what it is
A personal AI assistant agent from Nous Research. It’s a one-command install followed by a guided setup. Nous pitches it as a self-hosted assistant that writes and sends email, runs research and pairs with a coding tool.
how I use it
I installed it in August 2026 to try it.
what I found
- The install bundles its own Node runtime (Node 26) and symlinks
node,npmandnpxonto the PATH. On my machine that shadowed nvm, and a project that needs Node 24 started running on 26. - I first saw it in a Russian-language AI Telegram channel. The author ran it on Codex with a GPT-5.5 subscription and framed the cost as a binary choice, “either pay Anthropic for tokens, or use Codex.” The agent needs a capable backing model either way.
- The same author seeded the agent’s context by running one “build a profile of me” prompt in ChatGPT, Claude and Manus and feeding the result in. The prompt works for any new assistant. Translated from the Russian below.
Build a brief profile about me for a new personal AI assistant, based on our past conversations.
Include:
- Who I am, what I do, my roles and projects.
- My long-term goals.
- My current active projects and interests.
- What communication style I prefer.
- How I like to receive answers: brief/detailed, lists/tables, with/without recommendations.
- Which languages to use.
- My typical tasks for the assistant.
- Which decisions I usually make myself, and what can be delegated.
- My limits, taboos, sensitive topics.
- Any stable preferences: tools, services, workflows.
- What’s important for the new assistant NOT to forget about me.
Don’t include passwords, API keys, private tokens, banking data, or other secrets. Do it in a structured form.