PJUllrich

A Claude-based Devcontainer for Elixir development

14
1
100% credibility
Found Feb 26, 2026 at 13 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Shell
AI Summary

A ready-to-use development environment for Elixir and Phoenix web apps that safely runs AI coding assistants by limiting internet access to trusted sites and hiding sensitive files.

How It Works

1
🕵️‍♀️ Discover safe AI coding helper

You hear about a special workspace that lets you use smart AI helpers for building web apps without worrying about privacy risks.

2
📁 Add to your project

You copy a simple folder into your app's main directory to get everything ready.

3
✏️ Set your safety preferences

You list the websites your tools can visit and note which private files to keep hidden away.

4
🚀 Launch your secure space

With one easy command, your protected coding playground opens up, feeling safe and cozy.

5
Pick your AI companion
🧠
Smart text AI

Chat with an AI that suggests code and thinks step-by-step for your app.

👀
Visual AI viewer

Run a background tool that watches your code and offers live insights on your screen.

6
⚙️ Build and test your app

Start your web app, run checks, and code away with AI assistance feeling smooth and secure.

🎉 Code securely with AI magic

Your app comes alive faster, all your secrets stay safe, and development feels fun and protected.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 13 to 14 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is devcontainer?

This is a Claude-based devcontainer for Elixir and Phoenix development, bundling Claude Code and optional Tidewave in a secure Docker environment. It solves the risks of running Claude with --dangerously-skip-permissions by enforcing a domain allowlist for outbound traffic, hiding sensitive files like .env via bind mounts, and isolating Claude state per project. Using the devcontainer CLI, you copy it into your repo, tweak allowed domains and protected paths, then spin it up with make dc.up for a ready-to-code workspace connecting to your host Postgres.

Why is it gaining traction?

It stands out with a transparent Squid proxy that intercepts all HTTP/HTTPS traffic for strict filtering—no relying on env vars—plus auto-generated Claude deny rules and easy Makefile commands like dc.claude, dc.server, and dc.tidewave.bg. Devs notice the seamless VSCode/GitHub Codespaces integration, customizable remoteEnv for host secrets, and verification tests ensuring the firewall blocks unauthorized domains on startup. For AI-assisted coding, it reduces leak risks without full sandbox overhead.

Who should use this?

Elixir devs building Phoenix apps who rely on Claude Code for code generation and want safer unsafe mode. Phoenix teams using dev containers in VSCode or GitHub Codespaces, especially those exposing Tidewave on localhost:9833 or mounting host Docker services like Postgres. Avoid if you need Git inside the container or general sudo.

Verdict

Solid niche setup for Claude-powered Elixir devcontainers with thoughtful security, but at 10 stars and 1.0% credibility, it's early-stage—test thoroughly before production workflows. Great docs and Makefile make it worth forking if it fits.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.