经 AI Skill Hub 精选评估,开源MCP工具:Permanent memory for AI agents 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
icm是开源的MCP工具,提供永久内存功能,适用于AI代理。它是单个二进制文件,无依赖项,native MCP。icm的价值在于它提供了一个简单易用的方式来管理AI代理的内存,提高了AI代理的性能和可靠性。
开源MCP工具:Permanent memory for AI agents 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
icm是开源的MCP工具,提供永久内存功能,适用于AI代理。它是单个二进制文件,无依赖项,native MCP。icm的价值在于它提供了一个简单易用的方式来管理AI代理的内存,提高了AI代理的性能和可靠性。
开源MCP工具:Permanent memory for AI agents 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/rtk-ai/icm
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"--mcp---permanent-memory-for-ai-agents": {
"command": "npx",
"args": ["-y", "icm"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 开源MCP工具:Permanent memory for AI agents 执行以下任务... Claude: [自动调用 开源MCP工具:Permanent memory for AI agents MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"__mcp___permanent_memory_for_ai_agents": {
"command": "npx",
"args": ["-y", "icm"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
English | Français | Español | Deutsch | Italiano | Português | Nederlands | Polski | Русский | 日本語 | 中文 | العربية | 한국어
<p align="center"> <img src="assets/banner.png" alt="ICM — Infinite Context Memory" width="600"> </p>
<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"><img src="https://github.com/rtk-ai/icm/actions/workflows/ci.yml/badge.svg" alt="CI"></a> <a href="https://github.com/rtk-ai/icm/releases/latest"><img src="https://img.shields.io/github/v/release/rtk-ai/icm?color=purple" alt="Release"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache--2.0-blue.svg" alt="Apache-2.0"></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 day-to-day usefulness. My focus is currently on rtk; ICM updates are merged on a best-effort cadence. Issues and pull requests are welcome but may take longer to review than usual. ICM is Apache-2.0 licensed and ships as-is, without warranty of any kind (see LICENSE). Before any destructive operation, run the read-only equivalent first (icm uninstall --dry-run,icm uninstall --check).
---
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 │
│ │ │
│ ┌───┐ ┌───┐ ┌───┐ │ ┌───┐ │
│ │ m │ │ m │ │ m │ │ │ C │──depends_on──┐ │
│ └─┬─┘ └─┬─┘ └─┬─┘ │ └───┘ │ │
│ │decay │ │ │ │ refines ┌─▼─┐│
│ ▼ ▼ ▼ │ ┌─▼─┐ │ C ││
│ weight decreases │ │ C │──part_of──>└───┘│
│ over time unless │ └───┘ │
│ accessed/critical │ Concepts + Relations │
├──────────────────────┴─────────────────────────┤
│ SQLite + FTS5 + sqlite-vec │
│ Hybrid search: BM25 (30%) + cosine (70%) │
└─────────────────────────────────────────────────┘
Two memory models:
depends_on, contradicts, superseded_by, ...). Filter by label.```bash
curl -fsSL https://raw.githubusercontent.com/rtk-ai/icm/main/install.sh | sh
irm https://raw.githubusercontent.com/rtk-ai/icm/main/install.ps1 | iex
```bash
icm init
Configures **17 tools** in one command ([full integration guide](docs/integrations.md)):
| Tool | MCP | Hooks | CLI | Skills |
|------|:---:|:-----:|:---:|:------:|
| Claude Code | `~/.claude.json` | 5 hooks | `CLAUDE.md` | `/recall` `/remember` |
| Claude Desktop | JSON | — | — | — |
| Gemini CLI | `~/.gemini/settings.json` | 5 hooks | `GEMINI.md` | — |
| Codex CLI | `~/.codex/config.toml` | 4 hooks | `AGENTS.md` | — |
| Copilot CLI | `~/.copilot/mcp-config.json` | 4 hooks | `.github/copilot-instructions.md` | — |
| Cursor | `~/.cursor/mcp.json` | — | — | `.mdc` rule |
| Windsurf | JSON | — | `.windsurfrules` | — |
| VS Code | `~/Library/.../Code/User/mcp.json` | — | — | — |
| Amp | JSON | — | — | `/icm-recall` `/icm-remember` |
| Amazon Q | JSON | — | — | — |
| Cline | VS Code globalStorage | — | — | — |
| Roo Code | VS Code globalStorage | — | — | `.md` rule |
| Kilo Code | VS Code globalStorage | — | — | — |
| Zed | `~/.zed/settings.json` | — | — | — |
| OpenCode | JSON | TS plugin | — | — |
| Continue.dev | `~/.continue/config.yaml` | — | — | — |
| Aider | — | — | `.aider.conventions.md` | — |
Or manually:
bash
icm config # Show active config
Config file location (platform-specific, or $ICM_CONFIG):
~/Library/Application Support/dev.icm.icm/config.toml # macOS
~/.config/icm/config.toml # Linux
C:\Users\<user>\AppData\Roaming\icm\icm\config\config.toml # Windows
See config/default.toml for all options.
icm init --mode cli
Injects ICM instructions into each tool's instruction file:
| Tool | File |
|---|---|
| Claude Code | CLAUDE.md |
| GitHub Copilot | .github/copilot-instructions.md |
| Windsurf | .windsurfrules |
| OpenAI Codex | AGENTS.md |
| Gemini | ~/.gemini/GEMINI.md |
ICM can be used via CLI (icm commands) or MCP server (icm serve). Both access the same database.
| CLI | MCP | |
|---|---|---|
| **Latency** | ~30ms (direct binary) | ~50ms (JSON-RPC stdio) |
| **Token cost** | 0 (hook-based, invisible) | ~20-50 tokens/call (tool schema) |
| **Setup** | icm init --mode hook | icm init --mode mcp |
| **Works with** | Claude Code, Gemini, Codex, Copilot, OpenCode (via hooks) | All 17 MCP-compatible tools |
| **Auto-extraction** | Yes (hooks trigger icm extract) | Yes (MCP tools call store) |
| **Best for** | Power users, token savings | Universal compatibility |
icm是一个值得关注的开源MCP工具,提供了永久内存功能,适用于AI代理。它的简单易用和高性能使得它成为AI开发者的一种选择。然而,icm的稳定性和兼容性需要进一步的测试和验证。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:开源MCP工具:Permanent memory for AI agents 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | icm |
| 原始描述 | 开源MCP工具:Permanent memory for AI agents. Single binary, zero dependencies, MCP native.。⭐366 · Rust |
| Topics | ai-agentsmcprust |
| GitHub | https://github.com/rtk-ai/icm |
| License | Apache-2.0 |
| 语言 | Rust |
收录时间:2026-05-23 · 更新时间:2026-05-23 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端