Run five agents on a task and you hit the same wall: each one works in its own sandbox, blind to what the others produced. Blaxel Agent Drive is a shared, persistent filesystem that fixes that — mount the same Drive across multiple agent sandboxes and they all read and write the same files.
What it actually is
Not another agent frontend. It’s infrastructure. Agent Drive is a distributed filesystem multiple sandboxes mount at once with concurrent read-write access. A coding agent writes an artifact, a review agent in a separate sandbox reads it as a normal file path. Drives scale automatically — no fixed capacity, no pre-provisioning — and files stick around independent of any single session.
The API and where it fits
For developers, it’s a mount-and-read/write API on Blaxel’s sandbox platform. Typical uses: pass files between sandboxes, store tool-call outputs and context history for other agents to pick up, share a common dataset, or keep a shared package-dependency cache so agents stop reinstalling everything.
Multi-agent orchestration is having its moment, and the missing piece has been shared state. That’s the bet here — own the filesystem layer everyone else builds on. It’s in private preview.
You Might Also Like
- From Claude Flow to Ruflo 22k Stars 5900 Commits and the Multi Agent Swarm Taking Over Claude Code
- Oh my Claudecode Turns Claude Code Into a 32 Agent dev Team and 11 8k Stars Agree
- Claude Code Source Leak Kairos how a 59 8 mb File Exposed Anthropics Entire Agent Playbook
- Hiveterm Bets on the Multi Agent Workspace Claude Codex and Gemini in one Terminal
- Openai Codex Claude md Auto Import Makes Switching From Claude Code a two Click Move

Leave a comment