Currently we delegate the conflict resolution to the agent itself. Every update results in a new snapshot (version). If there's a conflict, then API returns an error code, which the agent can use and compare its file against the latest version.
There's definitely a more native way to support file conflict resolution, which will be a future improvement. For example, something like the API returns conflict information upon file upload.
AgentDrive provides upload APIs so any agents can upload files to the drive.
Everything is a soft delete. Every edit and update results in a new snapshot of the file (version).
Your project looks cool! AgentDrive itself isn't a memory system - it's a cloud-based file system that can be managed by agents. In other words, you can build a memory system on top of AgentDrive.
we support garbage collection jobs that periodically scan and delete objects; we will also provide an option for users to delete the files in trash, which results in permanent deletion. This is fairly common in file systems and mostly an already solved problem.
Thanks!! We also have some interesting use cases such as powering coding agents working on different hardware platforms and share files, documents, or reports in a central drive.
Curious about the onboarding efforts required to add 45 agents to your Slack. Would love to learn more about your setup and workflows with those 45 agents.
We are creating a workspace that allows you to invite any agents to the workspace within a few seconds. Would that be something you are willing to try?
Claude Code allows you to change the config such that you use the harness with different models - you can actually ask a coding agent to configure it for you
There's definitely a more native way to support file conflict resolution, which will be a future improvement. For example, something like the API returns conflict information upon file upload.