RO

richarvey/omnimem

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

63 stars 7 forks 质量 69 趋势 34MIT

为AI代理提供自托管语义记忆。持续会话、经验评分和死胡同的墓地,这些知识由你阅读并存储在Valkey矢量中的RSS中获得的知识支撑......

概览

开发发生在Squarecows上——请在那里提供问题和公关。 每次Claude Code的会话都是从零开始的。对你的项目毫无记忆。对上周失败的事情毫无记忆。不记得你上周二花了三个小时才发现为什么Onnxruntime在Alpine上爆炸,才找到真正能用的东西。 于是你又解释了一遍项目。克劳德又建议用同一个坏掉的图书馆。同样的警报。同样的歌。你是比尔·默里,克劳德是潘克苏托尼。 OmniMem 解决了这个问题。它是一个自托管的 MCP 服务器,为你的 AI 代理提供跨会话、项目和机器的持久内存。它运行在你自己的硬件上,且永久免费。 那个警告是凭记忆说的,不是运气好。你已经付钱的错误不能再被收费两次。 一个命令可以让整个栈从预构建的 Docker Hub 镜像中运行:然后指向你的代理——快速启动会带你走过剩下的部分,或者跳转到下面更完整的快速启动部分。

概述(AI 翻译)

omnimem.org ·在Squarecows上开发,镜像到GitHub ·GitHub上的问题

别再经历同一场游戏了。

每个编码代理会话都是从零开始的。它不知道你的项目。它不记得上周哪里失败了。它根本不知道你在搞懂为什么WebKitGTK默默无视自定义URL方案的重定向时浪费了一个晚上。

于是你又把一切都解释清楚,经纪人自信地提出了那个没用的方案。同样的警报,同样的歌。你是比尔·默里,你的经纪人是潘克苏托尼。

OmniMem 解决了这个问题。它为你的 AI 代理提供跨会话、项目和机器的内存,通过 MCP 运行,所以它可以和你喜欢的任何代理配合使用。它运行在你自己的套件上,而且是免费的。

那个警告是凭记忆说的,不是运气。你已经付过钱的错误不能再被收费两次。

[!注] 7.0.3 是 OmniMem 7 的第一个版本:用一个应用替代了 6.x 运行的四个容器。每个平台的安装程序都在发布页面。运行 6.x 吗?参见 Coming from 6.x:6.x Docker 栈仍保留在 v6.7.x 分支,其一行安装程序仍然可用。


一个程序,两种运行方式

OmniMem 7 是一个单一二进制。

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。

omnimem.org · Developed on Squarecows, mirrored to GitHub · Issues on GitHub

Stop living the same session twice.

Every coding agent session starts from zero. It doesn’t know your project. It doesn’t remember what failed last week. It has no idea you lost an evening working out why WebKitGTK quietly ignores a redirect from a custom URL scheme.

So you explain everything again, and the agent confidently suggests the exact thing that didn’t work. Same alarm, same song. You’re Bill Murray and your agent is Punxsutawney.

OmniMem fixes that. It gives your AI agent a memory that lasts across sessions, projects and machines, over MCP, so it works with whichever agent you like. It runs on your own kit and it’s free.

claude> answer the settings form with a 303 redirect

⚠ WARNING: previously abandoned approach

  303 from omnimem://: WebKitGTK never follows it (effort: 4/5)
  → answer with a page that replaces itself instead

That warning came from memory, not luck. A mistake you’ve already paid for doesn’t get to charge you twice.

[!NOTE] 7.0.3 is the first release of OmniMem 7: one app in place of the four containers 6.x ran. The installers for every platform are on the releases page. Running 6.x? See Coming from 6.x: the 6.x Docker stack stays on the v6.7.x branch, and its one-line installer still works.


One program, two ways to run it

OmniMem 7 is a single binary. The MCP server, the memory engine, the embedding model, RSS ingestion and the database all live in one process, with your memories in one SQLite file. No containers to wrangle, no database server to babysit.

  • On your desktop it sits in the tray (or the menu bar on a Mac). The icon tells you it’s running, copies the MCP address for you, and opens a settings window where you can browse memories, review skills, edit your feeds, take backups and change settings.
  • On a server it’s omnimem serve: a systemd service from the .deb or .rpm, or a container, configured with environment variables (one .env file for the service), with nothing graphical anywhere near it.

The embedding model (all-MiniLM-L6-v2 on ONNX Runtime) runs locally. Nothing leaves the machine unless you add an Anthropic API key for the optional Claude Haiku features: fact extraction, query expansion, deeper contradiction checks and RSS summaries.

在 GitHub 查看完整 README

安装

This server does not publish a one-line install command.

Open the repository installation guide 新手?先看 mcpskill.org 教程 →