npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

pi-everos

v0.2.0

Published

EverOS Cloud memory plugin for Pi Agent: proactive recall and save via uvx MCP.

Readme

pi-everos

官方入口: 已提交到 EverMind-AI/Plugins 的 pi/(PR #33)。

本仓库继续作为 pi install git: / npm 的安装源(Pi 不能装 git 子目录)。两边怎么同步见 MAINTENANCE.md。

pi-everos 诊断与 /everos 命令

给 Pi Agent 接上 EverOS Cloud 云端记忆。安装后自动注册 uvx everos-mcp(exposure: direct),并把记忆协议注入每次运行,模型会自己检索和保存,不必每次说「去查 EverOS」。

用户记忆协议段默认英文(受 prompt.maxTokens 限制)。agent 经验(case/skill)另有一段 everos-agent,不受该上限挤压。/everos 命令与 doctor 跟随 PI_LANG/LANG(zh 用中文)。

需要

安装

pi install npm:pi-everos

本仓库(Pi 不能装 git 子目录,所以 git 安装仍指向这里):

pi install git:github.com/Chasen-Liao/pi-everos

官方仓(clone 后装子目录):

git clone https://github.com/EverMind-AI/Plugins.git
pi install ./Plugins/pi

装好后新开一个 Pi 会话,可用 /everos doctor 检查连接。

若 ~/.pi/agent/mcp.json 里已有启用的 everos 条目,文件配置会覆盖插件,插件改用 everos-pi。把该条目设为 enabled: false 或改名后 /reload,插件即可占用 everos。插件不会改你的 mcp.json。

命令

/everos status
/everos login
/everos logout
/everos scope
/everos reconnect
/everos doctor
  • 登录不把 API key 写入 everos.json。设好用户环境变量后 /everos login 或 /everos reconnect 会重新读 key。
  • /everos logout 只断开本插件并写入 enabled: false,不删除系统里的 EVEROS_API_KEY。

作用域

  • 项目连接:当前工作区(projectId: auto 时用目录名)
  • 全局连接:everos-global(默认 global)
  • /everos scope auto|project <id>|global <id> 可改映射
  • agent 身份:assistantSenderId(默认 assistant-<userId>)。case/skill 挂在这个 id 上;改了会看不到旧经验

Agent 经验

EverOS 把完整任务轨迹蒸馏成 case(一次怎么做的),相近 case 再聚成 skill(可复用做法)。插件不在本地提取:模型调用 record_trajectory / recall_agent_experience,Cloud 后台完成蒸馏(数秒到数分钟)。

  • 轨迹默认写入当前项目;只有用户明确要求记下跨项目习惯时才写全局
  • 召回先查项目,没有相关经验再查全局
  • 需要超过三轮工具调用才会生成 case;更短的轨迹不要 record_trajectory
  • forget_session 删除本会话记忆和 case,保留已经学到的 skill

开发

npm test
pi -e ./extensions/index.ts

架构见 docs/architecture.md。

限制

  • 默认是 uvx everos-mcp + API key,7 个工具。
  • 远程 OAuth MCP 不是 v1 默认。
  • plan 模式会拦截 add_memory / forget_session / record_trajectory。
  • forget_session 会先向你确认;不会删除已学到的 skill。