raxol — 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 DROOdotFOO · MCP Server · ★ 76

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

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

About raxol

Raxol Recursively, axol. Forever FOSS. Write one app. Render it to a terminal, a browser, an SSH session, or an agent. Your application is a single TEA module (, , ) running as an OTP GenServer. Raxol renders that module to four surfaces from one codebase: The interesting part is the runtime, not the terminal. Your app gets crash isolation per Component, hot code reload without restart, distributed clustering with CRDTs, and an agent surface where LLMs interact with structured Component trees instead of scraping pixels. Bubble Tea, Ratatui, and Textual are excellent renderers. A2UI and AG-UI define agent-UI wire formats. Raxol is the runtime that renders all four surfaces from one source module. Built with Raxol Xochi Xochi is a private cross-chain

agent-uiagentic-commerceai-agentsbeamcrdtdistributed-systemselixirelm-architectureflexboxhot-reload

Quick Facts

Stars76
Forks5
LanguageElixir
CategoryMCP Server
LicenseMIT
Quality Score65.7342194010547/100
Open Issues55
Last Updated2026-09-11
Created2025-03-16
Platformsbrowser, mcp
Est. Tokens~18k

Compatible Skills

These tools work well together with raxol for enhanced workflows:

  • vibe — semantic(0.21)+complementary+rare_topics+same_lang+similar_pop+shared_platform (66%)
  • claude-code-elixir — semantic(0.22)+complementary+rare_topics+similar_pop (52%)
  • hermes-mcp — semantic(0.30)+rare_topics+same_lang+similar_pop+shared_platform (50%)
  • distributed-system-testing — semantic(0.23)+complementary+rare_topics+similar_pop (48%)

raxol alternative? Top 6 similar tools

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

  • limoni by thebanri · ⭐ 151

    Terminal UI engine for Go that tests can click and AI agents can drive (MCP). Zero-allocation rendering, immed

  • pepe by pepe-agent · ⭐ 67

    An Elixir/OTP AI agent runtime: define agents, connect any OpenAI-compatible model, and run a tool-calling loo

  • vibe by elixir-vibe · ⭐ 97

    BEAM-native coding agent for Elixir/OTP projects with TUI, web UI, eval, tools, memory, and subagents

  • OSA by Miosa-osa · ⭐ 76

    An AI agent for your terminal, built on signal theory: every output is signal, not noise. Codes, runs multi-st

  • pi-elixir by dannote · ⭐ 69

    BEAM runtime tools for pi — connects to the running Elixir app via Tidewave

  • hive-mind by projectmentor · ⭐ 56

    Persistent institutional shared memory as observable middleware for collaborative AI agents

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Elixir Agent Tools

Frequently Asked Questions

What is raxol?

raxol is Write one app, render it to a terminal, a browser, or as agent tools. The terminal for your Gundam.. It is categorized as a MCP Server with 76 GitHub stars.

What programming language is raxol written in?

raxol is primarily written in Elixir. It covers topics such as agent-ui, agentic-commerce, ai-agents.

How do I install or use raxol?

You can find installation instructions and usage details in the raxol GitHub repository at github.com/DROOdotFOO/raxol. The project has 76 stars and 5 forks, indicating an active community.

What license does raxol use?

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

What are the best alternatives to raxol?

The top alternatives to raxol on Agent Skills Hub include limoni, pepe, vibe. 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