Build a Devin-style SWE agent

What you’re building: an autonomous software engineer: a long-running agent takes a task, works in its own machine for minutes or hours, and reports back with code and a result.

Primitives you’ll use: Organization, Sandboxes, Agents, Deployments, Custom domains

What you’re building

A Devin-style product is about autonomous, long-running work. The user hands over a task, the agent works in its own machine for a long time, and the product reports progress and a finished result. The hard parts are isolation, observability, and cost.

MIOSA runs the agent against a dedicated sandbox, streams its events (tool calls, stdout, file writes) so the UI shows progress, and stores the runs so you can pause, steer, or cancel. Snapshots let you keep a known-good state, and the machine is disposable when the task ends.

Keep the run in a durable sandbox with a generous --ttl, and stream events rather than polling stdout.

What you need on MIOSA

Architecture

Step 1: Create an account and an API key

Install the CLI, sign in, and mint a key for your product. The secret is printed once; store it as an environment variable, never in code.

npm i -g @miosa/cli
miosa login
miosa whoami
miosa api-key create swe-agent-key --preset agent     # prints the secret once
export MIOSA_API_KEY="msk_u_..."

Both SDKs read MIOSA_API_KEY from the environment, so a server or a worker needs nothing else. See API keys for scopes and how to create keys in the console.

Step 2: Create the resources

Step 3: Wire the agent loop

Cancel a run that is going the wrong way with client.agentRuns.cancel(run.id) and use the events to show an honest progress view.

Step 4: Preview

A Preview is a throwaway public URL for a port inside the machine. Start the app as a background process so it survives the CLI disconnecting, then expose its port.

Open the exact Preview URL MIOSA returns.

Step 5: Deploy

Publish the machine to an immutable Deployment. Give it the source machine, the path the app lives at inside it, and the command that serves it.

Publishing the same deployment name again creates a new immutable version and keeps the same URL. Roll back with miosa deploy rollback swe-agent --to <version-id>, and inspect a live app with miosa deploy logs swe-agent -n 100. See Publishing and Rollback.

Step 6: Custom domain

Attach a domain your customer owns to the deployment. The platform URL keeps working while DNS propagates.

miosa deploy domain-add swe-agent app.example.com
miosa deploy domains swe-agent          # shows the DNS record and verification target
miosa deploy domain-verify swe-agent <domain-id>

Copy the exact DNS record MIOSA shows into the customer’s DNS provider; for a subdomain it is normally a CNAME. Once verified and TLS is active, MIOSA routes the domain to the deployment’s active version. In code, read the URL from the publish response instead of building it: the SDK method is miosa.deployments.domains.add(deploymentId, { domain }) (TypeScript) or miosa.deployments.domains(deployment_id).add(domain=...) (Python). See Domains.

Costs and limits

Everything bills while it runs: machines (sandboxes and computers) by the second, managed databases while running, and deployments when they serve. Pausing a machine stops compute billing but keeps disk. Set an --idle-timeout or a --ttl so a forgotten machine cannot run forever, and cap spend with rate limits and per-workspace quotas.

• Pricing - plans, the published rate card, and the free Developer grant.
• Sizing and limits - machine sizes and what each costs to run.
• Timeouts and auto-stop - --ttl, --idle-timeout, and pause/resume.

Next steps