Skip to content

OYYO Agents

AI that can act, with boundaries.

OYYO Agents are designed to use tools, code, browsers and connected systems through permissions, sandboxes, approval gates and audit trails.

On the roadmapยท 0.9 Agents

AI that can act, with boundaries.

OYYO Agents are designed to use tools, code, browsers and connected systems through permissions, sandboxes, approval gates and audit trails.

  • Permission model
  • Sandboxed execution
  • Approval gates
  • Audit trail
  • Tool and MCP surface
  • Scoped autonomy
OYYO Agents, illustrative diagram of how the capability is designed to work

Autonomy where useful. Control where necessary.

This capability is part of the published OYYO roadmap. It is described here as designed and planned, not as shipped software.

Think. Create. Execute.

One intelligence. One workspace. One place for everything.

OYYO is being built in public against a versioned release line. Join the early access list and follow the roadmap.