Ronin

somebody just built a repo to run AI agents from your phone imagine developing your product from your phone while sitting in a café right-agent is open sourced, built in Rust, runs on your existing Claude subscription what it does: - turns Telegram into a command center for multiple Claude agents - each agent runs in its own sandbox (can't leak your credentials or access other agents) - agents write their own identity files and remember everything across sessions - schedule tasks with cron, upload files, route to group chats - one install command. that's it set up the agent once from your terminal → then just text it from your phone → it runs Claude Code in a sandbox → writes code, edits files, executes commands → sends the result back in Telegram the security is what impressed me: - credentials stored on host only (agents never see raw tokens) - TLS inspection per sandbox - domain allowlists so agents can only access what you approve it's like having a team of interns that can't steal your passwords i tested it today while i've been outside and it's definitely underrated yet Repo: http://github.com/onsails/right-agent [ BOOKMARK ]

this guy just cracked how to get 10x more out of Codex I tested his method and it completely changes how the agent works for you the mistake everyone makes: using Codex like a chatbot. prompt, wait, clarify, re-prompt, repeat here's how it actually works: 1. write one detailed task doc with every requirement, context, and the final vision 2. fire one command: "accomplish this and test until done" 3. walk away that's it. no babysitting. no "can you clarify" loops. no rate limits it runs GPT-5.5 for hours straight in the background while you do something else think of it like this: ChatGPT = a coworker you have to micromanage every 5 minutes Codex = a contractor you hand a detailed brief and come back to a finished product the key: front-load your thinking into the doc. the better the brief, the longer it runs without interrupting you $200/mo with no daily cap while most AI tools burn your entire allowance in 3 prompts this is probably the most underrated setup in AI right now study this.

big shoutout for this detailed guide for @nateherk

This 2-hours FREE video course is the only one you need to build your own Operation System I got impressed when I saw how this guy automated his entire $3M/year business Bookmark & watch this. Best 2 hours you'll spend this week: https://t.co/0XAdyGCIXi

somebody just built a repo to run AI agents from your phone imagine developing your product from your phone while sitting in a café right-agent is open sourced, built in Rust, runs on your existing Claude subscription what it does: - turns Telegram into a command center for multiple Claude agents - each agent runs in its own sandbox (can't leak your credentials or access other agents) - agents write their own identity files and remember everything across sessions - schedule tasks with cron, upload files, route to group chats - one install command. that's it set up the agent once from your terminal → then just text it from your phone → it runs Claude Code in a sandbox → writes code, edits files, executes commands → sends the result back in Telegram the security is what impressed me: - credentials stored on host only (agents never see raw tokens) - TLS inspection per sandbox - domain allowlists so agents can only access what you approve it's like having a team of interns that can't steal your passwords i tested it today while i've been outside and it's definitely underrated yet Repo: http://github.com/onsails/right-agent [ BOOKMARK ]

this guy just cracked how to get 10x more out of Codex I tested his method and it completely changes how the agent works for you the mistake everyone makes: using Codex like a chatbot. prompt, wait, clarify, re-prompt, repeat here's how it actually works: 1. write one detailed task doc with every requirement, context, and the final vision 2. fire one command: "accomplish this and test until done" 3. walk away that's it. no babysitting. no "can you clarify" loops. no rate limits it runs GPT-5.5 for hours straight in the background while you do something else think of it like this: ChatGPT = a coworker you have to micromanage every 5 minutes Codex = a contractor you hand a detailed brief and come back to a finished product the key: front-load your thinking into the doc. the better the brief, the longer it runs without interrupting you $200/mo with no daily cap while most AI tools burn your entire allowance in 3 prompts this is probably the most underrated setup in AI right now study this.

big shoutout for this detailed guide for @nateherk

This 2-hours FREE video course is the only one you need to build your own Operation System I got impressed when I saw how this guy automated his entire $3M/year business Bookmark & watch this. Best 2 hours you'll spend this week: https://t.co/0XAdyGCIXi