Zikkaron

v1.0.0Knowledge & Memorystable

Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQLite.

agent-memoryartificial-intelligencecausal-inferenceclaudeclaude-code
Share:
58
Stars
0
Downloads
0
Weekly
0/5

What is Zikkaron?

Zikkaron is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to biologically-inspired persistent memory engine for claude code. 26 cognitive subsystems, hopfield networks, predictive coding, causal discovery, successor representations, all running locally over sql...

Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQLite.

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Biologically-inspired persistent memory engine for Claude Co

Use Cases

Persistent agent memory with causal inference
Local SQLite-based cognitive architecture
amanhij

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

PIP

pip install zikkaron

Manual Installation

pip install zikkaron

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Zikkaron

Zikkaron is a biologically-inspired persistent memory engine for Claude Code that implements 26 cognitive subsystems including Hopfield networks, predictive coding, causal discovery, and successor representations—all running locally over SQLite. It gives AI agents human-like memory consolidation, decay, and recall across sessions without relying on any external API or cloud service. Developers use it to build agents that remember project context, learn from past interactions, and reason causally about what they have done before.

Prerequisites

  • Python 3.10 or later installed
  • pip or uv package manager
  • Claude Code or another MCP-compatible client
  • Local disk space for the SQLite database (stored in ~/.zikkaron/memory.db by default)
1

Install Zikkaron via pip

Install the package from PyPI. This also installs the sentence-transformers library which downloads the all-MiniLM-L6-v2 embedding model on first run.

pip install zikkaron
2

Verify the installation

Confirm the zikkaron command is available on your PATH before adding it to your MCP config.

zikkaron --help
3

Open your Claude Code MCP configuration

Claude Code reads MCP servers from its settings file. Open ~/.claude/settings.json or the project-level .mcp.json file in your editor.

4

Add the Zikkaron server block

The minimal config requires no environment variables. Optional ZIKKARON_ prefixed variables let you tune memory decay, embedding model, and database location.

{
  "mcpServers": {
    "zikkaron": {
      "command": "zikkaron"
    }
  }
}
5

Optionally customise with environment variables

Use ZIKKARON_DB_PATH to store the database inside your project, ZIKKARON_DECAY_FACTOR to control how fast memories fade, and ZIKKARON_EMBEDDING_MODEL to switch the local sentence-transformer model.

{
  "mcpServers": {
    "zikkaron": {
      "command": "zikkaron",
      "env": {
        "ZIKKARON_DB_PATH": "/home/user/projects/myapp/.zikkaron/memory.db",
        "ZIKKARON_DECAY_FACTOR": "0.95",
        "ZIKKARON_EMBEDDING_MODEL": "all-MiniLM-L6-v2"
      }
    }
  }
}
6

Restart Claude Code and seed your project

After restarting, ask Claude Code to call the seed_project tool to initialise project-specific memory context. From then on, Zikkaron will record and recall memories automatically across sessions.

Zikkaron Examples

Client configuration

Minimal claude_desktop_config.json entry for Zikkaron with optional database path customisation.

{
  "mcpServers": {
    "zikkaron": {
      "command": "zikkaron",
      "env": {
        "ZIKKARON_DB_PATH": "~/.zikkaron/memory.db",
        "ZIKKARON_DECAY_FACTOR": "0.95",
        "ZIKKARON_COGNITIVE_LOAD_LIMIT": "4"
      }
    }
  }
}

Prompts to try

Example requests that exercise Zikkaron's memory, recall, causal, and project-context tools.

- "Remember that we decided to use PostgreSQL instead of MySQL for this project"
- "Recall what we discussed about the authentication flow last week"
- "Show me my memory stats and how many memories are currently stored"
- "Get the full project story and summarise the key decisions made so far"
- "Detect any gaps in my knowledge about the payment module"
- "Create a checkpoint of my current memory state before the refactor"

Troubleshooting Zikkaron

zikkaron command not found after pip install

The script may not be on your PATH if pip installed it into a user or virtual environment bin directory. Run python -m zikkaron or activate your virtual environment, then retry.

Slow startup or hang while downloading the embedding model

On first run, sentence-transformers downloads all-MiniLM-L6-v2 (~90 MB) from Hugging Face. Ensure internet access and wait for the download to complete. Subsequent starts use the cached model.

Memories not persisting between sessions

Verify ZIKKARON_DB_PATH points to a writable directory. If you run Claude Code under different user contexts (e.g. sudo), the database path may differ. Use an absolute path and confirm file permissions.

Frequently Asked Questions about Zikkaron

What is Zikkaron?

Zikkaron is a Model Context Protocol (MCP) server that biologically-inspired persistent memory engine for claude code. 26 cognitive subsystems, hopfield networks, predictive coding, causal discovery, successor representations, all running locally over sqlite. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Zikkaron?

Install via pip with: pip install zikkaron. Then configure your AI client to connect to this MCP server.

Which AI clients work with Zikkaron?

Zikkaron works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Zikkaron free to use?

Yes, Zikkaron is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "zikkaron": { "command": "pip", "args": ["install", "zikkaron"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Zikkaron?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides