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

@arvoretech/pi-slack-agent

v0.1.1

Published

Slack Agent that drives Pi via RPC with native streaming, thinking steps, and assistant APIs

Readme

Pi Agent — Slack

Agente de IA no Slack que conecta o Pi como agente nativo, com streaming em tempo real, thinking steps e suporte a imagens.

Setup rápido (5 min)

1. Crie o Slack App

  1. Vá em https://api.slack.com/apps → Create New AppFrom a manifest
  2. Selecione o workspace da Árvore
  3. Cole o conteúdo de manifest.json
  4. Crie o app
  5. Em Socket Mode → gere um App-Level Token com scope connections:write → copie o xapp-...
  6. Em Install App → instale no workspace → copie o Bot Token xoxb-...
  7. Em App Home → ative Messages Tab e marque "Allow users to send messages from the chat tab"

2. Descubra seu Slack User ID

No Slack: clique no seu perfil → Copy member ID (formato U...)

3. Configure o .env

cd packages/slack-agent
cp .env.example .env

Edite o .env:

SLACK_BOT_TOKEN=xoxb-seu-token
SLACK_APP_TOKEN=xapp-seu-token
ALLOWED_USER_IDS=seu-user-id
ANTHROPIC_API_KEY=sk-ant-sua-key
WORKSPACE_PATH=/caminho/dos/seus/repos

4. Rode

Com Docker (recomendado):

docker compose up -d

Sem Docker:

pnpm install && pnpm build
node dist/cli.js

5. Use

Abra o Slack → busque "Pi Agent" nos apps → mande uma mensagem. Cada thread é uma sessão independente.

Features

| Feature | Descrição | |---|---| | Streaming | Respostas aparecem em tempo real | | Thinking Steps | Cada tool executada aparece como task card com status | | Imagens | Cole screenshots/figmas e o Pi analisa | | Steering | Mande outra mensagem durante execução para corrigir o rumo | | Suggested Prompts | Botões prontos ao abrir o agent | | Thread = Sessão | Cada thread é uma sessão Pi persistente |

Comandos úteis

# Ver logs
docker logs -f slack-agent-pi-slack-agent-1

# Parar
docker compose down

# Rebuild após mudanças
docker compose up -d --build

Variáveis de ambiente

| Variável | Obrigatória | Descrição | |---|---|---| | SLACK_BOT_TOKEN | sim | Bot token xoxb-... | | SLACK_APP_TOKEN | sim | App-level token xapp-... | | ALLOWED_USER_IDS | sim | Seu Slack user ID (vírgula-separados se >1) | | ANTHROPIC_API_KEY | sim | API key do Anthropic (para o Pi usar Claude) | | WORKSPACE_PATH | sim | Caminho dos repos na sua máquina | | PI_MODEL | não | Modelo (default: Pi decide) |

Segurança

  • O agent tem acesso total aos repos montados (leitura + escrita + bash)
  • Só user IDs na allowlist podem usar
  • Rode apenas na sua própria máquina