Nimbalyst

The deciding trait is that changes arrive as red and green diffs you step through one at a time and accept or reject. That is a different relationship with an agent than reviewing a finished branch: you catch the wrong idea at the third hunk instead of after twenty files, and you stay responsible for what your repository contains.

The cost is pace. Stepping through diffs is slower than trusting a run, and if you have five agents going it becomes the bottleneck. Pick it if you review everything anyway. Pick Proliferate if you would rather check the branch afterwards.

The gap is between the list and the footnote. Two providers carry an alpha label in the documentation, which means a user who picks one of them is running the least tested path in the product while believing they picked from a menu. Nobody reads the footnote during evaluation. They read it after a session behaves strangely.

What it does right is isolation. Every session gets its own worktree and its own branch, so a misbehaving agent damages a directory rather than the working tree you were using.

1. Choosing plain files as the storage format is the decision that makes the rest defensible. A diagram held in application state is invisible to review; the same diagram written to the tree is diffable, bisectable and survives the tool that made it. 2. That also removes the migration problem, since abandoning the product leaves the artefacts behind rather than trapped.

2. No evaluation is published, and none is required: the claims are about representation and workflow, both of which are verified by reading the repository afterwards.

A named successor product is a useful signal. It means the team learned something expensive and chose to rebuild rather than patch, and it means the previous audience carries over at no acquisition cost. It also means the clock started again, and there is still no visible way this turns into money.

Moat: the extension surface, if third parties actually build on it. Likely acquirer: a developer platform that wants the desktop workflow and not the codebase. Position: use it, and assume the commercial layer arrives later and changes the terms.

The financial review is over in a sentence and the security review is not. A phone application that approves changes and queues work extends the trust boundary to hardware outside our fleet, and my questionnaire has four pages about exactly that. There is no directory integration and no central policy to lean on.

Operationally it stays on the desktop and never becomes a measurable step, so throughput claims cannot be verified against anything we track. Approved with conditions: laptops only, phone companion disabled until mobile device management covers it.

Embedding a real terminal instead of writing a mediocre one is the tell that somebody here has taste. The same instinct shows in the extension SDK: rather than guessing which file types matter, they exposed the host and let me write the editor for the format my team invented. That is the difference between a product and a platform.

MCP support means the servers already running on this machine become tools without a shim, and the permissive licence keeps a fork viable if the desktop app ever goes somewhere I dislike.