# AI use cases for Noraz Agent (mogons/noraz-agent) Repo: [mogons/noraz-agent](https://github.com/mogons/noraz-agent) | Use cases: 4 | Page: https://dedupedai.com/use-cases/mogons-noraz-agent/ Noraz AI is an open-source, Node.js and TypeScript trading agent system for Robinhood Chain that screens markets, scores signals with a swarm consensus, and posts call cards to Discord and Telegram. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Get screened Robinhood Chain signal cards on chat: https://dedupedai.com/use-cases/mogons-noraz-agent/receive-screened-robinhood-chain-signal-cards/ - Audit a Robinhood Chain token before buying: https://dedupedai.com/use-cases/mogons-noraz-agent/audit-a-token-before-buying-it/ - Run the agent 24/7 on a VPS with health checks: https://dedupedai.com/use-cases/mogons-noraz-agent/keep-the-agent-running-24-7-on-a-vps/ - Write screening rules in plain English: https://dedupedai.com/use-cases/mogons-noraz-agent/tune-screening-rules-with-a-plain-english-prompt/ ## How to get screened Robinhood Chain signal cards on chat with Noraz Agent Repo: [mogons/noraz-agent](https://github.com/mogons/noraz-agent) | Difficulty: Intermediate | Time: 90 minutes | Basis: From the README Run five screening agents that post only 80%+ confidence call cards to Discord and Telegram. **Who it is for:** A crypto trader on Robinhood Chain who wants filtered trade ideas delivered to chat instead of scanning many markets by hand. **The problem:** Scanning meme tokens, LP pools, NFT floors, Robinhood Chain alpha, and whale flow manually takes hours and mixes weak signals with strong ones. **The outcome:** A running bot that posts call cards only when the swarm consensus reaches the 80% confidence floor, with DRY_RUN keeping execution off by default. ### Steps 1. Run `git clone https://github.com/runesatsdev/noraz-agent.git` and then `cd noraz-agent` (the README clone URL differs from the repository URL given, so confirm the source first). 2. Run `bash setup.sh` on Linux or macOS, or `.\setup.bat` on Windows. 3. Run `npm run wizard` (or `noraz onboard`) and set your API keys, AI models, and TP/SL values. 4. Run `npm run dev` (or `noraz run`) to start the live bot. 5. Open the `#call-meme-robinhood` or other `#call-*` Discord channel and check that call cards appear with audit data. ### Prompt to paste into your agent ```text Using the noraz-agent repo, set up the bot with DRY_RUN enabled and start it in development mode. Expected output: the bot runs and posts at least one call card or a status message to the configured Discord or Telegram channel. Verify that DRY_RUN is still true in the .env file before reporting success. ``` ### Caveat The README says execution stays under your control through DRY_RUN and manual confirmation, so a call card is a research output and not an automatic trade. Risk, credentials: The wizard asks for API keys and chat credentials, so store the .env file securely and never post it in a channel. 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/mogons-noraz-agent/receive-screened-robinhood-chain-signal-cards/ ## How to audit a Robinhood Chain token before buying with Noraz Agent Repo: [mogons/noraz-agent](https://github.com/mogons/noraz-agent) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README Run a token audit from the terminal or Discord to check security before any trade decision. **Who it is for:** A trader who has found a token on Robinhood Chain and wants a security check before deciding whether to buy. **The problem:** Checking a token's security across several sources by hand is slow, and a single missed red flag can cost real money. **The outcome:** A live token audit from the Terminal TUI or the #audit-on-demand channel that shows the security results before any trade decision. ### Steps 1. Run `npm install` and `npm run build` from inside the Noraz Agent folder. 2. Run `noraz terminal` (or `npm run terminal`) to open the standalone Terminal TUI. 3. Choose the live token audit option and enter the token contract address you want to check. 