by mrosnerr
Shared, persistent memory for AI assistants, built on the Zettelkasten method
Provides shared, persistent memory for AI assistants using the Zettelkasten method, enabling context to persist across sessions through searchable atomic notes stored locally.
open-zk-kb is a community-built MCP server published by mrosnerr that provides AI assistants with tools and capabilities via the Model Context Protocol. Shared, persistent memory for AI assistants, built on the Zettelkasten method It is categorized under auth security. This server exposes 3 tools that AI clients can invoke during conversations and coding sessions.
You can install open-zk-kb in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
open-zk-kb is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
Strong directory entry: open-zk-kb surfaces stars and publisher context so we could sanity-check maintenance before adopting.
open-zk-kb has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
open-zk-kb is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
open-zk-kb reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
Useful MCP listing: open-zk-kb is the kind of server we cite when onboarding engineers to host + tool permissions.
open-zk-kb reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
open-zk-kb reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
I recommend open-zk-kb for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
I recommend open-zk-kb for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
We evaluated open-zk-kb against two servers with overlapping tools; this profile had the clearer scope statement.
showing 1-10 of 74
Shared, persistent memory for AI assistants, built on the Zettelkasten method. One knowledge base for all your tools — so context persists across sessions and clients.
AI assistants forget everything between sessions. open-zk-kb gives your assistant a persistent, structured memory it queries automatically.
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
Your AI assistant gets three MCP tools:
| Tool | What it does |
|---|---|
knowledge-search | Search the knowledge base before starting work |
knowledge-store | Save decisions, preferences, procedures, and insights |
knowledge-maintain | Review, promote, archive, and rebuild notes |
The installer injects instructions that guide the AI to proactively search for relevant context before starting work and store valuable knowledge as it discovers it. No plugin required — the AI drives everything through tool calls.
Notes are stored as Markdown files with YAML frontmatter. A SQLite index provides fast full-text search, with local vector embeddings for semantic matching. No API key needed.
Zero configuration required for basic usage. The installer creates ~/.config/open-zk-kb/config.yaml automatically.
To use an API provider for embeddings instead of local models:
embeddings:
provider: "api"
base_url: "https://openrouter.ai/api/v1"
api_key: "your-api-key-here"
model: "openai/text-embedding-3-small"
dimensions: 1536
Any OpenAI-compatible API works (OpenRouter, Together, Groq, local vLLM, etc.). See docs/configuration.md for the full reference.
| Kind | Default Status | Use Case |
|---|---|---|
personalization | permanent | User preferences, habits, and personal style |
reference | fleeting | Technical facts, API details, and documentation snippets |
decision | permanent | Architectural choices, project commitments, and trade-offs |
procedure | fleeting | Step-by-step workflows and recurring tasks |
resource | permanent | Links, tools, libraries, and external documentation |
observation | fleeting | Insights, patterns, and temporary findings |
Notes follow a lifecycle: fleeting → permanent → archived. See Note Lifecycle for details.
<details> <summary><h2>Manual Install</h2></summary>If you prefer manual configuration, add open-zk-kb to your client's MCP config file. No cloning required — the npm package includes everything.
Note: Manual install only adds the MCP server. To also inject the agent instructions, run
bunx open-zk-kb@latest install --client <name>or add the contents ofagent-instructions-full.md(oragent-instructions-compact.mdfor token-constrained clients) to your client's instruction file.
~/.config/opencode/opencode.json
{
"mcp": {
"open-zk-kb": {
"type": "local",
"command": ["bunx", "open-zk-kb@latest", "server"],
"enabled": true
}
}
}
~/.claude/settings.json
{
"mcpServers": {
"open-zk-kb": {
"command": "bunx",
"args": ["open-zk-kb@latest", "server"]
}
}
}
~/.cursor/mcp.json
{
"mcpServers": {
"open-zk-kb": {
"command": "bunx",
"args": ["open-zk-kb@latest", "server"]
}
}
}
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"open-zk-kb": {
"command": "bunx",
"args": ["open-zk-kb@latest", "server"]
}
}
}
~/.config/zed/settings.json
{
"context_servers": {
"open-zk-kb": {
"command": "bunx",
"args": ["open-zk-kb@latest", "server"]
}
}
}
git clone https://github.com/mrosnerr/open-zk-kb
cd open-zk-kb
bun install && bun run build
bun run setup # interactive installer
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.