse all bundles or submit your own.