puppyone-ai/puppyone-cloud

What it solves

Puppyone provides a centralized, version-controlled "Context Drive" for AI agents. It solves the problem of managing fragmented data across various SaaS tools and ensuring that different agents have secure, scoped access to only the specific files and information they need to perform their tasks.

How it works

It connects to external data sources (GitHub, Gmail, Google Drive, web pages, etc.) and transforms that data into agent-friendly formats like Markdown or JSON. This data is stored in a cloud file system. Agents can then access this drive through multiple "Access Points," including the Model Context Protocol (MCP), REST APIs, a CLI, or isolated sandboxes (Docker/E2B) where only authorized files are mounted.

Who it’s for

Developers and teams building AI agents that require persistent, shared, and secure context management across different tools and environments.

Highlights

• File Level Security (FLS): Enforces permissions at the filesystem layer so agents only see files they are authorized to access.
• Git-native Versioning: Includes version history, diff comparisons, one-click rollbacks, and a checkout/commit workflow for agent edits.
• Multi-modal Access: Supports MCP for integration with clients like Cursor and Claude Desktop, as well as bash/SSH and local folder sync.
• Built-in Connectors: Native integration with Google Workspace, GitHub, and Supabase to pull context automatically.