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

agentory

v0.0.2

Published

A CLI tool to help monitor AI agents

Downloads

34

Readme

Agentory

A CLI tool with a web UI to help monitor AI agents status and progress.

Setup and usage

Install globally:

npm install -g agentory

Setup AI agents

First let's setup our agents:

agentory setup

The command will discover installed AI agents on your machine and configure them so send status updates to the agentory tool.

Start watching

To start the server and dashboard:

agentory

This starts a background server (if one is not already running) and opens the TUI. Quit with q or Ctrl+C — the server keeps running. Run agentory again to reopen the dashboard.

agentory stop

stops the background server.

agentory serve --no-tui      # start the server and exit
agentory serve --foreground  # run the server in this process (no TUI)

Notifications

The dashboard bell still rings on status changes. The background server can also fan those out to webhooks, Slack, Discord, Telegram, email, or a local command.

Config lives in ~/.agentory/notifications.json (edits apply without restarting). By default channels fire on idle, error, prompted, and removed. Session added is ignored unless you include it in trigger. The TUI notify toggle and per-agent mute still apply.

agentory notify add command --command 'notify-send "{{agent_name}} is {{status}}" "{{title}}"'
agentory notify add slack --url https://hooks.slack.com/services/...
agentory notify add discord --url https://discord.com/api/webhooks/...
agentory notify add telegram --token "$BOT_TOKEN" --chat-id "$CHAT_ID"
agentory notify add webhook --url https://example.com/hook
agentory notify add email \
  --host smtp.gmail.com --port 587 \
  --from [email protected] --to [email protected] \
  --username [email protected] --password-env GMAIL_APP_PASSWORD
agentory notify add slack --url https://hooks.slack.com/services/... --trigger idle,error,prompted,added,removed
agentory notify list
agentory notify test
agentory notify disable slack

Template variables: {{event}} (idle/error/prompted/working/added/removed), {{agent_name}}, {{status}}, {{previous_status}}, {{title}}, {{directory}}, {{host_name}}, {{user_name}}, {{model_id}}, {{provider_id}}, {{instance_id}}, {{first_seen_at}}, {{last_event_at}}, {{tmux_session}}, {{tmux_window}}, {{tmux_pane}}, {{json}}.

The command channel also sets AGENTORY_* env vars (e.g. AGENTORY_AGENT_NAME). Commands run with your user privileges; prefer env vars if agent fields may contain shell metacharacters.