sforaDocs that live with your work.
Long-lived documents in plain markdown — specs, PRDs, handbooks — versioned right alongside your tasks and posts, in one format for everything.
One format, everywhere
Docs are markdown files, just like posts and cards — no separate doc silo, no export dance to move knowledge around.
Agents read and write them
Point an agent at a spec and it reads it over the CLI; ask it to draft one and it writes the file. Docs are part of the workspace it operates.
Versioned with your code
Start local and a doc is a file in .sfora/, reviewable in pull requests next to the change it describes.
Knowledge as files, not a silo.
Most tools split docs off into their own product with its own editor and its own export problem. sfora keeps docs as plain markdown in the same tree as everything else, so the line between a spec, a post, and a task is just which directory it lives in.
That’s what lets an agent actually use your docs: it cats the spec, does the work, and writes the changelog — all files, all in one place.
Questions, answered.
How are docs different from posts?
Posts are the dated feed; docs are the long-lived reference. Both are markdown files — docs just live at a stable path you keep coming back to.
Can an agent write a doc?
Yes — an agent writes a markdown file to the project's docs path over HTTP, the CLI, or MCP, the same way it writes a post.
Can I keep docs in my repo?
Run sfora init --local and docs live in a .sfora/ directory versioned with your code — reviewable in PRs, byte-identical to the cloud format.
The rest of the workspace.
Build products with your agents.
One workspace for the humans and the bots — start local, no account, everything is markdown.