# AI use cases for Hermes Agent (NousResearch/hermes-agent) Repo: [NousResearch/hermes-agent](https://github.com/NousResearch/hermes-agent) | Use cases: 3 | Page: https://dedupedai.com/use-cases/nousresearch-hermes-agent/ Hermes Agent is a self-improving AI agent from Nous Research. It creates skills from experience, improves them while using them, keeps agent-curated memory, searches its own past conversations, and can run on a small VPS, a GPU box or serverless infrastructure. You talk to it from a full terminal UI or from Telegram, Discord, Slack, WhatsApp and Signal through one gateway, and it can run scheduled jobs in plain language. It works with Nous Portal, OpenRouter, OpenAI or your own endpoint. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Install Hermes Agent and switch models without code: https://dedupedai.com/use-cases/nousresearch-hermes-agent/install-hermes-agent-and-pick-a-model/ - Talk to Hermes from Telegram while it works on a server: https://dedupedai.com/use-cases/nousresearch-hermes-agent/talk-to-hermes-from-telegram-while-it-works-on-a-vps/ - Schedule a daily report or nightly job in plain language: https://dedupedai.com/use-cases/nousresearch-hermes-agent/schedule-a-daily-report-in-plain-language/ ## How to install Hermes Agent and switch models without code with Hermes Agent Repo: [NousResearch/hermes-agent](https://github.com/NousResearch/hermes-agent) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Run the installer, start the terminal chat, and change provider or model with one command. **Who it is for:** A developer who wants a capable terminal agent without being locked to one model vendor. **The problem:** Most agent CLIs tie you to one provider, and switching means new tools and new config. **The outcome:** Hermes running in your terminal with the provider and model you chose, and a setup you can change any time. ### Steps 1. Install on macOS, Linux or WSL2 with `curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash` 2. Reload your shell, then start chatting with `hermes` 3. Choose your LLM provider and model with `hermes model` 4. Turn tools on or off with `hermes tools`, or run the whole wizard with `hermes setup` 5. If something breaks, run `hermes doctor` ### Prompt to paste into your agent ```text Install NousResearch/hermes-agent with the official installer, set the model to with hermes model, run hermes doctor, and summarise which tools are enabled by default. ``` ### Caveat Risk, remote script: The installer is a script fetched from the internet; read it first if you are cautious. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/nousresearch-hermes-agent/install-hermes-agent-and-pick-a-model/ ## How to talk to Hermes from Telegram while it works on a server with Hermes Agent Repo: [NousResearch/hermes-agent](https://github.com/NousResearch/hermes-agent) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Start the messaging gateway on a cheap VPS so the agent keeps working and you steer it from your phone. **Who it is for:** Someone who wants an agent that keeps running when the laptop is closed. **The problem:** A local agent stops the moment you close the lid, and you cannot check on it away from the desk. **The outcome:** Hermes on a server, reachable from Telegram, Discord, Slack, WhatsApp or Signal, with conversations continuing across platforms. ### Steps 1. Install Hermes on a VPS or cloud VM 2. Run `hermes setup` and add the bot token for your messaging app 3. Start the gateway with `hermes gateway` 4. Message the bot; voice memos are transcribed and the conversation continues across platforms ### Prompt to paste into your agent ```text Set up NousResearch/hermes-agent on my server, configure the Telegram gateway with my bot token from an environment variable, start hermes gateway, and tell me how to restrict who can message the bot. ``` ### Caveat Risk, credentials: The bot token and model key live on the server; anyone who can message an unrestricted bot can use your agent and your tokens. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/nousresearch-hermes-agent/talk-to-hermes-from-telegram-while-it-works-on-a-vps/ ## How to schedule a daily report or nightly job in plain language with Hermes Agent Repo: [NousResearch/hermes-agent](https://github.com/NousResearch/hermes-agent) | Difficulty: Intermediate | Time: 20 minutes | Basis: From the README Use the built-in cron scheduler to have Hermes run tasks unattended and deliver the result to any connected platform. **Who it is for:** Someone who wants a daily summary, a nightly backup check or a weekly audit without writing cron jobs. **The problem:** Recurring chores need scripts, crontabs and a place to send the output. **The outcome:** A scheduled task that runs on its own and posts its result to your chat app. ### Steps 1. Connect at least one messaging platform with `hermes gateway` 2. Describe the job in chat, for example a daily report every morning 3. Let Hermes create the schedule with its built-in cron scheduler 4. Check the first few runs and adjust the wording if the output is off ### Prompt to paste into your agent ```text Using NousResearch/hermes-agent's built-in scheduler, create a job that every weekday at