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

getdevbrain

v1.0.0

Published

Git-backed prompt memory and resume skills for Claude Code and Codex — the log is the agent.

Downloads

22

Readme

Every prompt is captured to a private, git-synced markdown store, distilled into a searchable brain, and replayable by any future session or machine. Markdown + git is the source of truth; everything else is a rebuildable projection. Built for Claude Code, with the same workflows installed as skills in other agents (e.g. Codex).

How It Works

devbrain install wires Claude Code (and any other installed agents) on this machine, then gets out of the way:

A. Capture    every prompt → raw markdown log      automatic, model-free · source of truth
B. Brain      /distill → brain pages + queue        markdown on disk · searchable, rebuildable
C. Assemble   /continue → brief + work top task     opens a minimal-MVP PR · /loop to drain

The hooks are devbrain hook <event> commands registered in the agent's settings.json — a UserPromptSubmit hook logs every prompt verbatim; a 5-min timer commits and pushes it off-machine. Config lives at ~/.config/devbrain/config.json. The markdown log layout is the same across agents, with only header metadata naming which one. /distill folds new log into linked brain pages and queue tasks; /continue pulls what's relevant, briefs you, and works the top task. The log is keyed by git remote, so all worktrees of a repo collapse to one project. Full design in DESIGN.md.

Only the system ships. devbrain is a single binary. Your prompts and brain live in a separate private store at ~/devbrain-data that you own — devbrain install creates it; give it a private remote to back up and sync.

Install

brew install TheWeiHu/devbrain/devbrain
devbrain install

No Homebrew? go install github.com/TheWeiHu/devbrain/cmd/devbrain@latest or grab a release tarball and put devbrain on PATH.

devbrain install is idempotent and wires only this machine. In a terminal it asks y/n per component; non-interactive runs take every default. When it finishes it opens the browser dashboard (devbrain queue — Board · Nightshift · Profile). Common flags:

devbrain install --without nightshift          # skip the overnight loop
devbrain install --only capture                # just the prompt-capture hook
devbrain install --no-open                     # don't auto-open the dashboard
DEVBRAIN_DATA=~/path devbrain install          # store the brain elsewhere

devbrain needs only your coding agent and Git — no python3 or Node. Some agents may ask you to review and trust the installed hooks with /hooks on next startup; that is their normal hook trust flow.

Daily Use

| Command | What it does | |---|---| | (automatic) | every prompt captured; flusher commits and pushes every 5 min | | /distill | fold new log → brain pages and queue tasks | | /continue | resume: brief, then work the top task as a minimal-MVP PR | | /work | lean drain turn: top task → MVP PR, no fold-in/briefing (for /loop + nightshift) | | /loop /work | keep draining the queue fast, one MVP PR per task | | /reconcile | mark brain facts the live repo contradicts (auto-runs ~daily) | | gbrain search / devbrain brain search | query the brain from the shell (gbrain if installed, else offline grep) | | devbrain queue | browser control plane for the queue (view · edit · prioritize · unblock) | | devbrain help | every devbrain subcommand |

The brain records what happened; the queue records what's next — one markdown file per task, priority-ranked. /distill fills it, /continue drains it, and a task isn't done until its PR merges. Agents without slash commands run the same workflows as skills ($distill, $continue, $work, $reconcile).

nightshift

Run several claude workers in parallel against the queue, each in its own worktree, auto-merging green work onto a throwaway nightshift branch — you wake to one git diff main...nightshift.

devbrain nightshift start ~/nightshift/myrepo   # launch the fleet (runs until stopped)
devbrain nightshift watch                       # live browser dashboard
devbrain nightshift stop                        # stop the fleet

Installing it never spawns anything — the fleet runs only when you start it, and it does autonomous git ops and spends real tokens, so point the first runs at a throwaway. You stay the only nightshift → main gate.

More

  • DESIGN.md — architecture, the TODO queue, and the golden rule (never lose the log)
  • SECURITY.md — what's captured, where it's stored, who can see it, and how to report a vuln
  • CHANGELOG.md — release history
  • make test — run the full suite
  • Ranked + semantic brain search comes from the optional gbrain engine, installed by default; skip it with devbrain install --without-gbrain and the offline devbrain brain search still works.
  • devbrain import — seed the brain from your existing agent transcripts.
  • Re-run devbrain install anytime; it only adds what's missing. Tear down with devbrain uninstall (leaves your data untouched).