BearDrive

BearDrive — Google Drive for AI agents

BearDrive mounts any folder as a synced volume: its contents stay synchronized across all your devices and teammates through a BearDrive hub, every change is tracked (who, when, on which device), and everything keeps working offline. The CLI is bdrive; a hub is a bdrive web server you (or we) run on an object store — clients sync through it over HTTPS and never touch the storage directly.

What it's for, first and foremost: sharing context across AI agents — give every agent on the team the same folder as memory, and your agent knows what their agent knows. (People are covered too: any synced file becomes a public URL that renders as a page.) Notes, plans, findings, and artifacts follow the team everywhere — and unlike a memory API, they stay real files with provenance: every change is attributed to the human, agent, and device that made it, and the hub's Insights show what your agents actually read (and which hot-but-stale docs nobody maintains).

Browse with read heat	Public share pages

$ bdrive login https://your-hub   # once per device — self-host a hub in ~10 min (docs/self-hosting.md)
$ cd ~/workspace && bdrive init
initialized /Users/snow/workspace
  project: workspace (p-7f3a2c91)
  daemon:  running (pid 55434, scan 3s, remote sync 10s)

BearDrive Cloud — zero-setup, bare bdrive login — is on the waitlist at beardrive.ai. Self-host to try it today.

On another machine:

$ bdrive login https://your-hub && cd ~/workspace && bdrive init
# … connect the same project; the files appear and stay in sync

Features

• Any folder is a project — bdrive init turns any folder into a synced project. Files are real files on disk: every tool, editor, and agent can use them with zero integration work. Rename or move the folder freely — state is keyed by a stable id, never the path.
• Multi-device sync — devices converge through a shared hub. Each device only writes its own append-only journal, so no locking service is needed; the hub can be backed by any object store.
• Change tracking — bdrive log and the web UI's History view show which account changed which file, when, from which device (name, OS, IP). Content is stored content-addressed, so every version is retained — view or download any point in a file's history.
• Cloud-provider agnostic — a hub can store on Amazon S3 (s3://), Google Cloud Storage (gs://), any S3-compatible store (MinIO, Cloudflare R2 via AWS_ENDPOINT_URL), or a plain shared directory (file://, e.g. a NAS). Clients never see it.
• Offline-first — the working folder is always fully usable with no network. Changes are journaled locally and pushed when the remote becomes reachable again.
• Conflict-safe — concurrent edits resolve deterministically (last-writer-wins), and the losing version is preserved as a name.bdrive-conflict-<device>-<time> file. Nothing is silently dropped.
• Selective sync — a gitignore-style .bdriveignore opts files out, and bdrive init --shared <dir> (or the interactive prompt) narrows sync to one shared subfolder.
• macOS & Linux.

Install

brew install runbear-io/tap/beardrive  # macOS (and Linuxbrew); installs the `bdrive` CLI

or from source:

go install github.com/runbear-io/beardrive/cmd/bdrive@latest

Quick start

# 1. Sign this device in against your hub (once per device).
#    Self-host a hub in ~10 minutes (docs/self-hosting.md), then:
bdrive login https://your-hub
#    (BearDrive Cloud — zero-setup, bare `bdrive login` — is coming;
#    join the waitlist at beardrive.ai. Self-host to try it today.)

# 2. Start syncing a project — interactive: create or connect a project,
#    sync the whole folder or just ./shared. Re-run any time to resume.
cd ~/my-project && bdrive init

# 3. Work normally — create, edit, delete files with any tool.
echo "remember this" > memory.md

# On every other device: `bdrive login https://your-hub` once, then bdrive init in a folder
# and connect the same project.

# See what changed, who changed it, and from which device
bdrive log

# Check sync state and the daemon
bdrive status

# Stop syncing (files stay on disk; bdrive init resumes any time)
bdrive stop