pie-ai-agent — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

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 WiseriaAI · Agent Tool · ★ 182

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

🔒 Is pie-ai-agent safe to install? View the security audit →

About pie-ai-agent

Pie Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skills, CDP keyboard control, and a sandboxed, prompt-injection-resistant execution model. English · 简体中文 · Español (Latinoamérica) · 日本語 · Português (Brasil) Install · Configure · Privacy · Changelog · Roadmap · Architecture · Archive Why Pie Pie turns Chrome into a browser-automation agent. Describe a task in natural language; the LLM plans steps and executes them through a typed tool registry — DOM actions, cross-tab orchestration, and CDP-level keyboard input for canvas e

agentic-aiai-agentanthropicbrowser-automationbyokchrome-devtools-protocolchrome-extensionclaudedeepseekfunction-calling

Quick Facts

Stars182
Forks8
LanguageTypeScript
CategoryAgent Tool
LicenseApache-2.0
Quality Score71.4815748083023/100
Open Issues10
Last Updated2026-08-10
Created2026-04-17
Platformsbrowser, claude-code, gemini, node
Est. Tokens~17k

pie-ai-agent alternative? Top 6 similar tools

Looking for a pie-ai-agent alternative? If you're comparing pie-ai-agent 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.

  • pie-ai-agent by wiseria-ai-labs · ⭐ 80

    Pie – free, open-source AI browser agent for Chrome. Reads pages & PDFs, fills forms, extracts data, automates

  • Cerno-Agentic-Local-Deep-Research by Cerno-AI · ⭐ 84

    Cerno is a local-first research platform that leverages agentic AI to break down complex queries into verifiab

  • ha-claude by Bobsilvio · ⭐ 81

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

  • ToolRegistry by Oaklight · ⭐ 61

    ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs (OpenAI, Anthropic, Gemini

  • vllora by vllora · ⭐ 812

    Debug your AI agents

  • wcgw by rusiaaman · ⭐ 674

    Shell and coding agent on mcp clients

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is pie-ai-agent?

pie-ai-agent is Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skills, CDP keyboard control, and a confirm-before-act security model. BYOK across 8 LLM provi. It is categorized as a Agent Tool with 182 GitHub stars.

What programming language is pie-ai-agent written in?

pie-ai-agent is primarily written in TypeScript. It covers topics such as agentic-ai, ai-agent, anthropic.

How do I install or use pie-ai-agent?

You can find installation instructions and usage details in the pie-ai-agent GitHub repository at github.com/WiseriaAI/pie-ai-agent. The project has 182 stars and 8 forks, indicating an active community.

What license does pie-ai-agent use?

pie-ai-agent 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 pie-ai-agent?

The top alternatives to pie-ai-agent on Agent Skills Hub include pie-ai-agent, Cerno-Agentic-Local-Deep-Research, 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