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 rtk-ai · MCP Server · ★ 560
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is icm safe to install? View the security audit →
English 한국어 ICM Permanent memory for AI agents. Single binary, zero dependencies, MCP native. ICM gives your AI agent a real memory — not a note-taking tool, not a context manager, a memory. ICM (Infinite Context Memory) ┌──────────────────────┬─────────────────────────┐ │ MEMORIES (Topics) │ MEMOIRS (Knowledge) │ │ │ │ │ Episodic, temporal │ Permanent, structured │ │ │ │
| Stars | 560 |
| Forks | 54 |
| Language | Rust |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 67.2403997223853/100 |
| Open Issues | 6 |
| Last Updated | 2026-09-09 |
| Created | 2026-02-02 |
| Platforms | claude-code, mcp, rust |
| Est. Tokens | ~27k |
These tools work well together with icm for enhanced workflows:
Looking for a icm alternative? If you're comparing icm with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The control plane for AI coding agents.
The memory + security kernel for AI agents. Strata: a signed append-only log, receipts on every write, exact-h
Opensource Memory for Agents
A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficie
A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, sl
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowl
Explore other popular mcp server tools:
icm is Permanent memory for AI agents. Single binary, zero dependencies, MCP native.. It is categorized as a MCP Server with 560 GitHub stars.
icm is primarily written in Rust. It covers topics such as ai-agents, claude-code, experimental.
You can find installation instructions and usage details in the icm GitHub repository at github.com/rtk-ai/icm. The project has 560 stars and 54 forks, indicating an active community.
icm is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to icm on Agent Skills Hub include ai-devkit, vestige, forgetful. 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: