vellium — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 tg-prplx · MCP Server · ★ 136

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

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

About vellium

Vellium — local-first AI workbench for chat, roleplay and writing One desktop app for character chat, multi-character roleplay, long-form writing, RAG, MCP tools, plugins and local models. Vellium is a free, open-source desktop AI workspace that works with OpenAI-compatible APIs, OpenRouter, LM Studio, Ollama, KoboldCpp and custom endpoints. Your chats, characters, projects and knowledge stay in a local SQLite database. Download for macOS, Windows or Linux · Quick start · User guide Curr

aiai-chatai-roleplayai-roleplay-chatai-writinganimecharacter-aichatbotchatgptdesktop-app

Quick Facts

Stars136
Forks11
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score67.111553414785/100
Open Issues1
Last Updated2026-10-01
Created2026-02-18
Platformsmcp, node
Est. Tokens~16k

Compatible Skills

These tools work well together with vellium for enhanced workflows:

  • novel-engine — semantic(0.31)+complementary+same_lang+similar_pop+shared_platform (61%)
  • pawwork — semantic(0.30)+complementary+same_lang+similar_pop+shared_platform (60%)
  • ctxport — semantic(0.17)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)
  • atomic-agent — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)
  • GitHub-Stars-AI-Tools — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)

vellium alternative? Top 6 similar tools

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

  • PocketRisu by PocketRisu · ⭐ 368

    Self-hosted AI roleplay chat platform you run on your PC or personal server, forked from Risuai

  • ethora by dappros · ⭐ 547

    Open-source engine for chat 💬, AI assistants 🤖 & wallets 🪪. React, Typescript, Python, XMPP. Build future a

  • ctxport by nicepkg · ⭐ 495

    Copy AI conversations as clean Markdown Context Bundles — one click from ChatGPT, Claude, Gemini, DeepSeek, Gr

  • Liyuan by weidu12123 · ⭐ 237

    梨园 Liyuan — 以 rp agent为主体的ai角色扮演应用

  • c4-genai-suite by codecentric · ⭐ 173

    c4 GenAI Suite

  • repopack-py by abinthomasonline · ⭐ 122

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

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is vellium?

vellium is Local-first desktop AI workbench for roleplay, multi-character chat, long-form writing, RAG, MCP tools, plugins, and local models.. It is categorized as a MCP Server with 136 GitHub stars.

What programming language is vellium written in?

vellium is primarily written in TypeScript. It covers topics such as ai, ai-chat, ai-roleplay.

How do I install or use vellium?

You can find installation instructions and usage details in the vellium GitHub repository at github.com/tg-prplx/vellium. The project has 136 stars and 11 forks, indicating an active community.

What license does vellium use?

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

What are the best alternatives to vellium?

The top alternatives to vellium on Agent Skills Hub include PocketRisu, ethora, ctxport. 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