moli — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

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 lexmount · Agent Tool · ★ 2.0k

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

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

About moli

Moli English | 简体中文 | 日本語 | Deutsch | Français | Español Moli is a production-ready headless browser for AI agents. Its on-demand layout and rendering design combines a complete browser runtime with a lightweight resource footprint. Moli helps your AI agent fetch and extract web pages, search the web, and automate browser tasks. Use it through the CLI, CDP, WebDriver Classic, or WebDriver BiDi. Moli supports Linux, macOS, and Windows. Quick start Give this prompt to your AI agent: Direct installation On Linux or macOS: sh curl --proto '=ht

ai-agentsai-toolsbrowserbrowser-automationcloud-browserplaywrightpuppeteerrustservoweb-crawler

Quick Facts

Stars1,976
Forks135
LanguageRust
CategoryAgent Tool
LicenseApache-2.0
Quality Score65.1347170815579/100
Open Issues100
Last Updated2026-09-14
Created2026-08-10
Platformsbrowser, rust
Est. Tokens~25k

Compatible Skills

These tools work well together with moli for enhanced workflows:

  • hwatu — semantic(0.47)+complementary+same_lang+similar_pop+shared_platform (67%)
  • bladebro — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (62%)

moli alternative? Top 6 similar tools

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

  • crw by us · ⭐ 984

    Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for

  • brightdata-mcp by brightdata · ⭐ 2.6k

    A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.

  • webclaw by 0xMassi · ⭐ 2.3k

    Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI

  • browserable by browserable · ⭐ 1.2k

    Open source and self-hostable browser automation library for AI agents

  • browsernode by leoning60 · ⭐ 1.0k

    🌐 Make websites accessible for AI agents. Automate tasks online with ease.

  • web-agent-protocol by OTA-Tech-AI · ⭐ 505

    🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is moli?

moli is Best headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust. It is categorized as a Agent Tool with 2.0k GitHub stars.

What programming language is moli written in?

moli is primarily written in Rust. It covers topics such as ai-agents, ai-tools, browser.

How do I install or use moli?

You can find installation instructions and usage details in the moli GitHub repository at github.com/lexmount/moli. The project has 2.0k stars and 135 forks, indicating an active community.

What license does moli use?

moli 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 moli?

The top alternatives to moli on Agent Skills Hub include crw, brightdata-mcp, webclaw. 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