I put my Claude Code sessions on Discord — and now it's a one-line plugin

Charlie Archer Simmons — Wed, 17 Jun 2026 12:52:05 +0000

About 7,000 developers install a little tool of mine every month. It has 7 GitHub stars. I think about that gap a lot — but it also means thousands of these cards are quietly running in Discord right now, which is the whole point.

It's called claude-rpc, and as of today you can install it from inside Claude Code itself.

What it is

claude-rpc is a small Node daemon that takes the lifecycle events Claude Code already fires — session start, each tool call, token counts — and turns them into a live Discord Rich Presence card on your profile: current model, project, what tool is running, plus lifetime stats. Your friends see what you're building; you get a year heatmap of your own work.

It's free, open source, and has zero runtime dependencies — the Discord IPC client is hand-rolled, so the entire supply chain fits in a single review.

The new part: a Claude Code plugin

Two lines, in the editor:

/plugin marketplace add rar-file/claude-rpc
/plugin install claude-rpc@claude-rpc

The card shows up on your next session. That's it.

The plugin itself is deliberately thin — one SessionStart hook that runs the same installer you'd run by hand (npx claude-rpc@latest setup) once, in the background, then gets out of the way. Claude Code measures it at ~0 tokens of context per session. The real package still does the real work: wiring hooks, holding Discord's local socket, starting at login.

It's now the fifth way to install the same tool — npx, a curl one-liner, Homebrew, a Windows exe, and now this — so pick whatever fits your setup.

How it actually works

No magic: 5 hooks, one small state file, and a daemon that holds Discord's local socket. No polling, no network calls, no telemetry you didn't opt into. If you want to read it, start with src/discord-ipc.js.

Try it

Site + build log: https://claude-rpc.vercel.app
Source: https://github.com/rar-file/claude-rpc

Built solo, on weekends. If one of those 7,000 cards ends up being yours, a GitHub star is the cheapest possible way to tell me it's working.

I built a free self-hosted AI chat app with web search and browser agent automation

Charlie Archer Simmons — Tue, 17 Mar 2026 23:58:34 +0000

## What I built
1 paragraph — what SURF is, what problem it solves.

Why I built it

ChatGPT costs money. Runs in the cloud. Your data leaves your machine.
I wanted something free, local, and private.

What it can do

bullet list of features (keep it brief)
include a screenshot / gif here ← critical

Tech stack

Python · Flask · Playwright · DuckDuckGo (no key needed)

The hard parts

Pick 1-2 interesting technical challenges you solved.
e.g. "Getting Playwright to stream browser screenshots in real time was tricky because..."
This is what gets upvotes — people love implementation details.

Try it yourself

Link to GitHub + one-line install command

What's next

1-2 future features you're thinking about.
Ask readers: "What would you add?"

rar-file / surf

Self-hosted AI chat — web UI + terminal CLI. Connect any model (Ollama, OpenAI, Anthropic), free web search, browser agent automation, persistent memory, and analytics.

A self-hosted AI chat with a sleek web UI and a rich terminal CLI.
Connect any model. Search the web for free. Automate your browser. Remember everything.

SURF — Search · Understand · Reason · Fast

A self-hosted AI chat with a polished web UI and a rich CLI. Connect to any model — local or cloud — with free built-in web search, persistent memory, a browser automation agent, and a full analytics dashboard.

Preview

Web UI

Terminal CLI

Features

🦙 Any AI Provider Ollama (local), Anthropic Claude, OpenAI GPT, OpenRouter, or any OpenAI-compatible endpoint. Switch mid-conversation with `/provider`.	🔍 Free Web Search DuckDuckGo search with no API key and no quota. Multi-source synthesis powered by Playwright. Works in both web UI and CLI.
🤖 Browser Agent Vision-powered autonomous browsing. Give a task in plain English — SURF opens a real browser, takes screenshots, and executes: click, type, scroll…

View on GitHub

DEV Community: Charlie Archer Simmons