Google PageRank for AI agents. 80,000+ tools indexed.

icm MCP Server

rtk-ai/icm

Score: 90.0 ↓ 3.2% Rank #343 overall #118 of 59,750 in MCP Server MCP Server
[![AgentRank](https://agentrank-ai.com/api/v1/badge/rtk-ai--icm)](https://agentrank-ai.com/tool/rtk-ai--icm/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Maintain rtk-ai/icm? Feature it at the top of its category: $199/mo Feature rtk-ai/icm →

Permanent memory for AI agents. Single binary, zero dependencies, MCP native.

Add AgentRank to Claude Code Discover and compare tools like rtk-ai/icm — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

rtk-ai/icm is a Rust tool licensed under Apache-2.0. Permanent memory for AI agents. Single binary, zero dependencies, MCP native. Topics: ai-agents, claude-code, experimental, mcp, memory, rust.

Ranked #343 out of 81417 indexed tools.

In the top 1% of all indexed tools.

Has 17 contributors.

Ecosystem

Rust Apache-2.0
ai-agentsclaude-codeexperimentalmcpmemoryrust

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 580

580 stars → growing community

Freshness 25% 13d ago

Last commit 13d ago → recently updated

Issue Health 25% 86%

83/96 issues closed → responsive maintainer

Contributors 10% 17

17 contributors → active community

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 61
Description Good
License Apache-2.0

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

Badge all embed codes →

AgentRank score for rtk-ai/icm
[![AgentRank](https://agentrank-ai.com/api/v1/badge/rtk-ai--icm)](https://agentrank-ai.com/tool/rtk-ai--icm/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/rtk-ai--icm/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/rtk-ai--icm" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="rtk-ai/icm"></script>

Matched Queries

topic:mcp

From the README

[English](README.md) | [Français](README_fr.md) | [Español](README_es.md) | [Deutsch](README_de.md) | [Italiano](README_it.md) | [Português](README_pt.md) | [Nederlands](README_nl.md) | [Polski](README_pl.md) | [Русский](README_ru.md) | [日本語](README_ja.md) | [中文](README_zh.md) | [العربية](README_ar.md) | [한국어](README_ko.md)

<p align="center">
  
</p>

<h1 align="center">ICM</h1>

<p align="center">
  Permanent memory for AI agents. Single binary, zero dependencies, MCP native.
</p>

<p align="center">
  <a href="https://github.com/rtk-ai/icm/actions/workflows/ci.yml"></a>
  <a href="https://github.com/rtk-ai/icm/releases/latest"></a>
  <a href="LICENSE"></a>
</p>

---

> ⚠️ **Project status: experimental**
>
> ICM is pre-1.0 and under active development. Breaking changes can land
> in any minor release, and hooks/MCP configuration formats may shift.
>
> That said, I (the maintainer) use ICM every day as my primary AI
> coding memory layer — it's experimental in API stability, not in
>
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.