Run CrewAI on MIOSA

What you're building

a framework for crews of role-based agents working on tasks Modelled on CrewAI, by CrewAI.

You define agents with roles and goals and tasks they own; a crew runs the tasks in sequence or in parallel and passes results along.

Primitives you'll use: Sandbox

• Role-based agents
• Tasks with owners and expected outputs
• Sequential or parallel crews
• Flows that mix code and agents

You install and run the real CrewAI on MIOSA. Read the official docs first: docs.crewai.com. Every install command below comes from them; if the docs and this guide disagree, the docs win. CrewAI is open source Python framework.

What you need on MIOSA

Each row is one thing to create before you start. The number matches the step that uses it.

1. 1 Organization and API key Scopes every call; a workspace key is all a worker needs. miosa api-key create app-key --preset agent Docs
2. 2 Sandbox The isolated Linux workspace the agent writes code and runs commands in. miosa create app-box --template nextjs --wait Docs
3. 2 A workspace per customer Isolates each customer’s machines, deployments, and data as they onboard. miosa workspace create customer-1 Docs
4. 2 Branding and white-label Your name and slug on previews, deployments, and the desktop; customers never see MIOSA. miosa org Docs
5. 2 Usage metering and bill-to Usage per customer, and which account pays for new machines. miosa org bill Docs

Architecture

How it runs on MIOSA

Where it runs -> a MIOSA sandbox (an isolated Linux workspace)

State and files -> The crew project lives in /workspace; keep outputs in files or Postgres so runs survive a pause.

Model -> your own provider key, never a MIOSA platform key

Your customers -> one workspace each, isolated from each other

Auth and tenancy

Your organization is the platform; customers never get a MIOSA account, they sign into YOUR product. One workspace per customer, created as they onboard, isolates their machines, runs and data.

miosa workspace create crewai-customer-1

Tag every machine and run with the customer id in `metadata`, and never query across customers. Meter usage per customer with GET /api/v1/usage and set who pays with PUT /api/v1/bill-to (/docs/platform/usage-and-billing).

Install CrewAI

Run these inside the sandbox (for example `miosa exec crewai-box -- bash -lc '<command>'`), in order. The commands are from the official docs.

python3 --version   # CrewAI needs Python >= 3.10 and < 3.14

curl -LsSf https://astral.sh/uv/install.sh | sh

uv tool install crewai

uv tool update-shell

crewai create crew my-crew

cd my-crew

crewai install

Check: the install finishes without errors; the next sections configure and start it.

Configure

Put your own provider key in the project's `.env` (the generated project defaults to an OpenAI key); edit `agents.yaml` and `tasks.yaml` to define the crew.

Model: Anthropic (Claude). Calls use my own provider key (ANTHROPIC_API_KEY); MIOSA platform keys are never used.

export ANTHROPIC_API_KEY="..."   # set it in the process environment, or the Secrets API; never write it into files you commit

Run it

Start it and prove it works.

crewai run

Check: the tool starts without errors and responds.

Persistence and access

The crew project lives in /workspace; keep outputs in files or Postgres so runs survive a pause.

Check: after the machine pauses and resumes, the tool starts again with its state intact.

Make it a product

Expose crews as a per-customer API: one sandbox per customer workspace, a job queue in front, results stored per customer.

Limits and costs

Pin the version you tested and update deliberately; these tools change quickly.

Give the tool only the credentials it needs, as secrets, not baked into files.

Prototype: keep it to one machine at the default size, skip replicas and custom hostnames you do not need, and delete everything when you are done.

Acceptance checks

CrewAI runs on a MIOSA sandbox and answers a real task.

State survives a pause and resume.

Each customer has its own workspace and its own instance; nothing is shared between them.

Everything it created can be deleted with nothing left running.

Next steps

• Agent prompt builder Pick a product shape and hand the brief to your agent.
• Run coding agents Run Claude Code, Codex or Cursor in the cloud, or build a product on them.
• Compare MIOSA How MIOSA compares to other sandbox and agent platforms.
• What you can build Every product pattern MIOSA supports.