![\"Mascote](\"\/wp-content\/uploads\/2026\/09\/hermes-agent-hq.webp\")
<\/p>\n<\/p>\n
AI agents that live in your terminal have become a commodity \u2014 but an agent that learns from its own experience<\/em> is still rare. Hermes Agent<\/a><\/strong>, from Nous Research<\/a>, is exactly that: an open source agent (MIT, written in Python) with a built-in learning cycle \u2014 it creates skills from the tasks it performs, improves those skills through use, keeps memory between sessions and builds a model of who you are over time. And it isn't tied to your laptop: it runs on a 5-dollar VPS and you talk to it through Telegram while it works in a cloud VM.<\/p>\n Hermes is a general-purpose AI agent with two entry points: a full terminal TUI<\/strong> (multiline editing, command autocomplete, history, streaming tool output) and a messaging gateway<\/strong> that connects it to Telegram, Discord, Slack, WhatsApp, Signal and email \u2014 all in one process, with conversation continuity across platforms and even voice message transcription.<\/p>\n What sets it apart from competitors is its closed learning loop:<\/p>\n No model lock-in: works with Nous Portal, OpenRouter, OpenAI or your own endpoint (a local llama-server, for example). Switching models takes a One line:<\/p>\n When it finishes, reload the shell and launch the agent:<\/p>\n Everything lives in The fast route is the full wizard, which configures the provider, model, tools and gateway at once:<\/p>\n Or in parts:<\/p>\n If you'd rather not collect five API keys (model, web search, image generation, TTS, cloud browser), Nous Portal<\/strong> covers everything in one subscription, with more than 300 models available:<\/p>\n The everyday magic is in the gateway: you talk to the same agent from the terminal, Telegram or Slack, and the conversation picks up where it left off:<\/p>\n Inside any conversation (CLI or messenger), the commands are the same: If you already use an AI agent in the terminal, Hermes is in another category because of memory and skills: it gets better in your<\/em> environment as the weeks pass, and the messaging gateway turns any Linux server into an assistant available in your pocket. The project is MIT, has complete documentation<\/a> and an active community on the Nous Research Discord.<\/p>\n Install it, run a AI agents that live in your terminal have become a commodity \u2014 but an agent that learns from its own experience is still rare. Hermes Agent, from Nous Research, is exactly that: an open source agent (MIT, written in Python) with a built-in learning loop \u2014 it creates skills from the tasks it \u2026 Read more<\/a><\/p>","protected":false},"author":0,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[115,2,111],"tags":[333,332,116,128,334,5],"class_list":["post-688","post","type-post","status-publish","format-standard","hentry","category-ia","category-linux","category-opensource","tag-agente","tag-hermes","tag-ia","tag-llm","tag-nous-research","tag-ubuntu"],"_links":{"self":[{"href":"https:\/\/www.linuxpro.com.br\/en\/wp-json\/wp\/v2\/posts\/688","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.linuxpro.com.br\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.linuxpro.com.br\/en\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/www.linuxpro.com.br\/en\/wp-json\/wp\/v2\/comments?post=688"}],"version-history":[{"count":4,"href":"https:\/\/www.linuxpro.com.br\/en\/wp-json\/wp\/v2\/posts\/688\/revisions"}],"predecessor-version":[{"id":1443,"href":"https:\/\/www.linuxpro.com.br\/en\/wp-json\/wp\/v2\/posts\/688\/revisions\/1443"}],"wp:attachment":[{"href":"https:\/\/www.linuxpro.com.br\/en\/wp-json\/wp\/v2\/media?parent=688"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.linuxpro.com.br\/en\/wp-json\/wp\/v2\/categories?post=688"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.linuxpro.com.br\/en\/wp-json\/wp\/v2\/tags?post=688"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}What Hermes Agent is<\/h2>\n
\n
hermes model<\/code> \u2014 no code changes.<\/p>\nWhat you need<\/h2>\n
\n
curl<\/code> and internet access \u2014 the installer handles the rest: uv, Python 3.11, Node.js, ripgrep and ffmpeg<\/strong><\/li>\nInstalling on Ubuntu<\/h2>\n
curl -fsSL https:\/\/hermes-agent.nousresearch.com\/install.sh | bash<\/code><\/pre>\nsource ~\/.bashrc\nhermes<\/code><\/pre>\n~\/.hermes<\/code>. If something seems odd, the agent diagnoses itself:<\/p>\nhermes doctor\nhermes update # atualizar para a vers\u00e3o mais recente<\/code><\/pre>\nBasic configuration<\/h2>\n
hermes setup<\/code><\/pre>\nhermes model # escolher provedor e modelo de LLM\nhermes tools # ligar\/desligar ferramentas\nhermes config set # ajustar valores individuais\nhermes config get # conferir a configura\u00e7\u00e3o<\/code><\/pre>\nhermes setup --portal # login OAuth + Tool Gateway numa tacada\nhermes portal info # ver o que ficou habilitado<\/code><\/pre>\nMessaging integrations<\/h2>\n
hermes gateway setup # assistente: escolhe plataformas e tokens de bot\nhermes gateway start # sobe o gateway (Telegram, Discord, Slack, WhatsApp, Signal, e-mail)<\/code><\/pre>\n\/new<\/code> restarts, \/model<\/code> switches the model, \/personality<\/code> changes the persona, \/compress<\/code> compresses the context, \/skills<\/code> lists learned skills. There's also DM pairing and command approval as security layers.<\/p>\nOther integrations<\/h2>\n
\n
Is it worth it?<\/h2>\n
hermes setup<\/code> and give it a week of real tasks \u2014 then tell me on the contact page<\/a> how it went.<\/p>","protected":false},"excerpt":{"rendered":"