Servers
Rent, harden, and scale servers as customers arrive.
Give each customer an agent in its own isolated sandbox. Persistent files, browser access, and connections to Gmail, Slack, and other apps.
$1 free credit
Just want an agent for yourself? Create your free personal agent
Read the docs first: https://www.agent37.com/docs/llms-full.txt Build me a real estate assistant using Hermes.
Read the docs first: https://www.agent37.com/docs/llms-full.txt Build me a real estate assistant using Hermes.
Read the docs first: https://www.agent37.com/docs/llms-full.txt Build me a social media agent using OpenClaw.
Read the docs first: https://www.agent37.com/docs/llms-full.txt Build me a code-review agent using the Claude Agent SDK.
Read the docs first: https://www.agent37.com/docs/llms-full.txt Build me a coding assistant using OpenCode with DeepSeek Flash as the default model.
Read the docs first: https://www.agent37.com/docs/llms-full.txt Build me a real estate assistant using Hermes.
Powering agents for over 100 companies
Pricing
Find a cheaper sandbox? We’ll refund the difference.
4 GB persistent disk
Compute $0.37Disk $0.36
Unit rates
vCPU
$0.0011
per vCPU · hour
Memory
$0.00096
per GB · hour
Disk
$0.00012
per GB · hour
Compute is billed while your sandbox runs. Disk is billed while retained, awake or asleep.
curl https://api.agent37.com/v1/instances \
-H "Authorization: Bearer sk_live_..." \
-H "Content-Type: application/json" \
-d '{"template":"agent37-hermes"}'{
"id": "ab12cd34ef",
"status": "running"
}Here's what you'd have to build.
Rent, harden, and scale servers as customers arrive.
Keep every customer's agent, files, and credentials separate.
A web address per agent, authenticated requests, and routing that keeps your servers private.
Connect your app to each harness. Handle messages, sessions, and streaming responses.
Create, stop, restart, resize, update, delete. Every edge case is yours.
Put idle agents to sleep and wake them when a request arrives, with their files intact.
Back up customer files, test restores, and recover agents when a server fails.
Track compute, storage, and service usage. Set budgets and enforce spending limits.
Dashboards, alerts, on-call. Someone carries the pager. That someone is you.
Architecture
One call provisions a sandbox per customer. Message it across as many sessions as you like. Its files, memory, and connected tools stay put until you delete it.
Plus your own Docker image.
Managed models, or bring your own key.
1,000+ app connections via Composio.
Preinstall your own skills, prompts, and tools with a custom template.
Stream text and tool activity as your agent works.
Give an agent a cron schedule; it runs unattended and you read the results.
Security
We do not collect your prompts, files, or terminal sessions, and your data is never used to train AI models. SOC 2 Type I and readiness reports on request.
Every sandbox is enforced by gVisor, with its own filesystem and a hard disk quota. Tenants can never see each other.
gVisor, built at GoogleHosts have no public hostname. Every request enters through Cloudflare's edge over TLS and needs your API key, unless you've explicitly made a port public.
Cloudflare global edgeEgress is firewalled per sandbox: the public internet and nothing else. Not the host, not private networks.
Deny by defaultYour sandbox's disk, backups, and metadata are encrypted at rest, and every connection is encrypted in transit.
At rest and in transitCustomer stories
Agent products, customer workflows, and businesses built on Agent 37.
Cofounder @ Boon
“We had tried for nearly 6 months to do this on our own, that took only a few days of setup and effort working with Agent37.”
Boon gives nonprofits their own Hermes agents for grant fundraising.
Read the case studyFounder @ ETEC+
“Ideally I just want to sell, and not do any backend.”
ETEC+ moved from creating agents by hand to selling a branded product with signup and billing.
Read the case studyYou top up a prepaid balance and each sandbox spends it down per minute while it runs. No subscription, no plan fee, no minimum, and new accounts get a $1 starter credit once a card is on file, and nothing is charged until you top up. If the balance runs out, your sandboxes go to sleep until you top up again.
Neither. There is no subscription and nothing is added on top of it. You are charged per minute of uptime at your sandbox's own rate: a 2 vCPU 4 GB sandbox left running every minute of a month is $4.76, and the meter drops to its disk alone the minute it stops or sleeps. Delete it and you pay nothing. Model tokens, search, and integrations meter separately from the same balance, unless you bring your own keys.
Its disk alone, $0.36 a month for 4 GB. Compute stops the minute a sandbox stops or goes to sleep, and once you delete it you pay nothing.
Yes, and that spend never touches your balance. Use our gateway instead and models, search, and integrations meter from the same balance, with a spend cap you set per sandbox.
As long as you keep it. Nothing times out mid-task, and what your agent writes to disk is still there on the next call, weeks later.
Your harness, your workflows, your brand. Hosting, connections, models, and tools ready to build on.
$1 free credit