mini-claw — security grade SAFE, quality 77/100

Security audit verdict: SAFE · quality 77/100

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 htlin222 · Agent Tool · ★ 94

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

🔒 Is mini-claw safe to install? View the security audit →

About mini-claw

Mini-Claw Lightweight Telegram bot for persistent AI conversations using Pi coding agent. A minimalist alternative to OpenClaw -- use your Claude Pro/Max or ChatGPT Plus subscription directly in Telegram, no API costs. Why Mini-Claw? You already pay for Claude Pro or ChatGPT Plus. Why pay again for API tokens? Mini-Claw lets you chat with your existing subscription through Telegram -- persistent sessions, file attachments, shell access, zero extra cost. Features Persistent Sessions - Conversations are saved and auto-compacted Workspace Navigation - Change directories with , run shell commands with Session Management - Archive, switch, and clean up old se

ai-assistantanthropicchatbotclaudetypescript

Quick Facts

Stars94
Forks14
LanguageTypeScript
CategoryAgent Tool
LicenseMIT
Quality Score77.4919303916929/100
Last Updated2026-03-28
Created2026-02-01
Platformsclaude-code, node
Est. Tokens~4k

Compatible Skills

These tools work well together with mini-claw for enhanced workflows:

  • openclaw — semantic(0.49)+complementary+same_lang+shared_platform (57%)
  • crawbot — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (55%)
  • TomoriBot — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (54%)
  • cli-jaw — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (54%)

mini-claw alternative? Top 6 similar tools

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

  • openclaw-desktop by rshodoskar-star · ⭐ 119

    🖥️ A native desktop client for OpenClaw premium UI experience without the browser. Built with Electron + Rea

  • repopack-py by abinthomasonline · ⭐ 122

    Python version of 📦 repopack (https://github.com/yamadashy/repopack) by yamadashy (https://github.com/yamadas

  • ha-claude by Bobsilvio · ⭐ 86

    Home Assistant add-on: Claude Code, OpenAI/GPT, Gemini

  • fast-filesystem-mcp by efforthye · ⭐ 62

    A high-performance Model Context Protocol (MCP) server that provides secure filesystem access for Claude and o

  • claude-code-api by codingworkflow · ⭐ 331
  • lazy-bird by yusufkaraaslan · ⭐ 236

    Universal development automation for ANY project. Claude Code implements features, runs tests, creates PRs aut

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is mini-claw?

mini-claw is 🦞 Minimalist alternative to OpenClaw — lightweight personal AI assistant with multi-platform messaging support. It is categorized as a Agent Tool with 94 GitHub stars.

What programming language is mini-claw written in?

mini-claw is primarily written in TypeScript. It covers topics such as ai-assistant, anthropic, chatbot.

How do I install or use mini-claw?

You can find installation instructions and usage details in the mini-claw GitHub repository at github.com/htlin222/mini-claw. The project has 94 stars and 14 forks, indicating an active community.

What license does mini-claw use?

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

What are the best alternatives to mini-claw?

The top alternatives to mini-claw on Agent Skills Hub include openclaw-desktop, repopack-py, ha-claude. 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 Agent Tool tools