Agent Platform
Agent Platform is the deployment layer of the Menlo Stack. It is the platform for packaging, permissioning, and deploying AI agents to humanoid robots.
Why We Built Agent Platform
Traditional robotics treats autonomy as a tightly engineered program. Menlo treats autonomy as an agent payload:
- packaged,
- permissioned,
- constrained by safety envelopes,
- deployed with rollbacks and versioning,
- observable through operational telemetry.
This is a software-native approach to embodied systems. The core idea is that robustness is achieved through iteration, and iteration can only be fast if deployment is standardised.
What Agent Platform Provides
Packaging
Agents are packaged as deployable payloads, not custom integrations. An agent developed in any standard framework can be deployed to compliant humanoid hardware without modification.
Permissioning
Agents operate within defined safety envelopes. Permissioning ensures agents cannot exceed safe operational boundaries, protecting hardware and humans alike.
Safety Envelopes
Every agent deployment includes:
- Velocity and acceleration limits
- Workspace boundaries
- Force and torque constraints
- Emergency stop integration
Versioning and Rollbacks
Agent versions are tracked throughout deployment. If an issue arises, rollbacks restore previous versions instantly—no reengineering required.
Observability
Operational telemetry captures agent behavior, outcomes, and edge cases. This data feeds back into Uranus and Cyclotron for continuous improvement.
The Deployment Loop
Agent Platform enables the tight Menlo deployment loop:
- Define agent in standard framework
- Validate in Uranus simulation
- Refine skills in Cyclotron if needed
- Deploy to Asimov via Agent Platform
- Capture telemetry for improvement
- Iterate and redeploy
Integration
Agent Platform connects:
- Uranus: Validates agents before deployment
- Cyclotron: Trains motor skills as needed
- Data Engine: Streams telemetry for continuous improvement
- Asimov: Executes agents on physical hardware