Best wiki OKF Bundles for AI Agents

Wiki OKF bundles provide structured knowledge for AI agents working in this domain. These bundles are designed to be loaded directly into agent context, giving your AI assistant the domain expertise it needs without manual setup or complex infrastructure. Browse the top bundles below to find the right one for your workflow.

10 bundles · 38 total stars

Top wiki OKF Bundles

1

wiki-as-an-mcp

First general Wiki MCP following google's Open Knowledge Format. Let your agent to use, manage, maintain, and health check the wiki (knowledge base) for you. The wiki is general purpose.

agentaiknowledge-basellm-wiki
2

Wiki as MCP

OKF ✓

First general Wiki MCP following Google's Open Knowledge Format. Lets your agent use, manage, maintain, and health-check a wiki (knowledge base). General-purpose OKF wiki server.

mcpwikiknowledge-baseagent
3

Open Knowledge CLI

OKF ✓

CLI tool for managing Open Knowledge Format (OKF) bundles. Create, connect, inspect, publish, and maintain local LLM wikis that are readable for both humans and agents. Includes a local Markdown viewer, registry management, and HTML export.

cliwikiknowledge-basemarkdown
4

okf-loom

OKF ✓

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

agent-skillsagent-toolsdocumentationknowledge-graph
5

knowledge-os-plugin

OKF ✓

Portable, OKF-compatible company knowledge base in Markdown. Compiles to a hierarchical, scale-ready index for LLMs + an offline HTML viewer for humans — with facets, search-by-meaning, and built-in agent procedures (onboarding, dedup, capture). Works with Claude Code, Codex, Antigravity — or no agent.

ai-agentsclaude-codecodexdeveloper-tools
6

mosAIc

OKF ✓

Reconfigurable LLM surface that reshapes per task

aiai-toolsgenerative-uigenerative-ux
7

thats-a-first-crawler

OKF ✓

LLM-maintained knowledge base (OKF + Karpathy LLM-wiki pattern) for STRT's daily That's a First Digest n8n workflow.

anthropicclaudedocumentationknowledge-base
8

lan-master-nes-kb

This archive preserves the technical legacy of Lan Master, transforming raw assembly into transferable software engineering knowledge.

knowledge-baselan-masternesokf
9

okf-anything

OKF ✓

It's Mine or Nothing. Moon Escape: Reclaim Our Second Brains, Embrace Google OKF, Slay Every SaaS With Your Own Hands — Join Us.

kaparthymarkdownokfwiki
10

waqwaq

OKF ✓

Git-backed markdown wiki for humans and AI agents, web UI and MCP endpoint from one binary

ai-agentsgolangknowledge-basellm

How to Choose a wiki 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 wiki OKF bundle?

A wiki 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 wiki use cases. They work with Claude Code, Cursor, OpenCode, and any OKF-compatible agent — no SDKs, databases, or API keys required.

Which wiki bundle is best for Claude Code?

The best wiki 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.