Coder

You will reach for this the day someone asks where your agents are actually running. The answer here is a workspace you defined, on infrastructure you own, with the agent inside it rather than beside your dotfiles. That containment is the deciding trait, because every other question about autonomous work becomes easier once the blast radius is a disposable environment instead of your machine.

Pick it if that requirement is real and you have people to run it. Pick Ona when you want somebody else operating the same idea and will pay for the privilege.

Count what you are taking on. Workspaces declared as code need someone to maintain those definitions, a control plane needs upgrades and backups, a brokering layer sits in the path of every model call and becomes an outage when it fails, and all of that exists before a single line of code is written by an agent. Teams underestimate this consistently, and the failure is not a bug, it is an unstaffed rota.

What it does right: workspaces are network-isolated, so an agent that goes wrong is contained by the architecture rather than by a setting.

1. The governance layer intercepts model calls and tool-protocol traffic at the wire rather than instrumenting an agent, so any agent placed in a workspace is observable without modification. That is the correct architectural choice and it is why this design survives the agents themselves being replaced. 2. Environments declared as code make a run reproducible, which is the precondition for any claim about what an agent did.

No benchmark is published, and none would be meaningful for a substrate. The observation: the design's value grows as the agents inside it churn, which is a rare property.

This is the open-core split executed properly. A strong copyleft licence on the core means no cloud provider can offer it as a managed service without publishing their changes, which is the only structural defence an infrastructure company has ever had. Above it sits an annually priced tier for the buyers who need support and controls, and 14,366 stars indicate the free edition is doing its distribution job.

Likely acquirer: a cloud or a development platform that wants agent governance it did not build. Position: strong, with pricing power that grows as agents become a compliance question.

One sentence on the demo: the agent ran somewhere I could point at on a diagram. That is the whole value. It deploys on our own infrastructure, so residency and retention are answered by where we put it, the brokering layer gives security a record of what each agent called, and it runs unattended in our pipelines rather than only on a laptop. The obstacle is the missing number on the paid tier, which turns budgeting into a negotiation.

Onboarding is two weeks including the platform work. Approved with conditions: a named owner and a quoted annual price.

This is ownership in the strong sense. The licence forces anything derived from it to stay open, so a fork survives the company by design rather than by permission. Installation is a shell script onto my own boxes, the whole control plane is mine, and inference can point at an endpoint inside my own network, so nothing about this arrangement requires a vendor to exist tomorrow.

It speaks the tool protocol in both directions and exposes a documented interface, so I can script the platform itself rather than just the agents in it. The trade is that I now run a platform. I knew that going in.