Run LangGraph on MIOSA

What you're building

a framework for agents as a stateful graph with parallel branches and joins Modelled on LangGraph, by LangChain.

You define nodes and edges; state flows through the graph, branches run in parallel, and checkpoints let a run pause, resume and branch.

Primitives you'll use: Sandbox · Postgres

• Stateful graphs of agent steps
• Parallel branches and joins
• Checkpoints, pause and resume
• Human approval nodes

You install and run the real LangGraph on MIOSA. Read the official docs first: docs.langchain.com/oss/python/langgraph/overview. Every install command below comes from them; if the docs and this guide disagree, the docs win. LangGraph is open source Python library (LangChain).

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 Postgres Managed relational data, injected as DATABASE_URL in the machine and in production. miosa api POST /databases -d '{"name":"app-db","engine":"postgresql"}' Docs
4. 2 A workspace per customer Isolates each customer’s machines, deployments, and data as they onboard. miosa workspace create customer-1 Docs
5. 2 Branding and white-label Your name and slug on previews, deployments, and the desktop; customers never see MIOSA. miosa org Docs
6. 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 -> Checkpoints live in managed Postgres, so a run survives a sandbox 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 langgraph-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 LangGraph

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

pip install -U langgraph

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

Configure

Install the model package you use (for example `langchain-anthropic` or `langchain-openai`) and export your own provider key.

Use a Postgres checkpointer for state so a graph can pause and resume.

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.

python graph.py   # your script that builds and invokes the graph

Check: the tool starts without errors and responds.

Persistence and access

Checkpoints live in managed Postgres, so a run survives a sandbox pause.

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

Make it a product

Expose it as a per-customer API: one thread id per customer session, checkpoints keyed by 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

LangGraph 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.