clawless — security grade SAFE, quality 73/100

Security audit verdict: SAFE · quality 73/100

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 open-gitagent · Agent Tool · ★ 525

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

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

About clawless

ClawLess No server required to run Claw Agents, use ClawLess to run on browser! A serverless browser-based runtime for Claw AI Agents powered by WebContainers Run Claw Agents without a Server — entirely on-browser via WebContainers (WASM) Complete Audit &amp; Policy driven sandboxing Built on GitAgent Standard Pluggable SDK with template-based agent bootstrapping Secure by design — fully isolated WASM sandbox, no access to host system <a href="https:

agent-runtimeaiai-agentsai-sandboxaudit-loggingbrowser-runtimeclawlessdeveloper-toolsgitagentmonaco-editor

Quick Facts

Stars525
Forks94
LanguageTypeScript
CategoryAgent Tool
LicenseMIT
Quality Score72.5999007216018/100
Open Issues7
Last Updated2026-07-08
Created2026-03-19
Platformsbrowser, node
Est. Tokens~482k

Compatible Skills

These tools work well together with clawless for enhanced workflows:

  • ironcurtain — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (59%)
  • Aegis — semantic(0.26)+complementary+rare_topics+same_lang+similar_pop+shared_platform (59%)
  • mcpcat-typescript-sdk — semantic(0.23)+complementary+rare_topics+same_lang+similar_pop+shared_platform (57%)

clawless alternative? Top 6 similar tools

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

  • swarmclaw by swarmclawai · ⭐ 636

    Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory,

  • hcom by aannoo · ⭐ 490

    Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs

  • mcpproxy-go by smart-mcp-proxy · ⭐ 380

    Supercharge AI Agents, Safely

  • DashClaw by ucsandman · ⭐ 306

    Remote approvals, policy checks, and execution evidence for unattended AI agents.

  • runtm by runtm-ai · ⭐ 297

    Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, C

  • kontext-cli by kontext-security · ⭐ 210

    Runtime Security for tool-using AI agents, with local policies, pre-action enforcement, and forensic audit tra

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is clawless?

clawless is ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers. It is categorized as a Agent Tool with 525 GitHub stars.

What programming language is clawless written in?

clawless is primarily written in TypeScript. It covers topics such as agent-runtime, ai, ai-agents.

How do I install or use clawless?

You can find installation instructions and usage details in the clawless GitHub repository at github.com/open-gitagent/clawless. The project has 525 stars and 94 forks, indicating an active community.

What license does clawless use?

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

What are the best alternatives to clawless?

The top alternatives to clawless on Agent Skills Hub include swarmclaw, hcom, mcpproxy-go. 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