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

solo-memory

v1.0.0

Published

Local cross-tool AI chat history search and project recall CLI

Readme

Solo Memory

中文 | English

中文

Solo Memory 是一个本地 CLI,用于搜索 AI 编码助手的历史对话,并按项目目录召回相关上下文。支持 Codex 和 Claude Code 的本地对话记录;WorkBuddy 只能读取本地会话元信息和生成物,无法读取云端聊天正文。

运行要求

Node.js 22.5 或更新版本,需支持内置的 node:sqlite 和 FTS5。部分 Node.js 版本会显示实验性 API 警告。无需安装 npm 依赖。

安装与使用

发布到 npm 后可全局安装;在发布前可从源码安装:

npm install -g solo-memory
# 源码安装:git clone https://github.com/JiugeLi/solo-memory.git && cd solo-memory && npm install -g .
solo-memory index --source all
solo-memory search "K3S 部署" --limit 5
solo-memory recall "D:/my-project" --top 3 --format md
solo-memory compact "D:/my-project" --top 3

npm run build 使用 Bun 将 Node CLI 打包到 dist/;仅构建时需要 Bun,安装后的 CLI 由 Node.js 运行。compact 是输出 Markdown 精简上下文卡片的便捷命令,不会改写或压缩数据库;不传目录时默认当前工作目录。--db PATH 可覆盖默认数据库路径 ~/.solo-memory/memory.db。出现新对话后重新运行 index;索引所选来源时会更新已有记录,不会删除其他来源的数据。源文件删除后,数据库中的旧记录不会自动清除。搜索基于关键词(空格分隔的词采用 OR 匹配),不是语义搜索。项目召回使用启发式规则且会截断内容;重要信息请回查原始对话。

**隐私提醒:**本地索引保存未经脱敏的对话内容,可能包含凭据或私人信息。生成的数据库不包含在 npm 包或 Git 仓库中;不要发布生成的数据库或原始对话记录。

作为 Skill 使用时,请参阅 SKILL.md。

English

Local CLI for searching AI coding assistant conversations and recalling project context. Supports Codex and Claude Code local transcripts; WorkBuddy only supplies local session metadata and generated artifacts (not cloud chat messages).

Requirements

Node.js 22.5+ with built-in node:sqlite and FTS5. Some Node versions display an experimental API warning. No npm dependencies.

Install & usage

Once published to npm, install globally; before publication, install from source:

npm install -g solo-memory
# From source: git clone https://github.com/JiugeLi/solo-memory.git && cd solo-memory && npm install -g .
solo-memory index --source all
solo-memory search "K3S 部署" --limit 5
solo-memory recall "D:/my-project" --top 3 --format md
solo-memory compact "D:/my-project" --top 3

npm run build bundles the Node CLI into dist/ with Bun. Bun is needed for building only; the installed CLI runs on Node.js. compact prints truncated Markdown context cards; it does not compact the database. When omitted, the project directory defaults to the current directory. --db PATH overrides the default ~/.solo-memory/memory.db. Run index again when new conversations appear; selected sources are upserted without removing other sources. Deleted source files are not removed automatically from the database. Search is keyword-based (OR across whitespace-separated terms), not semantic search. Recall is heuristic and truncated: verify important details against the original conversation.

Privacy: The local index contains unredacted conversation text and may contain credentials or private information. The generated database is excluded from the npm package and Git repository. Never publish a generated database or raw transcripts.

For integration as a skill, see SKILL.md.