Zikkaron — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by amanhij · MCP Server · ★ 62

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is Zikkaron safe to install? View the security audit →

About Zikkaron

Zikkaron Zikkaron (זיכרון) is Hebrew for "memory." Your AI forgets you every time you close the tab. Every architecture decision you explained, every debugging rabbit hole you went down together, every "remember, we're using Postgres not SQLite" correction. Gone. You start the next session a stranger to your own tools. Zikkaron is a persistent memory engine for Claude Code built on computational neuroscience. It remembers what you worked on, how you think, what you decided and why. Not as a dumb text dump that gets shoved into context, but as a living memory system that consolidates, forgets intelligently, and reconstructs the right context at the right time. 26 subsystems. 24 MCP tools. Runs entirely on your machine. One SQLite file. Two minutes to never repeat yourself again Add to your Claude Code config: Tell Claude how to use it. Drop this in your global (your home directory, not per-project): markdown Memory On ever

agent-memoryartificial-intelligencecausal-inferenceclaudeclaude-codecognitive-architecturecomplementary-learning-systemshopfield-networksknowledge-graphllm-tools

Quick Facts

Stars62
Forks7
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score63.8538910544794/100
Open Issues1
Last Updated2026-04-01
Created2026-03-02
Platformsclaude-code, mcp, python
Est. Tokens~49k

Zikkaron alternative? Top 6 similar tools

Looking for a Zikkaron alternative? If you're comparing Zikkaron with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • Cortex by cdeust · ⭐ 73

    Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited n

  • omega-memory by omega-memory · ⭐ 219

    Persistent memory for AI coding agents

  • dreamgraph by mmethodz · ⭐ 116

    DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisio

  • prism-mcp by dcostenco · ⭐ 131

    The Mind Palace for AI Agents - HIPAA-hardened Cognitive Architecture with on-device LLM (prism-coder:7b), Heb

  • roampal-core by roampal-ai · ⭐ 51

    Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demo

  • shodh-memory by varun29ankuS · ⭐ 295

    Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is Zikkaron?

Zikkaron is Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQL. It is categorized as a MCP Server with 62 GitHub stars.

What programming language is Zikkaron written in?

Zikkaron is primarily written in Python. It covers topics such as agent-memory, artificial-intelligence, causal-inference.

How do I install or use Zikkaron?

You can find installation instructions and usage details in the Zikkaron GitHub repository at github.com/amanhij/Zikkaron. The project has 62 stars and 7 forks, indicating an active community.

What license does Zikkaron use?

Zikkaron is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to Zikkaron?

The top alternatives to Zikkaron on Agent Skills Hub include Cortex, omega-memory, dreamgraph. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools