exxperts — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 EXXETA · MCP Server · ★ 355

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

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

About exxperts

AI colleagues that learn and remember. On your machine, under your control. Local-first AI agents with governed, approval-gated memory. Works with any model provider; MCP tools and web search built in. Nothing remembered without your say-so, nothing leaves your machine. Download · See it · How it works · Why exxperts · Install · Ways to use it · Docs #

agentsaillmlocal-firstmcpmemorytypescript

Quick Facts

Stars355
Forks40
LanguageTypeScript
CategoryMCP Server
LicenseApache-2.0
Quality Score65.7065146773357/100
Open Issues26
Last Updated2026-09-16
Created2026-07-07
Platformsbrowser, mcp, node
Est. Tokens~16k

Compatible Skills

These tools work well together with exxperts for enhanced workflows:

  • atomic-agent — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • openclaw-engram — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)
  • agentuse — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • local-cocoa — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)

exxperts alternative? Top 6 similar tools

Looking for a exxperts alternative? If you're comparing exxperts 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.

  • flow-like by TM9657 · ⭐ 865

    Flow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration an

  • memov by memovai · ⭐ 190

    Give git-like & traceable memory to OpenClaw and any coding agents. By https://memov.ai/ aka Entire CLI for ev

  • claude-historian-mcp by Vvkmnn · ⭐ 177

    📜 An MCP server for conversation history search and retrieval in Claude Code

  • npcpy by NPC-Worldwide · ⭐ 1.5k

    The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and mor

  • awesome-hacking-lists by taielab · ⭐ 1.4k

    A curated collection of top-tier penetration testing tools and productivity utilities across multiple domains.

  • nerve by evilsocket · ⭐ 1.3k

    The Simple Agent Development Kit.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is exxperts?

exxperts is Local-first AI agents with governed, approval-gated memory. Any model provider; MCP tools and web search built in. Nothing remembered without your say-so, nothing leaves your machine.. It is categorized as a MCP Server with 355 GitHub stars.

What programming language is exxperts written in?

exxperts is primarily written in TypeScript. It covers topics such as agents, ai, llm.

How do I install or use exxperts?

You can find installation instructions and usage details in the exxperts GitHub repository at github.com/EXXETA/exxperts. The project has 355 stars and 40 forks, indicating an active community.

What license does exxperts use?

exxperts 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 exxperts?

The top alternatives to exxperts on Agent Skills Hub include flow-like, memov, claude-historian-mcp. 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