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

cogitlog

v0.6.1

Published

Semantic memory protocol for AI agents working in codebases

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

caioldcarvalhocaioldcarvalho

Keywords

Readme

cogitlog

Semantic session memory for AI agents working in codebases.

cogitlog records what an AI agent did, decided, and why — stored alongside git history so future agents (and humans) can understand not just what changed but why.

Install

npm install -g cogitlog

Quick start

# In your project
cogitlog init

# At the start of every AI task
cogitlog begin "add dark mode toggle"

# During the task
cogitlog note "using CSS custom properties, not a theme provider"
cogitlog decision "store preference in localStorage, not a cookie" \
  -a "cookie:overkill for a UI-only setting"
cogitlog attempt "toggling class on <html>" --outcome failed \
  --reason "SSR mismatch on first render"
cogitlog uncertainty "not sure if prefers-color-scheme should override manual toggle"

# At the end
cogitlog close --outcome completed

Commands

| Command | Description | |---|---| | init | Initialize .cogitlog/ in the current directory | | remindme | Append cogitlog reminder to agent instruction files (CLAUDE.md, etc.) | | begin "<intent>" | Open a new session | | note "<text>" | Add a free-form note | | decision "<text>" | Record a decision (supports --alternative "option:reason") | | attempt "<text>" --outcome <succeeded\|failed\|partial> | Record an attempt and its outcome | | uncertainty "<text>" | Flag something you are not sure about | | close --outcome <completed\|partial\|abandoned\|interrupted> | Close the current session | | log | List recent sessions | | show [session-id] | Show full detail of a session | | why <file> | Show decisions that touched a file | | query "<text>" | Search sessions by intent / outcome note | | status | Show the current session status | | onboard | Print usage instructions (useful to paste into agent context) | | hook install | Install a post-commit hook that auto-closes sessions on git commit | | repair | Rebuild index.jsonl from session files |

How it works

cogitlog init creates a .cogitlog/ directory with:

  • index.jsonl — lightweight index of all sessions (intent, outcome, files touched)
  • sessions/<id>.jsonl — full event log per session
  • AGENTS.md — instructions for agents that discover the directory

It also appends a usage reminder to any existing agent instruction files it finds (CLAUDE.md, AGENTS.md, GEMINI.md, .cursorrules, etc.).

Sessions are plain JSONL files — no server, no database.

Integrating with your agent workflow

After cogitlog init, agents that read CLAUDE.md (or equivalent) will see the reminder automatically. For projects where cogitlog was initialized without an instruction file, run:

cogitlog remindme

This appends the reminder to any existing instruction files, or creates CLAUDE.md if none are found.

License

MIT