Early access open — join the waitlist
Infrastructure for AI agents

The cloud belongs to everyone.

AI agents are deploying real applications. They shouldn't have to fight dashboards they can't click, SSH sessions they can't manage, or sandboxes that charge $83/month for what any VPS provider gives you for $5.

$ edi server create --name my-app --template node-22 --region us-east # server ready in 890ms { "id": "srv_x9k2m4", "status": "running", "url": "https://my-app.edi.cloud", "ip": "198.51.100.42", "ready_in_ms": 890 } $ edi server exec my-app -- python3 app.py { "exit_code": 0, "stdout": "Server running on :8080", "duration_ms": 45 }
< 1sBoot time from template
$5/moPersistent 1 vCPU / 1GB VM
7-16×Cheaper than E2B / Daytona
JSONEvery command, every response
$0Free tier — 1 VM, always-on

The cloud was built for humans.
AI agents are forced to use it anyway.

Today's AI agents — Claude Code, Codex, Gemini CLI — are doing real work: deploying applications, running tests, managing infrastructure. But the tools they're using were never designed for them.

Sandboxes are too expensive

$60-83/month for always-on compute

E2B and Daytona are great for ephemeral coding sessions. They weren't built for persistent workloads — and the pricing proves it. Any VPS provider will sell you that compute for $5.

VPS providers aren't agent-native

Human-readable everything

Hetzner is cheap. DigitalOcean has a decent API. But neither was designed for machine operators. Human-readable output, manual SSH setup, no budget controls, no exec primitive.

The big clouds lock you in

Complexity as a business model

AWS and GCP are powerful. They're also built to make the bill confusing enough that you stop questioning it — and to make you dependent on infrastructure you'll never own.

No one thought about the agent

SSH keys, dashboards, human prompts

Remote execution requires key management. Status requires parsing human-formatted output. Budget enforcement is impossible at the API level. The agent is an afterthought.

Infrastructure that works
the way your agent thinks.

Edi is CLI-first cloud compute built for AI agents and the developers who work alongside them. Every command returns JSON. No dashboard. No SSH key management. No fighting the tool.

$ json

JSON by default

Every command, every response. Structured errors always include a code, message, and resolution. Agents can parse everything without heuristics.

⚡ <1s boot

Pre-baked templates

Servers boot in under a second from ready-to-run templates: Node, Python, Go, Rust, and more. No waiting for package installs mid-agent-loop.

↩ exec

Remote exec as a primitive

Run a command on any server, get structured output back. No SSH. No key management. Just POST /exec and a JSON response.

$ budget

Hard budget limits

Set monthly, daily, and per-server limits in one command. Hard stops — not alerts you'll miss. Hand your agent real infrastructure access and actually sleep at night.

≋ fleet

Fleet management

Provision and manage dozens of isolated environments from a single command. Each agent gets its own VM. Declarative state via edi apply.

⏸ pause

Snapshot, pause, resume

Pause a VM and pay only for disk. Resume and pick up exactly where the agent left off. Stop paying for compute you're not using.

No SSH. No key management. Just run the command.

Remote execution is the single most important feature for agent-native infrastructure. Edi makes it a first-class API call — not an afterthought bolted onto SSH.

Your agent sends a command. Edi runs it inside the VM via vsock, collects the output, and returns structured JSON. Streaming output, working directory, timeout — all configurable. No key rotation, no host verification, no session management.

The entire path: API → gRPC → node agent → vsock → guest agent → process → response. End-to-end in milliseconds.

# From inside Claude Code, Codex, or any agent POST /v1/servers/srv_x9k2m4/exec { "command": "python3 deploy.py", "timeout": 60, "working_dir": "/app" } → 200 OK { "exit_code": 0, "stdout": "Deployed v1.4.2. 3 workers running.", "stderr": "", "duration_ms": 312 }

Give your agent real infrastructure access.
Set a limit. Sleep well.

No other cloud provider offers hard budget enforcement at the API level. Not AWS, not DigitalOcean, not anyone. Edi does — as a core primitive, not a dashboard toggle you'll forget about.

# Set limits once. They hold. $ edi budget set \ --monthly-max 100 \ --daily-max 10 \ --per-server-max 5 \ --alert-webhook https://your-app.com/hooks/spend \ --hard-stop { "monthly_max": 100, "daily_max": 10, "per_server_max": 5, "hard_stop": true, "status": "active" } # When the limit is hit, compute stops. Not an alert. A stop.

Hetzner prices. Agent-native API.
Nobody else has both.

The gap in the market is specific: persistent agent compute at commodity prices. Ephemeral sandboxes are 7-16× more expensive. Traditional VPS providers have no agent-native features.

Feature Edi E2B / Daytona Fly.io DigitalOcean Hetzner
1 vCPU / 1GB always-on $5/mo $60–83/mo ~$83/mo $6/mo ~$4.50/mo
Agent-native API (JSON everywhere) ✓ Yes ✓ Yes Partial No No
Hard budget controls (API-level) ✓ Yes No No Dashboard only No
Exec primitive (no SSH) ✓ Yes SDK only No No No
Always-on persistent VMs ✓ Yes No (max 24h) ✓ Yes ✓ Yes ✓ Yes
Fleet management ✓ Yes No No No No
Snapshot / pause / resume ✓ Yes No Partial Partial No

Flat-rate compute. No surprises.

We charge for compute. That's it. No marketplace tax, no platform fee, no percentage of your success. Paused VMs cost $0.10/GB/month — disk only. Free tier included.

Free forever
s-1vcpu-1gb
$0
1 vCPU
1 GB RAM
20 GB SSD
1 VM always-on
All features included
s-2vcpu-4gb
$16/mo
2 vCPU
4 GB RAM
80 GB SSD
Exec, budget, fleet
JSON everywhere
s-8vcpu-16gb
$64/mo
8 vCPU
16 GB RAM
320 GB SSD
Exec, budget, fleet
JSON everywhere

Paused VMs: $0.10/GB/month (disk storage only). More sizes available at launch.

We're building this differently.

The tech industry stopped building for us. We haven't forgotten what that feels like.

You keep the value you create.

We charge for compute. That's it. No marketplace tax, no platform fee, no percentage of your success. The infrastructure is yours — we just run it reliably and cheaply.

We're honest about what we are.

A small team. Leased Hetzner bare metal. Real margins. We'll tell you what Edi is not the right tool for — right now, that's GPU compute, SOC 2-required enterprise workloads, and stateless serverless. We'll be honest when that changes too.

We believe in the ecosystem, not just ourselves.

Edi is designed to work alongside other tools — Vercel, Cloudflare, your current provider. We're not trying to be everything. We're trying to be the right thing for persistent agent compute. Use us for that. Use others for the rest.

We take the AI transition seriously.

AI is displacing real people. We're not pretending otherwise. A portion of every dollar Edi makes goes toward reskilling resources for people navigating that shift — not as a vague "we give back" gesture, but as a founding principle with a real number attached.

Your agent already knows how to use us.

Edi speaks JSON natively. Every response your agent reads will be structured, predictable, and machine-readable — not scraped from human-readable output.

# Install the CLI $ curl -fsSL https://edi.cloud/install | sh # Authenticate $ edi auth login # Spin up your first server (free tier) $ edi server create --name first --template ubuntu-24 --region us-east { "id": "srv_abc123", "status": "running", "cost": "$0/mo (free tier)" }
Join the waitlist Read the docs →

Free tier includes 1 always-on VM. No credit card required to start.