collie — security grade CAUTION, quality 67/100

Security audit verdict: CAUTION · quality 67/100

Flagged: installs a background service, sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by AltanS · Agent Tool · ★ 979

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

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

About collie

Collie A phone web UI for your Herdr agent herd, served over Tailscale. Open a URL, see which agent is waiting on you, and answer it with your phone's keyboard. Each agent gets a colored terminal mirror, a slash-command palette, a special-keys pad, and a conversation history you can scroll and search. The reply box is an ordinary text field, so your phone's own voice dictation works in it; Collie ships none of its own. A Herdr plugin (thin launcher) plus a Bun/TypeScript bridge running as a service, serving a Vite + React + shadcn PWA. Contents Demo Security — read first Requirements Install First run — what you'll see Configure Dark mode / light mode Commands · Herdr actions Update Uninstall Deployment variants Windows (experimental) Web Push Troubleshooting Architecture Developing this plugin Demo A run through the herd from a phone: the dashboard floats the agent that needs you to the top, you drill into a sp

agent-orchestrationaiai-agentsai-codingai-toolsherdrherdr-pluginmultiplexingpwa

Quick Facts

Stars979
Forks132
LanguageTypeScript
CategoryAgent Tool
LicenseMIT
Quality Score66.8760648070211/100
Open Issues5
Last Updated2026-09-15
Created2026-06-28
Platformsnode
Est. Tokens~26k

Compatible Skills

These tools work well together with collie for enhanced workflows:

  • rulesync — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)
  • overstory — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • ai-maestro — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • brrr-cli — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)
  • agent-kanban — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)

collie alternative? Top 6 similar tools

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

  • pro-workflow by rohitg00 · ⭐ 2.8k

    Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context eng

  • awesome-agent-orchestrators by andyrewlee · ⭐ 1.9k

    List of agent orchestrators

  • pg-aiguide by timescale · ⭐ 1.8k

    MCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better Post

  • ai-devkit by codeaholicguy · ⭐ 1.6k

    The control plane for AI coding agents.

  • rulesync by dyoshikawa · ⭐ 1.4k

    A Utility CLI for AI Coding Agents

  • Mysti by DeepMyst · ⭐ 1.1k

    AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is collie?

collie is PWA to manage 🐑 herdr on the go. Tailnet accessible, push notifications, quick actions and more.. It is categorized as a Agent Tool with 979 GitHub stars.

What programming language is collie written in?

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

How do I install or use collie?

You can find installation instructions and usage details in the collie GitHub repository at github.com/AltanS/collie. The project has 979 stars and 132 forks, indicating an active community.

What license does collie use?

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

What are the best alternatives to collie?

The top alternatives to collie on Agent Skills Hub include pro-workflow, awesome-agent-orchestrators, pg-aiguide. 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