claude-db — security grade SAFE, quality 73/100

Security audit verdict: SAFE · quality 73/100

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 Avijit07x · Claude Skill · ★ 213

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

🔒 Is claude-db safe to install? View the security audit →

About claude-db

Persistent memory for Claude Code. Bring your own database. What it is Claude Code forgets everything when a session ends. Next time you open it, you re-explain the architecture, why you chose X over Y, and what already failed. claude-db records those decisions as you work and gives them back automatically. Local by default, no account, no subscription. Restart Claude Code. That's it. How it works Claude Code already writes every session to disk as JSONL — your prompts, its replies, every tool call. claude-db reads that file, so it captures why you did something, not just which files changed. Both steps are hooks, so they always run. Nothing depends on Cl

claudeclaude-aiclaude-apiclaude-codeclaude-code-pluginclaude-code-pluginsclaude-code-skillclaude-code-skillsclaude-desktopclaude-plugin

Quick Facts

Stars213
Forks23
LanguageTypeScript
CategoryClaude Skill
LicenseApache-2.0
Quality Score73.0086082632077/100
Last Updated2026-08-30
Created2026-08-15
Platformsclaude-code, node
Est. Tokens~15k

claude-db alternative? Top 6 similar tools

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

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

  • awesome-claude-skills by Mann1988 · ⭐ 66

    📊 Explore high-quality Claude skills focused on business analysis and content creation, enhancing your AI cap

  • claude-code-ios-dev-guide by keskinonur · ⭐ 816

    A comprehensive guide for setting up Claude Code CLI with PRD-driven workflows, extended thinking (ultrathink)

  • claude-elixir-phoenix by oliver-kriska · ⭐ 555

    Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP

  • awesome-claude-skills by karanb192 · ⭐ 512

    🎯 The definitive collection of 50+ verified Awesome Claude Skills for Claude Code, Claude.ai, and API. Boost

  • claude-cowork-linux by johnzfitch · ⭐ 405

    Run Claude Desktop’s Cowork mode natively on Linux — no macOS or VM required

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is claude-db?

claude-db is Persistent memory for Claude Code. Bring your own database.. It is categorized as a Claude Skill with 213 GitHub stars.

What programming language is claude-db written in?

claude-db is primarily written in TypeScript. It covers topics such as claude, claude-ai, claude-api.

How do I install or use claude-db?

You can find installation instructions and usage details in the claude-db GitHub repository at github.com/Avijit07x/claude-db. The project has 213 stars and 23 forks, indicating an active community.

What license does claude-db use?

claude-db is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to claude-db?

The top alternatives to claude-db on Agent Skills Hub include claudepro-directory, awesome-claude-skills, claude-code-ios-dev-guide. 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 Claude Skill tools