agentpipe — security grade CAUTION, quality 72/100

Security audit verdict: CAUTION · quality 72/100

Flagged: sudo usage, curl | sh from an untrusted host. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by kevinelliott · Agent Tool · ★ 145

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

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

About agentpipe

AgentPipe 🚀 AgentPipe is a powerful CLI and TUI application that orchestrates conversations between multiple AI agents. It allows different AI CLI tools (like Claude, Cursor, Gemini, Qwen, Ollama) to communicate with each other in a shared "room", creating dynamic multi-agent conversations with real-time metrics, cost tracking, and interactive user participation. Screenshots Enhanced TUI Interface ![AgentPipe TUI](scree

aiai-agentsai-agents-automationai-agents-cliclaude-codecli-appcursor-aifactory-aigemini-cligrok

Quick Facts

Stars145
Forks25
LanguageGo
CategoryAgent Tool
LicenseMIT
Quality Score71.5033793311507/100
Open Issues15
Last Updated2026-06-27
Created2025-09-12
Platformsclaude-code, cli, gemini, go
Est. Tokens~27k

Compatible Skills

These tools work well together with agentpipe for enhanced workflows:

  • gob — semantic(0.25)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
  • ordercli — semantic(0.31)+complementary+same_lang+similar_pop+shared_platform (56%)
  • skillshare — semantic(0.15)+complementary+same_lang+similar_pop+shared_platform (55%)

agentpipe alternative? Top 6 similar tools

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

  • hcom by aannoo · ⭐ 490

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

  • maestro-orchestrate by josstei · ⭐ 462

    Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, paralle

  • vexjoy-agent by notque · ⭐ 423

    VexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent

  • tsk-tsk by dtormoen · ⭐ 168

    Keeping your agents out of trouble with sandboxed coding agent automation

  • agf by subinium · ⭐ 152

    Find, search, and resume AI coding-agent sessions across Claude Code, Codex, Grok Build, Kimi Code, Qwen Code,

  • octomind by Muvon · ⭐ 139

    Open-source AI coding agent and agent runtime: one binary, any model, MCP-native. Runs in terminal, CI, or as

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Go Agent Tools

Frequently Asked Questions

What is agentpipe?

agentpipe is A CLI/TUI app that orchestrates multi-agent conversations by enabling different AI CLI tools (Claude Code, Gemini, Qwen, etc.) to communicate in shared rooms.. It is categorized as a Agent Tool with 145 GitHub stars.

What programming language is agentpipe written in?

agentpipe is primarily written in Go. It covers topics such as ai, ai-agents, ai-agents-automation.

How do I install or use agentpipe?

You can find installation instructions and usage details in the agentpipe GitHub repository at github.com/kevinelliott/agentpipe. The project has 145 stars and 25 forks, indicating an active community.

What license does agentpipe use?

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

What are the best alternatives to agentpipe?

The top alternatives to agentpipe on Agent Skills Hub include hcom, maestro-orchestrate, vexjoy-agent. 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