The agent you already use
Claude Code, Codex, OpenCode, Pi, and Cursor, signed in with an API key or your account
QuickstartRun Claude Code, Codex, OpenCode, Pi, or Cursor in the cloud, each in its own microVM with a persistent workspace and your repositories. Start a task, disconnect, and pick it up from any device.
The runtime behind 2,000+ ambitious teams
Customer storiesYour existing coding agent, on dedicated compute that keeps running when you disconnect.
Claude Code, Codex, OpenCode, Pi, and Cursor, signed in with an API key or your account
QuickstartRuns independently of your machine, and pushes to its own branch
QuickstartPreview each change on a public URL, then release through your pipelines
Explore preview environmentsRun harnesses on Northflank Cloud, or on a BYOC cluster in your VPC
Explore bring your own cloudHarnesses run independently of your machine. Start a task, disconnect, and review the branch and preview later.
Agents pick up tasks, write code, and open pull requests. Northflank turns every change into a live preview, promotes it through staging to production, and feeds what happens in production back into the next task. No tickets, no handoffs, no waiting for environments.
Connect to the same workspace from the dashboard, the CLI, or another machine.
Agents can create sandboxes, deploy services, and provision databases through the Northflank API and CLI.
Quickstartnpm install --global @northflank/cli
northflank login
northflank dev ssh --projectId my-app --harnessId claude-code
claude --continuePolicies for which agents run, and who can access each harness.
A Linux environment with your code, your tools, and the compute to run them.
QuickstartClaude Code, Codex, OpenCode, Pi, and Cursor, or an empty harness for your own tooling.
Each harness runs in its own Kata microVM, isolated from other workloads.
The home directory is a 5 to 100 GB volume that persists across restarts.
Clone a branch or create a new one, plus up to 10 more repos. Pushes are scoped to the harness branch.
Expose ports on public URLs to preview what the agent is building.
Any plan size and an optional GPU, with environment variables and secret files.
Standard Northflank rates, billed per second. No seat or per-agent fees. Paused harnesses don’t use compute.
Full pricing| Resource | ||
|---|---|---|
| Compute | ||
| CPU | $0.01667/ vCPU / hour | $0.02083/ node vCPU / hourVolume discounts available under a CSA |
| Memory | $0.00833/ GB / hour | Not billed |
| Ephemeral storageNot persisted | Free | Not billed |
| Storage and network | ||
| Persistent diskNVMe, for addon and service volumes | $0.11657/ GiB / month | Not billed |
| Additional IOPSFirst 3,000 IOPS and 140 MiB/s per disk included | $7.37/ 1,000 IOPS / month | Not billed |
| Additional throughputFirst 3,000 IOPS and 140 MiB/s per disk included | $5.85/ 100 MiB/s / month | Not billed |
| Network egressIngress is free | $0.06/ GB | Not billed |
| Egress gatewayDedicated IP | $15.00/ gateway / month | Not billed |
Teams that build and ship with Northflank, in their own words.
Cycle time is everything. With Northflank, I can make 100 commits and 100 deployments in a single day – it keeps up with my pace like nothing else. When it comes to debugging, the meantime to resolution is unbeatable. I can identify issues and deploy fixes faster than customers can even report them. I know about problems before they do and have them fixed before they call.
Northflank is the first batteries-included developer platform that doesn’t suffer from the invisible ceilings that hover over its competitors. We could have built all of Slack with Northflank – and we would have, had it been available.
Northflank helped us scale to over 3M users with an engineering team of two. It allows us to run 10,000 AI training jobs and half a million inference runs per day, without us having to worry about autoscaling or spot instance orchestration. We don’t waste time or money on infrastructure, so we can focus on building product.
Enterprise
Run agents, AI-built software, and core systems inside your own infrastructure, with the compliance, governance, and guarantees your organisation needs.
Claude Code, OpenAI Codex, OpenCode, Pi, and Cursor. You can also start an empty harness and install your own tools.
Claude Code, Codex, and Cursor can use an API key or your account. OpenCode and Pi sign in with your account from the terminal. API keys are stored encrypted and never shown again.
The workspace is on a persistent volume, from 5 to 100 GB, so files in the home directory survive restarts and pauses. You can grow the volume later.
Yes. Harnesses push through a proxy scoped to the harness’s branch, with credentials that refresh automatically.
Yes, on BYOC clusters with microVM (Kata) support, so code and data stay in your account.
Like any workload: by the second, for the CPU, memory, and GPU of the plan you choose, plus the workspace volume. On the free Sandbox plan, a harness can use up to 1 vCPU and 1 GB.
Start free on Northflank Cloud or in your own cloud account. Same platform and workflow either way.
npm i -g @northflank/clinorthflank login