Your machine
W1 runs on your own machine: Windows, macOS, Linux and inside VS Code. Your project stays on your disk. Only the context a request needs ever leaves it.
W1 is for the dreamers.
The ones with the whole thing in their head and no team, no budget, and no one coming to help. Describe it. W1 builds it, checks it, and shows you every step it took. An AI agent for real projects: code, documents, data and research.
Proudly African
Get started
Nothing to set up.
Nothing to set up.
Nothing hidden.
No API key to paste, no config to learn, no new way of working. Install it, open the folder you already have, and say what you want done. W1 plans the work, does it, runs the checks, and keeps every step on screen while it happens. When something fails, it says so.
- 01Install on Windows, macOS, Linux or VS Code. Two minutes.
- 02Open a project folder and say what you need done.
- 03Watch it work, check what it did, and ship it.
What W1 actually does.
Works with what you already have.
Your existing codebase
No migration, no new format, no wrapper repo. Open the folder you already have and describe the change. W1 reads the code around it before it writes anything.
Your tests and your tools
W1 runs the checks you already run and reports what passed and what did not, instead of telling you it is done. Your editor, terminal and git stay exactly as they are.
Your budget
W1 is built lean on purpose. Every call does useful work instead of rereading what it already read, so the same money ships more. The Free plan is free for good, and a paid plan only buys more room to work. It never unlocks a feature.
Questions about W1
What can it do?
Real project work, not chat. It reads an existing codebase and ships changes into it. It runs the tests and tells you what passed. It turns messy notes into a document, a deck and a spreadsheet, and pulls research together with the sources attached, all inside one project. If a task costs you an afternoon of tabbing between tools, that is the shape of task it is built for.
Do I need to know how to code?
No. You describe the outcome in plain language and W1 does the work in front of you. Knowing what you want is the only requirement. It is not a magic box either. Because every step stays visible, you end up understanding more of what happened than you would from a tool that hands you an answer.
What happens when it gets something wrong?
You see it, which is the whole point. W1 runs the checks that matter for the task and reports what failed instead of finishing with a confident summary. Every file it touched is listed, and you can rewind the work without reaching for git.
Does my project leave my machine?
Your project stays local. W1 sends only the context a request needs, never your whole codebase, and it will never ask you for a provider API key. Full run traces are kept on your own machine, in W1's own folder rather than inside your project. The privacy policy has the detail.
How is this different from the other agents?
Two things. It works across documents, data and research as well as code, in one project instead of four tools. And it is built lean: it reuses the context it already has instead of rediscovering it every turn, so a serious agent is not something you get priced out of.
What does it cost?
The Free plan is free, and it stays free after the beta. If you need more than the free budget you can buy more. Plans start at R150 a month, and every tier runs exactly the same software. See pricing.
Who is building this?
A team in Africa, shipping releases most weeks. Bug reports from beta users have turned into fixes in the same week. If you mail us, a person who works on the product reads it. See contact.
What a beta user said
★★★★★
“W1 has been genuinely useful for working on real projects rather than just generating snippets. I particularly like the project-level approach, where it can understand the existing codebase, work through tasks, and show the steps and changes it makes. The workflow feels much more practical than simply asking an AI for code and manually figuring out where everything belongs. Being able to have it work through a task, run checks, and report what happened makes it especially useful for larger projects. It is still beta software, so there is room for improvement, but the overall direction is very promising. For developers who want an AI agent that helps them actually move a project forward, rather than just provide suggestions, W1 is worth trying.”
Open a project. Describe the outcome.
Free on Windows, macOS, Linux and VS Code, and the Free plan stays free after beta. You sign in so usage stays fair and your sessions stay yours.