Build a Manus-style agent

What you’re building: a general agent with its own computer: it plans, uses a browser and desktop apps, produces files, and hands control to a human when it is stuck.

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

What you’re building

Manus-style products give the agent a real computer: a desktop, a browser, files, and the ability to click and type. That is what MIOSA’s Computers are for: full Linux desktops you reach over the API, with screenshots, mouse and keyboard control, and a streamed screen.

The agent loop is: look (screenshot), decide, act (click, type, open an app), verify, repeat. When it cannot proceed, hand the same live desktop to a human for a moment, then take it back. Because the computer is persistent, the session survives between turns and users come back to the same machine.

Use a Computer when the task needs a screen; use a Sandbox when it only needs a shell.

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 desk-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

See Computer use and Embedding and streaming for the live screen and human handoff.

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 desk-agent --to <version-id>, and inspect a live app with miosa deploy logs desk-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 desk-agent app.example.com
miosa deploy domains desk-agent          # shows the DNS record and verification target
miosa deploy domain-verify desk-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