代理记忆作为历史：巩固、锚点、来源层级、可问责的遗忘、源代码批评、叙事整合、正典流通、社会框架——基于记忆研究......
概览
记忆作为历史记录。它提供了一个基于SQLite支持的MCP服务器，具备明确的整合、源代码检查、修订、叙述版本和遗忘功能。 我合作了几个月的一位助理告诉我一些关于我自己项目的事情，直截了当地说，是事实。我问它从哪里来的。它无法告诉我。没有什么可说的：它保留的是一个评分足够高以存活下来的句子。是谁说的，它应该支持什么，是否有任何与之矛盾的地方——这些都没有被保留，因为评分的本意就是这些。 我不认为这是任何特定系统的bug。重要性权重、近期衰减、嵌入相似性——这些都是“我应该保留什么？”的答案。我想要一个不同的答案：我为什么相信这些，什么会让我停止。 这个问题不是关于存储的，我在软件里读内存时也没得到任何进展。
概述（AI 翻译）
英语 |简体中文
记忆作为历史记录了当时说了什么，哪些证据支持了某个说法，以及 采纳判断如何变化。它提供了一个SQLite支持的MCP服务器 明确的整合、来源核查、修订、叙述版本和遗忘。
为什么是历史，而不仅仅是记忆
一位我合作了几个月的助理告诉我一些关于我自己的事 项目，直白地陈述为事实。我问它从哪里来的。它说不出来 我。没有什么可说的：它保留的只是一句让我分心的句子 足够高以生存。谁说的，它应该支撑什么，是否 自那以后，任何与之相矛盾的证据都没有被保留，因为没有 这才是评分的重点。
我认为这不是任何特定系统的bug。重要性权重， 最近性衰减、嵌入相似性——它们都是“我应该做什么”的答案 “保持？”我想要一个不同的答案：为什么我会相信这些，并且 什么能让我停下来。
这个问题不是关于存储的，我读到的也没什么进展 软件中的记忆。我确实有所进展的是史学研究，也就是 他们花了一个世纪在同样问题的更糟糕版本上。
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
Memory as History
English | 简体中文
Memory as History records what was said, what evidence supports a claim, and how adopted judgments change. It provides a SQLite-backed MCP server with explicit consolidation, source checks, revisions, narrative versions and forgetting.
Why history, and not just memory
An assistant I’d been working with for months told me something about my own project, stated plainly, as fact. I asked where it got that. It couldn’t tell me. There was nothing to tell: what it had kept was a sentence that scored high enough to survive. Who said it, what it was supposed to support, whether anything had contradicted it since — none of that had been kept, because none of that was what the scoring was about.
I don’t think this is a bug in any particular system. Importance weights, recency decay, embedding similarity — they are all answers to “what should I keep?” I wanted an answer to a different question: why do I believe this, and what would make me stop.
That question isn’t about storage, and I got nowhere with it reading about memory in software. Where I did get somewhere was in historiography, which has spent a century on a worse version of the same problem.
The historians had it harder
A historian’s material is fragmentary, written by people with stakes, copied from other copies, and impossible to follow up on because the witnesses are dead. Nobody gets to re-run the query. And yet the discipline produces accounts you can argue with and correct — not by finding better sources, but by building a method around bad ones.
Marc Bloch wrote Apologie pour l’histoire in hiding, from memory, before the Gestapo shot him in 1944. It’s an unfinished book about craft, and the part that stuck with me is his insistence on splitting a question most people collapse: whether a document really comes from where it claims, and whether what it says is true. Those are separate investigations. He also points out that testimony which agrees almost word for word usually means one source copied three times, not three witnesses — which is, unfortunately, exactly what a scraped web page looks like.
Then there’s the part I almost missed. Trouillot’s Silencing the Past argues that the gaps in a record are produced, not accidental: something wasn’t written down, wasn’t kept, wasn’t narrated. So “no record of objection” is not “everyone agreed.” An agent that can’t distinguish those two will keep confidently reporting consensus that never existed.
安装
uvx memory-as-history配置
{
"mcpServers": {
"memory-as-history": {
"command": "uvx",
"args": ["memory-as-history"]
}
}
}