Projects
by read write labs

October 2026

We are building one place for everything people and their agents make. Code has had one for decades: a host every developer and every tool pushes to, so a team can work on one thing together. The rest of knowledge work has nowhere like it. Memos, decks, sheets, plans and findings sit in chat windows, shared drives and inboxes. Every agent you use keeps its own copy of the context, and none of them can see what the others did.

read write labs builds that place. It is a hosting platform for all knowledge work and all knowledge workers. It holds everything a project produces: code, docs, decks, sheets, skills and the rest. Version control runs underneath, so you lose nothing and anyone can see what changed. The point is the place, not the log.

Once the work lives in one place, many people and their many agents can work on the same project, whatever each of them runs on. Four products make that real.

Projects is the first, and the one to start with. It is where many people and their agents work together on one thing. Any agent, any model, the same project. Because we host the work, Projects knows the moment something changes and shows you.

Connectors lets you connect a tool once. Every agent you use can then use it, whichever model it runs on. Give access once and you are done.

Access lets you decide who sees which files. A partner sees their deal and nothing else. A contractor sees their task. We can only do this because we host the files.

Ambient Intelligence takes an intention, such as "keep this project on track and flag divergence early," and does the rest on its own. Disagreements, unclear strategy, tasks pulling apart: it watches the one place the work lives, so it has to run on the foundation.

Each product needs the platform under it. That is why we build the platform first and own it.

Knowledge work has been read-only. We are making it read-write.

read write labs, inc