4. If you prefer Discord, post the token address in the `#audit-on-demand` channel and wait for the audit reply. (inferred, check the README) 5. Review the GMGN and GoPlus security results before deciding whether to act. ### Prompt to paste into your agent ```text Using the noraz-agent repo, run a live token audit on through the Terminal TUI or the #audit-on-demand channel. Expected output: an audit summary that includes the GMGN and GoPlus security results. Verify that the audit result is shown before any buy or swap action is taken. ``` ### Caveat An audit is only one input; the README describes the tool as experimental research with no guarantee of results and says to do your own research. Risk, credentials: The terminal and Discord audit flow connects to your configured setup, so keep any wallet or API keys out of shared logs and screenshots. 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/mogons-noraz-agent/audit-a-token-before-buying-it/ ## How to run the agent 24/7 on a VPS with health checks with Noraz Agent Repo: [mogons/noraz-agent](https://github.com/mogons/noraz-agent) | Difficulty: Advanced | Time: 90 minutes | Basis: From the README Deploy the PM2 daemon, check diagnostics, and update the agent on a Linux server. **Who it is for:** A developer or operator who wants the bot to keep screening markets around the clock on a Linux VPS. **The problem:** A bot that stops when a terminal closes misses signals, and manual updates and restarts are easy to forget. **The outcome:** A PM2-managed daemon that stays up, a diagnostic report from doctor, and a self-update path with deployment notifications. ### Steps 1. Complete the Linux or VPS setup with `bash setup.sh`, then run `noraz onboard` to create the .env file. 2. Run `noraz deploy` (or `npm run deploy`) to start the PM2 24/7 daemon. 3. Run `noraz doctor` to check the full set of diagnostics. 4. Run `npx pm2 status` and `npx pm2 logs noraz-agent` to confirm the daemon is up and reading logs. 5. Run `noraz update` to pull the latest code, install, build, and restart PM2 with deployment notifications. ### Prompt to paste into your agent ```text Using the noraz-agent repo on a Linux VPS, run `noraz deploy` and then `noraz doctor`. Expected output: PM2 shows noraz-agent as online and the doctor report lists no failed checks. Verify the result with `npx pm2 status` before reporting success. ``` ### Caveat The README describes the self-updater as pulling from git and restarting PM2, so review changes before updating a server that holds live API keys. 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/mogons-noraz-agent/keep-the-agent-running-24-7-on-a-vps/ ## How to write screening rules in plain English with Noraz Agent Repo: [mogons/noraz-agent](https://github.com/mogons/noraz-agent) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README Describe the signals you want in one sentence and let the agent compile them into a strategy. **Who it is for:** A trader who wants screening that matches a specific pattern, such as CTO tokens with several smart wallets, without editing numeric gates by hand. **The problem:** Setting every hard gate by hand is slow and hard to reason about when the trading idea is described in words. **The outcome:** A validated strategy file compiled from your prompt, with a safe default if compilation fails, and the ability to re-apply it from chat. ### Steps 1. Run `noraz onboard` (or `npm run wizard`) and go to STEP 5.5 to choose the screening strictness. 2. Select the Custom Prompt option and write your rule in plain English, for example: only CTO tokens with 2+ smart wallets, min $10k liq. 3. Run `noraz run` (or `npm run dev`) so the prompt compiles into a validated strategy on first boot. 4. Check the logs or the control room for a confirmation that the strategy compiled, or that the safe default was used. 5. In `#noraz-control-room`, send the message "re-apply my strategy prompt" after you edit the prompt. ### Prompt to paste into your agent ```text Using the noraz-agent repo, set a Custom Prompt strategy describing and start the bot with `noraz run`. Expected output: a compiled strategy file or a logged fallback to the safe default. Verify that the 80% confidence gate and security gates are still listed as mandatory before reporting the setup as complete. ``` ### Caveat The README says the 80% confidence gate and security gates stay mandatory and fail-closed for every preset, so a custom prompt cannot remove them. 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/mogons-noraz-agent/tune-screening-rules-with-a-plain-english-prompt/