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.
You open a new session and your agent has no idea who you are. Again. You re-explain your stack, your conventions, that one edge case you've corrected five times.
open-zk-kb gives your agent a memory — so corrections stick, context compounds, and every session starts smarter than the last.
Your agent stores what it learns and searches it next session — automatically.
Your agent starts from zero every session. No memory, no learning curve. You correct the same mistakes, re-explain the same conventions, re-teach the same context. Switch tools and it's even worse — your Cursor agent doesn't know what your Claude agent learned.
open-zk-kb fixes that.
Your agent gets sharper the longer you use it — for your specific workflow.
Your knowledge base is a fully themed Obsidian vault — homepage dashboard, kind-based folders with icons, breadcrumb navigation, and quick-add buttons. No manual setup.
Homepage with project stats, navigation, and your full knowledge graph.
See the Obsidian Guide for the full walkthrough.
Requires Bun — install with
curl -fsSL https://bun.sh/install | bash
bunx open-zk-kb@latest
That's it. The interactive installer:
~/.local/share/open-zk-kbSupported clients: OpenCode, Claude Code, Cursor, Windsurf, Zed, Pi, OMP
See the Setup Guide for manual installation and troubleshooting.
Zero configuration required. Local embeddings work out of the box with no API key.
See the Configuration Guide for embeddings, vault path, lifecycle tuning, and Obsidian scaffold options.
Built on the Zettelkasten method — atomic, linked notes with structured kinds. Each note captures one concept (a decision, a preference, a gotcha) and links to related notes, building an interconnected knowledge graph.
Search combines SQLite FTS5 full-text indexing with local vector embeddings (MiniLM-L6-v2) for semantic matching. Markdown files are the source of truth; the database is a rebuildable index.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent