Digitize Book a call
AWS-native deployment Your account · Your data

QM for your whole company, running in your AWS account

We deploy and operate QM — Y Combinator's open-source agent harness for startups. Every employee gets an isolated workspace. Teams collaborate in Slack and on the web. Infrastructure stays in your VPC, on your bill.

Plug in your team size and engineer rate in our cost calculator to see first-year DIY vs managed totals — including AWS and your team's time.

48h
Typical go-live
BYOK
Your model API keys
1 org
Dedicated deployment
AWS
RDS · S3 · MicroVMs

DIY QM is a platform project

  • Terraform, ECR, RDS, S3, and Lambda MicroVMs to wire up
  • Slack SSO, sandbox images, secrets, and security posture
  • Ongoing upgrades across a moving open-source codebase
  • Per-employee sandboxes that scale with headcount

We deliver production QM on AWS

  • Full AWS stack provisioned via QM's official Terraform backend
  • Live verification: sign-in, chat, agent-computer proof, Slack reply
  • Operate tier: patches, monitoring, rollback, incident response
  • Handoff docs your team can audit — IAM role, not root keys

Wondering what DIY actually costs in year one? Run the cost calculator — model engineer hours, AWS spend, and the pilot offer for your headcount.

Built for AWS from day one

QM's AWS target uses Terraform, ECR, RDS, S3, and Lambda MicroVMs for per-scope agent sandboxes — the same path YC documents for production deployments.

RDS Postgres

Sessions, memory, queue, and org state — durable and backup-ready in your account.

S3 object store

Sandbox home snapshots, blobs, and artifacts — encrypted, lifecycle-managed.

Lambda MicroVMs

Isolated agent "computers" per person and Slack room — persistent disk, strong isolation.

ECR images

Immutable control-plane and sandbox images pinned by digest — reproducible deploys.

Terraform IaC

Infrastructure as code in a deployment repo you own — plan, apply, and audit every change.

Least-privilege access

Digitize operates via a scoped IAM role with external ID — no shared root credentials.

What's included

Operate · monthly

Ongoing operations

  • Health monitoring and alerting
  • Scheduled QM version upgrades (patch windows)
  • Sandbox image rebuilds and ECR digest pinning
  • Incident triage and rollback execution
  • Budget cap review (org + per-user LLM limits)
  • 4-hour response SLA (business hours)
  • Monthly status summary

Five-day delivery

Day 0

Kickoff

IAM role, deployment repo, auth and model choices

Day 1–2

AWS infrastructure

Terraform apply, ECR images, secrets push

Day 3

Deploy & prove

Live checks, admin chat, agent-computer verification

Day 4

Slack & connectors

Bot in workspace, OAuth connectors as scoped

Day 5

Handoff

Team onboarding doc, operate schedule, escalation path

Pricing

Transparent service fees. AWS and model API costs bill directly to your accounts. Estimate your year-one savings with the DIY vs managed cost calculator.

Launch

One-time deployment

$4,500

Typical 5 business days

  • Full AWS QM stack
  • Auth + admin setup
  • Live verification
  • Handoff documentation
Get started

Operate

Managed ongoing ops · requires Launch

$850/mo

Flat rate — monitoring, upgrades, and incident response

  • Health monitoring & alerting
  • Scheduled QM upgrades
  • Incident triage & rollback
  • 4hr business-hours SLA
Book a call

Pilot offer: first 3 customers — Launch at $3,000 including 60 days Operate. Estimated AWS infra: $370–870/mo for ~20 seats (varies by usage). LLM spend is separate (BYOK). Adjust team size, engineer rate, and AWS assumptions in the cost calculator. Larger teams or compliance requirements? Contact us for a custom quote.

FAQ

Do you host QM on your infrastructure?

No. We deploy into your AWS account. You retain data ownership, network control, and CloudTrail visibility. We operate via a scoped IAM role — not multi-tenant SaaS.

Which AWS regions are supported?

Any region where QM's AWS backend is available, including Lambda MicroVM support. We preflight with aws lambda-microvms list-microvm-images. Default recommendation: us-west-2 or us-east-1 unless you have compliance requirements.

Who pays for LLM API usage?

You do, via your own Anthropic, OpenAI, or OpenRouter keys (bring your own key). We configure QM budget caps and help you set sane org-wide limits. We do not markup model tokens.

Is Digitize affiliated with Y Combinator?

No. QM is an MIT-licensed open-source project from Y Combinator. Digitize is an independent consulting company that deploys and operates QM on AWS for customers.

What if we don't use AWS?

QM also supports Fly.io. This page focuses on our AWS offering for teams with existing AWS footprints or compliance needs. Contact us to discuss Fly.io or a hybrid approach.

Ready to deploy QM on AWS?

Book a free 30-minute discovery call. We'll qualify fit, estimate AWS costs, and outline a go-live date.