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 04mg · Agent Tool · ★ 101
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is caw safe to install? View the security audit →
Caw Web terminal multiplexer for AI agents. Features Run Agents in the Browser Launch Claude Code, Codex CLI, GitHub Copilot, OpenCode, Antigravity, or Pi side-by-side — Caw auto-detects which agents are installed and spins up a terminal pane for each. Agent Control Center Stop babysitting terminals. Caw watches each agent's transcript and shows its real-time state — Working, Needs Input, or Idle — on a live Kanban board. <source srcset="assets/fe
| Stars | 101 |
| Forks | 5 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 59.5372544246307/100 |
| Last Updated | 2026-09-06 |
| Created | 2026-07-04 |
| Platforms | browser, node |
| Est. Tokens | ~15k |
These tools work well together with caw for enhanced workflows:
Looking for a caw alternative? If you're comparing caw 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.
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs
Open-source Agentic AI framework in Go for building, orchestrating, and deploying intelligent agents. LLM-agno
🔐 SSH MCP Tool - AI-powered SSH management through MCP protocol | 基于MCP协议的SSH工具，为AI提供SSH远程操作能力
TUI for Ollama and other LLM providers
Create agentic AI workflows in ROBLOX Studio
Transform your Claude Code terminal with atomic precision statusline. Features flexible layouts, real-time cos
Explore other popular agent tool tools:
caw is Web interface for AI agents.. It is categorized as a Agent Tool with 101 GitHub stars.
caw is primarily written in TypeScript. It covers topics such as agentic-ai, agentic-coding, ai.
You can find installation instructions and usage details in the caw GitHub repository at github.com/04mg/caw. The project has 101 stars and 5 forks, indicating an active community.
caw is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to caw on Agent Skills Hub include hcom, AgenticGoKit, mcp-ssh. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: