PI-Desktop — security grade SAFE, quality 72/100

Security audit verdict: SAFE · quality 72/100

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 vastsa · MCP Server · ★ 4.6k

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

🔒 Is PI-Desktop safe to install? View the security audit →

About PI-Desktop

PI-Desktop A local-first desktop app for AI coding agents. Bring your own models. Keep your code, your keys, and your conversations on your machine. Download · Getting started · Highlights · How it works · Development · 简体中文 What is PI-Desktop? PI-Desktop puts an AI coding agent in a native desktop app. Point it at a project, describe what you want — explore and understand code, build a feature, review changes, fix a failing test — and watch it work, with every file edit and shell command surfaced for your approval. There is no account, no subscription, and no cloud in the middle: you connect the model provider you already use, and everything else — sessions, settings, API keys — stays local. Highlights Any model, your keys. Anthropic, OpenAI,

ai-agentcoding-agentdesktop-appelectronglobali18nlocal-firstmcppipi-agent

Quick Facts

Stars4,644
Forks393
LanguageTypeScript
CategoryMCP Server
LicenseLGPL-3.0
Quality Score71.5407501860854/100
Open Issues116
Last Updated2026-09-20
Created2023-03-22
Platformsmcp, node
Est. Tokens~15k

PI-Desktop alternative? Top 6 similar tools

Looking for a PI-Desktop alternative? If you're comparing PI-Desktop 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.

  • open-cowork by OpenCoworkAI · ⭐ 2.1k

    Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — w

  • tabularis by debba · ⭐ 1.2k

    A lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable

  • skills-hub by qufei1993 · ⭐ 1.7k

    A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ gl

  • mcp-for-beginners by microsoft · ⭐ 17.3k

    This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cr

  • plate by udecode · ⭐ 16.6k

    Rich-text editor with AI and shadcn/ui

  • ouroboros by Q00 · ⭐ 6.0k

    Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budget

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is PI-Desktop?

PI-Desktop is Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins. It is categorized as a MCP Server with 4.6k GitHub stars.

What programming language is PI-Desktop written in?

PI-Desktop is primarily written in TypeScript. It covers topics such as ai-agent, coding-agent, desktop-app.

How do I install or use PI-Desktop?

You can find installation instructions and usage details in the PI-Desktop GitHub repository at github.com/vastsa/PI-Desktop. The project has 4.6k stars and 393 forks, indicating an active community.

What license does PI-Desktop use?

PI-Desktop is released under the LGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to PI-Desktop?

The top alternatives to PI-Desktop on Agent Skills Hub include open-cowork, tabularis, skills-hub. 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