VM Access: SSH Into Your AI Development Environment

Your AI development team runs 24/7 on a dedicated cloud VM — and now you can log in and work alongside them.

Synthcore's VM direct access gives you SSH access to the same environment where your 13 specialized AI agents code, test, and ship. It's the difference between delegating and pair-programming.

Your AI Development Environment, Under Your Control

When you deploy a Synthcore project, we provision a dedicated AWS EC2 instance running Ubuntu 24.04. Your AI agents work on that VM continuously — building features, writing tests, filing bugs, and pushing commits to your GitHub repo.

VM access means you can SSH into that same VM and operate in the same environment as your agents. You're not using a separate development machine — you're collaborating with your AI team on shared infrastructure.

What Makes This Different

Unlike traditional AI coding assistants where you're either driving or delegating, Synthcore lets you switch between both modes instantly:

• Autonomous mode — Let your 14 agents work while you focus elsewhere
• Pair-programming mode — SSH in and drive with Claude Code CLI
• Debug mode — Jump in when an agent hits a tricky problem

No context loss. No handoff friction. Just seamless collaboration.

Getting Started in 3 Steps

1. Connect via SSH

Get your VM credentials from the Synthcore dashboard under Project Settings → VM Access. You'll find:

• Your VM hostname (e.g., proj-abc123.vm.synthcore.dev)
• Your connection username (ubuntu)
• Instructions to add your public SSH key

ssh -i ~/.ssh/your_private_key ubuntu@proj-abc123.vm.synthcore.dev

2. Verify Your Environment

Once connected, confirm you're in the right place:

whoami          # returns: ubuntu
cd ~/project    # your GitHub repo
claude --version   # confirms Claude Code is available

3. Start Building

You're now in your AI development environment with full access to:

• Your project repository
• Claude Code CLI for interactive sessions
• Packaged skills — code review, service management, web search, and more
• Real-time view of what your agents are working on

What You Can Do with VM Access

Run Claude Code Directly

When you want to drive the keyboard yourself, invoke Claude Code:

claude
# Now you're pair-programming with your AI team
claude "add user authentication to the dashboard"

Your session runs alongside the autonomous agents — no conflicts, no overwriting.

Use the Same Skills Your Agents Use

Synthcore packages developer tools as skills — the same ones your agents use daily:

| Skill | What It Does | |-------|--------------| | code-review | Security scanning, diff analysis, style checks | | dev-services | Start, stop, restart dev servers | | github-workflow | Branch, commit, PR operations | | web-search | Research documentation and errors | | lobster-workflows | Deterministic multi-step pipelines |

Debug in Real Time

When an agent encounters a tricky bug, you can:

1. Log in and inspect the current state
2. Run the same tests the agent ran
3. Make corrections directly
4. Hand it back to the agents

No waiting for the next cycle. You're in the loop.

Security and Isolation

Each customer gets a dedicated VM:

• Isolated infrastructure — your VM is for your project only
• Key-based SSH — password authentication disabled, no exposure
• Firewall-locked — only your IP can connect (AWS Security Groups)
• API keys isolated — your model keys stay on your VM
• Full audit log — every agent action is tracked

See Also

• How Synthcore's multi-agent architecture works — understand how 14 agents collaborate
• What agents built this week — real examples of agent output
• Getting started guide — full setup documentation

Start Building

VM access is available on all Synthcore plans. Connect your SSH key in the dashboard and start pair-programming with your AI team today.

Deploy your first project and get VM access in under 10 minutes.