ykdojo

ykdojo / safeclaw

Public

The easiest way to run multiple Claude Code sessions, each in its own container, with a dashboard to manage them all. Quick setup with battle-tested sensible defaults and skills.

agentic-coding agentic-coding-tool ai claude claude-ai
113
11
100% credibility
Found Feb 06, 2026 at 12 stars 9x -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
HTML
AI Summary

SafeClaw provides an easy way for users to run and manage multiple isolated AI coding sessions via a web dashboard and browser-based terminals.

How It Works

1
🔍 Discover SafeClaw

You learn about SafeClaw, a handy way to run several AI coding helpers at once, each in its own safe space so they don't mix up your work.

2
🛠️ Prepare your setup

You run a quick preparation command to get everything ready on your computer.

3
🔗 Connect your accounts

You link your AI service and online accounts like GitHub by pasting special access codes into a secure spot.

4
🚀 Launch a session

You start your first helper, and a web page pops open with a ready-to-use screen where the AI waits for your questions.

5
📊 Open the dashboard

You visit a simple web dashboard to view all your helpers, start new ones, connect your files, or stop ones you don't need.

6
➕ Add more helpers

You create extra sessions for different projects, mounting your folders so each one works on its own task without overlap.

✅ Work with multiple AIs

Now you juggle several independent AI coding partners safely and quickly, managing them all from one easy spot.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 12 to 113 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 safeclaw?

SafeClaw runs multiple Claude Code sessions in isolated Docker containers, each exposing a web terminal for AI-driven coding and a persistent conversation history on your host. A simple dashboard lets you create sessions with volume mounts, initial queries, start/stop them, and view live iframes—all via battle-tested sensible defaults like optimized prompts and no auto-compaction. It's the easiest way to manage parallel Claude code tasks safely, using HTML for the UI and scripts for quick Docker spins.

Why is it gaining traction?

Unlike native Claude Code installs, it containerizes `--dangerously-skip-permissions` runs without host risks, starting sessions in seconds on auto-assigned ports. The dashboard centralizes control with real-time updates, plus easy integrations for Gemini CLI and Slack reads. Devs grab it for easiest github badges to get via AI automation, or tackling easiest way to find ancient city in Minecraft scripts alongside real projects.

Who should use this?

Claude Code powerusers juggling research, prototyping, or game dev hacks like easiest way to get slime minecraft or transport villagers. Backend teams mounting project volumes for isolated API experiments, or indie devs chasing easy github achievements without setup hassle.

Verdict

Solid docs and 76 stars make it usable now, but 1.0% credibility score flags early maturity—expect tweaks for edge cases. Grab it for heavy Claude workflows; otherwise, stick to plain installs.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.