Launching today
BearDrive
The open-source shared folder for your team's AI agents
138 followers
The open-source shared folder for your team's AI agents
138 followers
Your AI agents create real files on your laptop: research, plans, decks, data. BearDrive syncs them to your team with versions, authorship, and links, so teammates and their agents can reuse them. No new workspace to adopt. Your filesystem is the shared surface.
Runbear
Runbear
@michael_vavilov It's a fair question! Thank you, Michael. Honest answer first: if Notion + MCP is working for your team, don't migrate. Notion is great for prose the team reads.
The category is different though: we're much closer to Google Drive than to Notion. Notion is a place agents write into; BearDrive is a folder agents work in. And being the native file system makes a bigger difference than it sounds.
Our agents' output is mostly not prose: HTML reports, CSVs, PDFs, deck files. In Notion those become attachments, and an attachment is a dead end for the next agent. In a real folder they're just files at real paths, so when my agent continues a teammate's work it greps, edits, and re-renders with its normal tools. No fetching blocks over an API, no markdown-to-blocks conversion loss, no re-explaining context.
So in practice teams run both: Notion stays the wiki humans read, the shared folder is where working artifacts live, with attribution per change down to the agent session (which already caught an accidental rollback of a teammate's edits for us).
If your agents' output is mostly prose pages, you're honestly not our user yet, and that's fine. Curious though: what happens today when an agent produces something that isn't a page, like a CSV or an HTML report?
BearDrive
Maker here. Really proud of the team for bringing BearDrive to life🔥
AI agents are having their Dropbox moment!
Our agents can produce dozens of HTML pages and PDFs in a day: quick dashboards, analysis reports, launch docs.
Creating useful files is easy now.
Finding them again is not.
A week later, I know the report exists. I just don’t know whether it’s on someone’s laptop, attached in Slack, or buried under a filename nobody remembers.
And when I do find it, I’m not always sure it’s the latest version.
That’s the Dropbox moment: not another place to dump files, but a way to stop agent-made work from feeling scattered and disposable.
The part I care about most is the handoff. One agent creates something, and another teammate’s agent can actually find it and build on it later.
When an agent creates a useful file on your team, how does the next person find it a week later?
the "syncs to your team in seconds" part is what gives me pause rather than the storage question everyone else is asking. an agent working on something sensitive - a customer contract draft, a research doc that accidentally captured an API key or PII from a scraped page - now propagates to the whole team's synced folder before any human looks at it, since there's no workspace-level review step like a PR or a Slack post someone has to actually send. is there any per-file or per-folder gate before something syncs, or is the model "everything your agent writes locally is now everyone's by default" and you're expected to gitignore-style exclude the sensitive stuff yourself?
Disclosure: I'm a friend of Snow's. That said, the framing here is sharp — "your filesystem is the shared surface" is a much better bet than asking teams to migrate into yet another workspace. The versioning + authorship layer is what makes it more than a sync tool. Congrats on the launch!
Runbear
@jaehee_ko Thank you very much for your support, Jaehee!
Runbear
Having a shared folder for each customer has made working together so much easier for our team. So excited that we got to build this together! Thank you so much for your support! 🐻🚀
Runbear
@shuwn_jung let's goooooooo