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

thought-cabinet

v0.2.0

Published

Thought Cabinet (thc) — CLI for structured AI coding workflows with filesystem-based memory and context management.

Readme

Thought Cabinet

A CLI tool that gives AI coding agents persistent, structured memory through filesystem-based notes and version-controlled knowledge sharing.

Why Thought Cabinet?

AI coding agents like Claude Code are powerful but face key challenges:

  • Context limits: Large codebases exceed model context windows
  • No persistent memory: Agents forget learnings between sessions
  • Unstructured work: Complex tasks benefit from planning before implementation
  • Isolation: AI-generated knowledge isn't easily shared with teams

Thought Cabinet solves these by providing:

  • Context offloading: Research and plans are saved to disk, freeing model context
  • Filesystem memory: Version-controlled thoughts persist across sessions
  • Structured workflows: Slash commands guide agents through research → plan → implement → validate
  • Team sharing: Thoughts sync via git, enabling knowledge sharing

Quick Start

cd your-project

# 1. Install
pnpm install -g thought-cabinet

# 2. Initialize thoughts in your project
thc init

# 3. Install skills to your AI agent
thc skill install

# 4. Use skills in your agent session (e.g. Claude Code)
> /research-codebase How does the authentication system work?
> /creating-plan Add OAuth2 support based on the research
> /implementing-plan thoughts/shared/plans/add-oauth.md
> /validating-plan thoughts/shared/plans/add-oauth.md

Skills

Skills are installed by thc skill install and invoked as slash commands in your agent session:

| Skill | Description | | -------------------- | --------------------------------------------------------------------- | | /research-codebase | Deep-dive into codebase, save findings to thoughts/shared/research/ | | /creating-plan | Create implementation plan with phases and success criteria | | /iterating-plan | Refine existing plans based on feedback | | /implementing-plan | Execute plan phase-by-phase with verification | | /validating-plan | Verify implementation against plan's success criteria | | /commit | Create git commits with clear, descriptive messages |

Typical workflow: research the codebase to build understanding, create a plan, iterate until the plan is solid, implement it, then validate the result.

Core Concepts

Thoughts as Memory

The thoughts/ directory is a filesystem-based memory system for AI agents:

thoughts/
├── {user}/           → Personal notes (your learnings, scratchpad)
├── shared/           → Team-shared knowledge
│   ├── research/     → Codebase research documents
│   └── plans/        → Implementation plans
└── global/           → Cross-repository thoughts

All thoughts are version-controlled via a dedicated git repository, separate from your code. Sync with thc sync.

Context Offloading

AI agents have limited context windows. Thought Cabinet offloads context to the filesystem:

┌─────────────────┐     ┌─────────────────────────────┐
│  Model Context  │     │  filesystem (thoughts/)     │
├─────────────────┤     ├─────────────────────────────┤
│ Current task    │ ←── │ research/auth-system.md     │
│ Active code     │     │ plans/add-oauth.md          │
│ Recent changes  │     │ previous session learnings  │
└─────────────────┘     └─────────────────────────────┘

Research and plans are written to disk. The agent reads back only what it needs, freeing context for active work.

CLI Overview

| Command | Description | | ------------------- | -------------------------------------------------- | | thc init | Initialize thoughts for current repository | | thc sync | Sync thoughts to git repository | | thc status | Show thoughts repository status | | thc skill install | Install skills and agents to your AI coding agent | | thc skill update | Update installed skills from latest package bundle | | thc config | View or edit configuration |

See docs/CLI.md for the full command reference with all flags and options.

Advanced Topics

  • Worktrees — Parallel development with git worktrees and tmux sessions
  • Hooks — Custom hooks that run on thought and worktree lifecycle events

License

Apache-2.0

Credits

  • The name "Thought Cabinet" is from CRPG Disco Elysium created by Robert Kurvitz, Aleksander Rostov, Helen Hindpere and others
  • The thoughts system is based on humanlayer