OYYO Agents
AI that can act, with boundaries.
OYYO Agents are designed to act only inside the capability they have been given. Read access, reversible creation, external changes and high impact actions remain distinct risk classes.
On the roadmapยท 0.9 Agents
Capability scope
How it is designed to work.
- Permission model
- Sandboxed execution
- Approval gates
- Audit trail
- Tool and MCP surface
- Scoped autonomy
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.