Show HN: Workplane – collaborative filesystem for humans and AI

Posted by tweezers0x on Wednesday May 27, 2026 @12:22PM
from the show-hn dept.

Workplane is a browser-based workspace designed for both humans and AI agents.

HTML, Markdown, and other files are rendered directly in the browser, support comments, are versioned automatically, and can be shared with teammates or clients.

MCP-compatible tools like Claude Desktop, Claude Code, and OpenClaw can access shared folders, read and edit files, generate artifacts, and collaborate on the same workspace as your team.

Would love feedback from people sharing files with AI tools.

( 5 comments | 5 points | on HN )

Re:Show HN: Workplane – collaborative filesystem for humans ... by NonToxCo on Wednesday May 27, 2026 @09:27PM (#48303161)

How are conflicts represented when two people and an agent edit the same directory at once?

[ Parent | on HN ]

Re:Show HN: Workplane – collaborative filesystem for humans ... by hagay3 on Thursday May 28, 2026 @06:43AM (#48307122)

how its shared across the orgnization?

[ Parent | on HN ]

Re:Show HN: Workplane – collaborative filesystem for humans ... by tweezers0x on Tuesday June 02, 2026 @09:18AM (#48369901)

Per-artifact today, which is a folder with versions.

You invite people as editor/viewer, or make a artifact public for link-sharing.

Agents get in via a token scoped to your account. There's no org layer yet — domain membership or SSO — that's next.

Is org-wide sharing what you actually need?

[ Parent | on HN ]

Re:Show HN: Workplane – collaborative filesystem for humans ... by geraldsterling on Friday May 29, 2026 @04:29AM (#48320578)

The human/agent handoff angle is interesting. How are you thinking about provenance over time — e.g. being able to tell which artifact came from which agent run, prompt/context, or human edit?

[ Parent | on HN ]

Re:Show HN: Workplane – collaborative filesystem for humans ... by antonios_makro on Monday June 01, 2026 @11:17AM (#48357977)

For the human collaboration part, what's the hand-off model? does the agent block waiting for a human to resolve a comment, or is it fire-and-forget?

[ Parent | on HN ]