Ask nanobot about your GitHub pull requests from your phone
Connect GitHub's remote MCP server to nanobot with a read-only token, limit its tools, and get a weekday list of pull requests waiting on you.
All apps
nanobot
A lightweight personal AI agent from HKU.
Deploy nanobot
7 days free, then from $5 a month.
nanobot is a small, open-source personal agent with memory, skills, scheduled tasks and chat-app channels. On ranx it runs its gateway and browser WebUI, and you sign in with your ranx.cloud account.
What you get
- Browser WebUI with chat, sessions and settings
- Memory, workspace and chat history kept on your instance's own disk
- Telegram, Discord, Slack, WhatsApp and Feishu as chat channels
- Use your own LLM key
- Sign in with your ranx.cloud account
Per-instance encryption key, on every plan. Its disk and backups are encrypted with a key unique to your instance, and deleting the instance destroys the key.
On Pro and Power
- Daily backups (7 days)A snapshot of the instance's disk every day, the last 7 kept, restorable from the dashboard. Stored in the same Google Cloud region as the instance.
Live
7 days free, then from $5 a month. Your instance runs on Google Cloud in the US with its own subdomain; add your own LLM key in its dashboard.
Deploy nanobotSource codeGuides
All nanobot guidesReal use cases for nanobot, set up end to end.
Check and correct what nanobot remembers about you
Where nanobot keeps long-term memory, how Dream updates it, and the chat commands to inspect, correct, roll back and prune what it saved about you.
Give nanobot its own email address and forward it your mail
Set up a dedicated Gmail mailbox for nanobot, forward it threads and PDFs from your own inbox, and get back the action items and deadlines by reply.
Reminders and a to-do list you text to nanobot on Telegram
Connect nanobot to a private Telegram bot, then use it for one-off reminders, recurring nudges and a to-do file it keeps for you, with a weekly review.
Run nanobot for a few dollars a month: a model budget that holds
Set a hard spending cap, a cheap primary model with a fallback, and a stronger model on demand in nanobot, then check the monthly bill against real token numbers.