Most AI work apps have one lane: coding. Useful, but my day does not.
I might fix a bug, check a project file, plan a YouTube upload, run a server command, build a game, then switch to something completely different. I wanted one desktop workhorse that could move between those jobs without making me juggle a pile of tabs and disconnected tools.
So I built SARAH.
SARAH is a desktop application powered by the AI provider you choose. Connect a hosted provider, use an OpenAI-compatible API, or run a local model with Ollama. The provider supplies the brain; SARAH supplies the workspace and the hands.
Inside a project, SARAH can work with real files, run commands, organise tasks and notes, use plugins, and turn small programs into reusable tools. It can help write and debug code, but coding is one job among many—not the whole product. The same workspace can support channel planning, game development, server chores, research, and the odd “what is this file?” mystery.
A few things I built because I wanted them myself:
- Projects with real context: files, tasks, notes, skills, plugins, and project memory stay together.
- Tools you can inspect: plugins are readable files; small programs can become reusable tools.
- A proper work loop: run commands, preview results, steer or stop live runs, and keep the work in one place.
- Room to recover: snapshots and undo help when an edit goes sideways.
- Your choice of brain: use a supported provider or connect a local Ollama model.
It is not magic, and it is not a replacement for judgement. It is a practical desktop workhorse for handing AI more of the actual job: context, files, tools, and follow-through.
If you want an AI app that can help with more than the code-shaped part of your life, take a look at SARAH: https://sarahai.co.uk
I built this as an independent project. I would genuinely love to hear what work you would hand to a desktop AI workhorse—and what it would need to do to earn that trust.
Top comments (0)