Most people think of AI assistants as something you use at your desk. Open a tab, type a prompt, get a response, close it. Maybe you use Claude Code in a terminal. Either way, it is a sit-down-at-your-computer experience.
I changed that a few weeks ago. Now I message my AI agent the same way I message a friend — from my phone, while I am walking the dog, from bed, wherever. It responds in seconds with full context about what we have been working on.
Here is the setup and why it matters more than you might think.
The Unlock: Claude Code Channels
When Anthropic shipped Claude Code Channels, they quietly enabled something powerful: you can connect Claude Code to Discord. Your Claude Code instance becomes a Discord bot that listens and responds to messages.
On its own, this is cool but limited. A Claude Code session still forgets everything between restarts. So you have a Discord bot with amnesia — it can respond, but it does not know who you are or what you were working on yesterday.
The real unlock comes when you combine Channels with persistent memory.
What It Actually Looks Like
Here is a real interaction from this week. I was testing my product in a VM and found a bug in the setup process. I messaged my agent from Discord:
Me: I just ran into the first issue. I'm running Claude Code
in the Claude Desktop app, not the terminal. The setup agent
checked for Claude Code with brew and didn't find it, but then
moved on assuming it must be installed since the session is
running. Well... it's running in Claude Desktop, not Claude Code.
Agent: Good find. The issue is in section 1.4 of the product
file. The current logic assumes that if someone is reading the
setup instructions, they must be running Claude Code — but
Claude Desktop can also read and execute the file. The fix
needs to not assume the runtime is Claude Code, actually
install it via brew if missing, and recognize Claude Desktop
as a valid way to run the setup.
It immediately knew which product file I was talking about, found the exact section with the bug, explained why the logic was wrong, fixed it, pushed the code to GitHub, and updated the live product — all from one Discord message. I did not re-explain the project, the file structure, or the deployment pipeline. It already knew.
From my phone. While testing in a VM.
The Architecture in 60 Seconds
Three pieces make this work:
1. A tmux session on a Mac
Claude Code runs in a tmux session with caffeinate to prevent sleep. This keeps it alive 24/7.
2. The Discord plugin
Claude Code Channels connects it to a Discord bot. I message the bot, Claude Code receives the message, processes it, and replies.
3. A persistent brain
A folder of markdown files that the agent reads at startup and writes to during conversations. This is where memory lives — learnings, corrections, project context, preferences, conversation logs.
The brain is the difference between a chatbot and an agent. Without it, you just have a Discord bot that happens to be powered by Claude. With it, you have something that accumulates knowledge and gets better over time.
Why Discord?
I get this question a lot. Why not Slack? Why not a custom web app?
A few reasons:
It is already on your phone. Discord has a solid mobile app. No building a frontend, no deploying a web app, no PWA shenanigans. Install Discord, join your server, start messaging.
It is free. Discord bots are free to create and run. No API costs on the Discord side.
It supports rich interactions. File attachments, reactions, threads, embeds. Your agent can send you code snippets, images, or long-form responses and it all renders properly.
It separates your agent from your workspace. When your agent lives in Discord, you can reach it from any device. Your phone, a friend's computer, an iPad. You are not tied to the machine it runs on.
The Compounding Effect
The part that surprised me most is how the persistent memory changes the relationship with the tool.
After a week, my agent knew my coding style preferences, understood multiple project contexts, and started to build a context of corrections.
This is not theoretical. There is a file in the agent's brain called Corrections.md where it documents every time it was wrong, what it should have done instead, and how to prevent it. It reads this file at startup. It literally learns from its mistakes.
The Cost
The agent runs on your existing Claude Pro or Max subscription. There is no additional API cost. Discord is free. The Mac needs to stay on, but a Mac Mini draws about 10 watts idle — less than a light bulb.
The only real cost is the Claude subscription you are already paying for.
Try It Yourself
If you want to set this up, you have two paths:
Build it yourself. I wrote a detailed architecture post about the brain framework — search for "Building Persistent Memory for Claude Code Agents" on Dev.to. It gives you the full structure and design reasoning.
Use AgentWake. I packaged the entire setup into a single file that Claude Code reads and executes. It automates most of the process and walks you through the rest. $24.99 one-time at agentwake.com.
Either way, if you are using Claude Code and have not tried Channels yet, you are missing out. Having your AI accessible from your phone changes how you think about what it can do for you.
I am building AgentWake — tools for persistent AI agents. Follow me for more posts about what you can actually do with Claude Code when you push it beyond the defaults.
Top comments (0)