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

@codehourra/llm-iwiki

v0.3.2

Published

面向 AI Agent 的本地知识库 CLI:采集 Claude Code / Cursor / Codex / CodeBuddy / Gemini 会话,按项目归一化,生成总结与经验并导出到 Obsidian。

Readme

llm-iwiki

English

npm version npm downloads Node.js Release License: MIT Changelog

把本地 AI 编程会话沉淀为可检索的 Obsidian 知识库。

llm-iwiki 会采集 Claude Code、Cursor、Codex、Gemini 和 CodeBuddy 的本地会话记录,按项目归一化到 SQLite,生成适合 AI 助手处理的总结任务,保存经过确认的项目经验,并导出为可导航的 Obsidian Markdown 笔记。

功能特性

  • 采集多个 AI 编程工具的本地会话记录。
  • 按项目、仓库、路径或 slug 解析和归类会话。
  • 为 AI 助手生成会话总结和经验提取任务文件。
  • 在发布到知识库前审核并采纳可复用的工程经验。
  • 导出项目摘要、会话笔记和项目经验到 Obsidian。
  • 更新托管内容块时保留用户手写区域。
  • 通过 CLI 检索会话摘要和已采纳经验。

环境要求

  • 运行时需要 Node.js 20 或更高版本。
  • 本地开发、测试和构建需要 Bun。

SQLite 由 better-sqlite3 提供;npm 安装时会自动下载可用的预编译二进制。

安装

npm install -g @codehourra/llm-iwiki

也可以不全局安装,直接使用 npx

npx @codehourra/llm-iwiki --help

快速开始

llm-iwiki init
llm-iwiki sync
llm-iwiki projects list
llm-iwiki projects inspect .

配置 Obsidian 库并导出笔记:

llm-iwiki config set obsidian.vault ~/Obsidian/Vault
llm-iwiki summarize prepare changed --project .
llm-iwiki summarize apply --project . --file .llm-iwiki/exchange/summaries.yaml
llm-iwiki experiences prepare --project . --from changed-summaries
llm-iwiki experiences propose --project . --file .llm-iwiki/exchange/experiences.yaml
llm-iwiki experiences candidates --project .
llm-iwiki experiences accept <candidate-id>
llm-iwiki obsidian export --project .

prepare 命令会生成供 AI 助手阅读的任务文件。根据任务文件编写对应 YAML 后,再用上面的 apply / propose 命令落库。

常用命令

llm-iwiki sync [--project <path>]
llm-iwiki projects list
llm-iwiki projects inspect <project>
llm-iwiki projects dedupe
llm-iwiki sessions list --project <project>
llm-iwiki sessions read <session-id>
llm-iwiki summarize prepare [changed|all] --project <project>
llm-iwiki summarize apply --project <project> --file <summaries.yaml>
llm-iwiki experiences prepare --project <project> [--since 30d]
llm-iwiki experiences propose --project <project> --file <experiences.yaml>
llm-iwiki experiences accept <candidate-id>
llm-iwiki search <sessions|experiences> <query>
llm-iwiki obsidian export [--project <project>|--all]
llm-iwiki obsidian check

<project> 可以是本地路径、proj_xxx 项目 id、展示名或 slug。如果匹配到多个项目,请先用 projects list 找到准确的项目 id。

Obsidian 输出结构

导出内容会写入已配置 vault 下的 LLM-iWiki/ 目录:

LLM-iWiki/
├── README.md
├── Projects/
│   └── <project-slug>/
│       ├── Project Summary.md
│       ├── sessions/
│       └── experiences/
└── Topics/

生成的笔记包含 frontmatter 和 aiwiki:managed 托管内容块。你可以在托管块之外自由补充内容;重新导出时会保留这些手写内容,除非显式使用 --force

AI 助手 Skill

将内置的 aiwiki-knowledge skill 安装到当前项目:

llm-iwiki skills init [--target codex|claude-code|cursor] [--force] [--dry-run]

这个 skill 会教兼容的 AI 助手如何执行 sync -> summarize -> experiences -> export 流程,以及如何为 summarize applyexperiences propose 生成合法 YAML。

开发

bun install
bun run typecheck
bun test
bun run build

项目使用 Changesets 管理版本号、变更记录和 npm 发布:

bun run changeset
bun run version-packages
bun run release

面向用户的变更应包含一个 .changeset/*.md 文件。GitHub Actions 会创建发布 PR,并在发布 PR 合并后发布到 npm。

变更记录

CHANGELOG.md

路线图

docs/roadmap.zh-CN.md

许可证

MIT