llm-wiki — OKF Bundle for AI Agent Memory
OKF ✓ v0.1Local-first agent memory for multi-tool workflows. Markdown vault, session capture, compile-to-notes — OpenCode, Claude Code, Codex, Cursor. No cloud lock-in.
Best for
- AI agents using the MCP protocol
- Claude Code and AI coding agents
- Knowledge graph and knowledge management systems
- Markdown note-taking and personal knowledge management
- Obsidian vault users
What it does
- Local-first agent memory for multi-tool workflows.
- Markdown vault, session capture, compile-to-notes — OpenCode, Claude Code, Codex, Cursor.
How to use with AI agents
Step 1: Clone the repository
git clone https://github.com/Ekgardt/llm-wiki
cd llm-wiki Step 2: Point your AI agent at the bundle directory
# Claude Code
claude /path/to/llm-wiki # OpenCode
opencode /path/to/llm-wiki MCP: This bundle supports the Model Context Protocol. Configure your MCP client to discover and load this bundle.
Frequently Asked Questions
Is llm-wiki OKF conformant?
Yes, llm-wiki is OKF conformant (version 0.1). This means it follows the Open Knowledge Format specification.
How do I install llm-wiki?
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 llm-wiki?
llm-wiki works with any AI agent that supports OKF bundles, including Claude Code, OpenCode. Just point your agent at the bundle directory.
What are alternatives to llm-wiki?
Similar bundles include samemind, dev-workspace, 50firsttapes. Browse these for alternative approaches and feature sets.