Gives your AI assistant persistent memory across sessions using the Zettelkasten method. Exposes three MCP tools: knowledge-search for retrieving context before tasks, knowledge-store for saving decisions and preferences, and knowledge-maintain for lifecycle management. Uses hybrid search with local embeddings and full-text matching over a local SQLite index. Notes live as Markdown files with YAML frontmatter in six categories (personalization, reference, decision, procedure, resource, observation) that progress from fleeting to permanent to archived. Works offline with no API keys required, though you can plug in OpenAI-compatible endpoints for embeddings. Includes an installer that injects instructions into OpenCode, Claude Code, Cursor, Windsurf, and Zed so the assistant proactively queries and updates its own knowledge base.
claude mcp add --transport stdio mrosnerr-open-zk-kb uvx open-zk-kb