Run a coding agent on local models.
For when the constraint is not cost but that the code cannot leave the building.
What running locally actually requires
Three things, and most tools fail at least one. The application has to be a desktop binary rather than a web app. It has to accept an arbitrary model endpoint rather than routing through a vendor. And it has to work with no outbound connection at all, which means bundled assets rather than fetched ones. All three are true here, which is why offline is a supported mode rather than a degraded one.
Setup
Install Ollama, pull a coding-oriented model, and point the app at the local endpoint. There is no account, no API key and no first-run call home. Disconnect the machine afterwards and behaviour is unchanged, which is the test that matters.
The quality tradeoff, stated plainly
Local open models are behind frontier hosted ones. The gap is largest on long multi-step reasoning and smallest on structured tasks like reading a repository and emitting a graph, which is why diagram generation holds up locally better than open-ended refactoring does. If your constraint permits a hosted model you will get better results; this exists for when it does not.
Mixing local and hosted
Roles can use different models, so a local model can handle everything that touches source while a hosted one handles work that does not. That is a middle position many organisations can actually approve, and it is more useful than the all-or-nothing framing the choice usually gets.
What changes when you go local
| Local model | Hosted model | |
|---|---|---|
| Code leaves the machine | No | Yes, to your provider |
| API key required | No | Yes, yours |
| Marginal cost per turn | Zero | Provider's token pricing |
| Works with no network | Yes | No |
| Quality on structured extraction | Good | Better |
| Quality on long reasoning | Noticeably behind | Better |
| Speed | Bounded by your hardware | Bounded by the provider |
Setup
Questions
Related
- Local-First AI Coding AgentSame agent core in a native desktop app and a 6 MB Rust binary, running whichever model you choose, including one on your own laptop.
- Diagram-Driven DevelopmentThe diagram stops being documentation produced after the fact and becomes the instruction the code is written from.
- Terminal Coding AgentOne binary, no runtime, no browser. Free and open source.
- AI Assistant for ObservabilityWorth being precise about what this is: it drives the observability tools you already run. It is not an LLM tracing platform, and if that is what you searched for, the tools below are the right ones.