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

brethof-brain-dsh

v0.1.3

Published

brethof-brain memory for DeepSeek Harness (dsh) — native cordis plugin: session-start injection, per-prompt ambient recall, per-turn archiving.

Readme

brethof-brain cloud + DeepSeek Harness (dsh)

A native cordis plugin — the full brethof-brain contract on dsh's own typed extension points:

| Extension point | Effect | |---|---| | agent/session-start | your memory brain block injected before turn 1 | | agent/pre-step | ambient recall relevant to each prompt, added to the entered batch | | agent/turn-stopping | the turn (user + assistant) archived into long-term memory |

Every listener is fail-open: memory can never break a run.

Why native (not the Claude-Code hooks bridge)

dsh ships @deepseek-ai/dsh-hooks-claude-code, and it does run our hook set — but two dsh design decisions cap what a bridge can deliver (both measured 2026-08-22):

  • dsh executes hooks through ctx.shell, whose credential scrub strips *_API_KEY from hook process environments — env-configured hooks silently run keyless.
  • At Stop, the persisted transcript deliberately omits the open turn — a transcript-reading archiver can never see the exchange it is supposed to archive.

dsh's own design notes say bespoke integrations belong on the typed extension points. This plugin is that.

Install

# 1. Your key lives in the config FILE (the env var would be scrubbed):
mkdir -p ~/.brethof-brain
cat > ~/.brethof-brain/config.json <<EOF
{"api_key": "bmv2_YOUR_KEY", "default_project": "myproject"}
EOF

# 2. Install the plugin into your profile (from npm):
dsh plugin --profile <name> add brethof-brain-dsh

# 3. Register it — add to $DSH_HOME/profiles/<name>/cordis.patch.yml:
#    (new rows use the patch layer's `insert` form)
- insert:
    - id: brethof-brain
      name: brethof-brain-dsh

Restart the profile. Verify like every other platform: ask the agent to search memory — a well-formed answer, even "no results", means connected.

Optional row config (all default from ~/.brethof-brain/config.json):

- insert:
    - id: brethof-brain
      name: brethof-brain-dsh
      config:
        endpoint: http://127.0.0.1:8610
        project: myproject

Notes

  • Proven by the harness rig on dsh 0.1.1-rc.2 (fresh virtual machine, newest release, judged server-side by the Brain itself).
  • dsh is a developer preview and its APIs move; the rig run is what catches drift.
  • The archive index is per-session and the server UPSERTs on (session_id, index, text) — replays are idempotent; transient outages defer turns in memory and retry on the next turn's archive call.