Authorization notice. Nano Muse is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.
Credentials. A routine that reaches a login or CAPTCHA hands it to you, so do not expect it to type passwords or codes on its own.
Who it is forA person with a recurring check, such as a daily status or a morning briefing, who wants it done without opening the app.
The problemRecurring checks are easy to forget, and a chat assistant only works while someone is talking to it.
The outcomeA goal that is checked on a schedule and a morning feed written for you, both running while the app is closed.
What you need first
- An Android 8.0+ arm64 phone, an iPhone or iPad (TestFlight beta), or a Windows, macOS or Linux x64 computer
- An account: sign in with an e-mail or a mainland-China phone number, or use your own model key
- For self-hosting: a server you control and Docker for the web app; git to fetch the repository
Steps
- Open Nano Muse on your phone or desktop and sign in.
- Describe the goal you want checked and how often, and ask the agent to keep checking it on a schedule.
- Ask for a routine that runs while the app is closed, and for a feed written for you each morning.
- Watch the first run, and answer any login or CAPTCHA the agent hands back to you so the routine can resume.
Prompt for your agent
In the nano-muse/nanoMuse repository, use the signed-in app on <device> to set one scheduled goal and one morning feed. Report the goal and schedule the agent confirms, and verify the first run completes after the app is closed.
Caveat. The README names scheduled goals, routines and the morning feed but does not give the exact setup steps, so confirm the schedule the agent records before you rely on it.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page