Permanent memory for AI agents. Single binary, zero dependencies, MCP native.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
git clone https://github.com/rtk-ai/icm && cp icm/*.md ~/.claude/agents/Subagents overview
What people ask about icm
What is rtk-ai/icm?
+
rtk-ai/icm is subagents for the Claude AI ecosystem. Permanent memory for AI agents. Single binary, zero dependencies, MCP native. It has 427 GitHub stars and was last updated 3d ago.
How do I install icm?
+
You can install icm by cloning the repository (https://github.com/rtk-ai/icm) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is rtk-ai/icm safe to use?
+
Our security agent has analyzed rtk-ai/icm and assigned a Trust Score of 97/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains rtk-ai/icm?
+
rtk-ai/icm is maintained by rtk-ai. The last recorded GitHub activity is from 3d ago, with 31 open issues.
Are there alternatives to icm?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy icm to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.