rtk-ai/icm

英语 |法语 |西班牙语 |德语 |意大利语 |葡萄牙语 |荷兰语 |波兰语 |Русский |日本語 |中文 |العربية |한국어

ICM

AI编码代理的长期记忆，跨工具共享。 一个二进制文件，一个SQLite文件。没有LLM调用来存储或调用内存。

周一告诉 Claude Code 你的项目如何处理认证，周二的 Gemini CLI 会议已经知道了。ICM 将编码代理学到的内容（决策、修复、约定、偏好）保存在你机器上的一个 SQLite 文件中，并在每次会话开始和你发送的每个提示时回归相关部分。最多有 18 个代理和编辑器共享这些内存，这样你就不必每次打开会话或切换工具时都重新解释你的项目。

• LoCoMo 92.9%（1,540道题，平均三次运行），与《Hindsight》持平（92.0%），每题背景少三分之一。以下有详细信息和注意事项。
• 无需调用LLM来存储或回忆。 Hindsight、Mem0、Graphiti（Zep）和claude-mem默认调用它们存储的每个内存都会调用LLM。ICM则不支持。

English | Français | Español | Deutsch | Italiano | Português | Nederlands | Polski | Русский | 日本語 | 中文 | العربية | 한국어

ICM

Long-term memory for AI coding agents, shared across your tools. One binary, one SQLite file. No LLM call to store or recall a memory.

Tell Claude Code how your project handles auth on Monday, and Tuesday’s Gemini CLI session already knows it. ICM keeps what your coding agents learn (decisions, fixes, conventions, preferences) in one SQLite file on your machine, and gives the relevant part back at the start of each session and with each prompt you send. Up to 18 agents and editors share that memory, so you stop re-explaining your project every time you open a session or switch tools.

• 92.9% on LoCoMo (1,540 questions, mean of three runs), level with Hindsight (92.0%), with a third less context per question. Details and caveats below.
• No LLM call to store or recall. Hindsight, Mem0, Graphiti (Zep) and claude-mem call an LLM for every memory they store by default. ICM does not. Only its automatic extraction of facts from tool output goes through the LLM command-line tool you already use, when one is installed; provider = "none" keeps that local too (see Quickstart).
• Useful without an embedding model. Keyword recall alone puts at least one of the right sessions in the top 5 for 88.6% of LoCoMo questions, with a median of 6.8 ms per recall on Linux x86-64.
• 97.4% on LongMemEval-S, retrieval with no LLM: one of the right sessions in the top 5 for 487 of 500 questions, against 96.6% for MemPalace and 95.2% for agentmemory on the same measure.
• Not ahead everywhere. On PersonaMem (a user’s evolving preferences), Hindsight leads: 86.6% against ICM’s 81.7%.

Quickstart

brew tap rtk-ai/tap && brew install icm    # or: curl -fsSL https://raw.githubusercontent.com/rtk-ai/icm/main/install.sh | sh
icm init                                   # instructions, skills and hooks for every agent it detects