Home / hermes-brasil / hermes-brasil · skills/hermes-philosophy-podcast/SKILL.md · GitHub

hermes-philosophy-podcast skillA

hermes-philosophy-podcast is agent-read markdown (skill) from hermes-brasil/hermes-brasil: Insights do podcast Peter Yang com Karan Malhotra (Nous)..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Filosofia Hermes — Podcast Peter Yang + Karan Malhotra (Nous Research)

> Fonte: "Hermes Co-Founder on Building an AI Agent That Improves Itself" (Peter Yang, 02/08/2026)
> Karan Malhotra — co-fundador da Nous Research (empresa por trás do Hermes Agent).
> YouTube: UWjh5Z4s8jY · Podcast também no Spotify/Apple.

## Contexto
Karan co-fundou a Nous Research (2023) com Jeffrey Quesnelle, Teknium e Shivani Mitra. Hermes é o #1 agente pessoal e app de IA no OpenRouter. Nous Research em negociação de valuation US$1,5bi (Jul/2026). ~214k estrelas no GitHub.

## Pontos-chave do episódio

### 1. O modelo é DESCARTÁVEL, o contexto é OURO
```
"O 'pessoal' no agente pessoal NÃO é o modelo.
É a MEMÓRIA das conversas + as SKILLS que você construiu."
```
- Trocar de modelo (DeepSeek, Claude, etc.) quase não muda a personalidade
  se o agente acumulou contexto suficiente sobre o usuário
- O modelo é intercambiável; a camada de contexto (memória + skills + self-improvement) é o ativo que preservar
- APLICAÇÃO: valorizar memória/skills como "segundo cérebro" que persiste entre modelos

### 2. Hermes melhora sem virar slop (self-improvement loop)
```
…

Read the whole file at its exact version.

How to install

Latest version
mdr add hermes-brasil/hermes-brasil/hermes-philosophy-podcast@git:20260804.5e2ca7f
Exact content
mdr add hermes-brasil/hermes-brasil/hermes-philosophy-podcast@sha256:994e0e8ff0fd4f65

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ypdb2xggxwydhxlg.svg)](https://markdownregistry.com/a/art_ypdb2xggxwydhxlg)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260804.5e2ca7f latest2026-08-04 5e2ca7f 3,280 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3280 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

hermes-brasil/hermes-brasil · 144 stars · license MIT · pushed 2026-09-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ypdb2xggxwydhxlg
GET https://markdownregistry.com/api/v1/resolve?ref=hermes-brasil/hermes-brasil/hermes-philosophy-podcast
GET https://markdownregistry.com/api/v1/blob/994e0e8ff0fd4f65d878132bbca333ac48830a2a7beea34a13dd796fd5fcde49

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from hermes-brasil/hermes-brasil

anti-ai-slop skill
hermes-brasil/hermes-brasil · skills/anti-ai-slop/SKILL.md · Protocolo de revisão editorial para eliminar AI slop em textos PT-BR e EN. Use em toda peça escrita antes da entrega…
v1.0.0 · audit A · 144 stars
hermes-ops-producao skill
hermes-brasil/hermes-brasil · skills/hermes-ops-producao/SKILL.md · Operar Hermes Agent em produção no VPS — update, restart de gateway, health-check, profiles múltiplos e ambientes sem…
git:20260804.b558aec · audit A · 144 stars
orquestracao-kanban-humano-agente skill
hermes-brasil/hermes-brasil · skills/orquestracao-kanban-humano-agente/SKILL.md · Orquestrar projetos com Kanban humano + agentes de IA.
git:20260804.a5390e5 · audit A · 144 stars
prospeccao-b2b-comercio-local skill
hermes-brasil/hermes-brasil · skills/prospeccao-b2b-comercio-local/SKILL.md · Prospeccao B2B de comercio local (Google Places + WhatsApp + registro).
git:20260803.34bcfeb · audit A · 144 stars
rag-assistente-conhecimento skill
hermes-brasil/hermes-brasil · skills/rag-assistente-conhecimento/SKILL.md · Criar assistente RAG com conhecimento da empresa.
git:20260803.34bcfeb · audit A · 144 stars
think-tank-research skill
hermes-brasil/hermes-brasil · skills/think-tank-research/SKILL.md · Use quando precisar de pesquisa multi-persona com síntese protegida por evidências.
v0.1.0 · audit A · 144 stars
triagem-conteudo-externo skill
hermes-brasil/hermes-brasil · skills/triagem-conteudo-externo/SKILL.md · Tratar conteúdo externo não confiável antes de agir.
v1.0.0 · audit A · 144 stars

Every file in hermes-brasil/hermes-brasil

Browse by kind, by grade A, or by owner.