English 
Français 
Español 
Deutsch 
Português 
Italiano 
العربية AI AGENT
AI agent reasoning grounded in IoT data
Reason across live telemetry, historical sensor data, site context, and operating policy.
Kilo Physical AI Platform
The Physical AI platform for safe AI agent device control.
Kilo is the reliable, scalable IoT execution server between AI agents and real-world devices—normalizing sensor data, governing commands, and returning consistent, verifiable results.
MCP · REST · gRPC · Built-in AI · Cloud or on-premise
KILO EXECUTION
LIVE AI INTENT
“Keep this cold room below 4°C without creating a false alarm.”
01 ✓
Live IoT context loaded
Temperature, door state, command definitions, and recent history
02 ✓
IoT automation simulated
Trigger and non-trigger readings tested; side effects captured
03 ✓
AI-proposed change approved and deployed
Versioned build enters production after confirmation
04 ✓
Device command verified
Controller response and outcome retained in execution history
Consistent IoT data. Controlled device action. Verifiable physical result.
Physical AI infrastructure
Why AI agents need a Physical AI infrastructure layer
AI agents can reason, but controlling real-world devices carries consequences. Kilo handles IoT protocols, live device state, permissions, failure paths, and operational evidence that a language model should never have to improvise.
SAFE DEVICE CONTROL
Governed AI device control
Expose consistent device capabilities, enforce boundaries, execute the command, and return the verified result.
OBSERVE
The physical world
- Sensors and meters
- Machines and actuators
- Buildings and fleets
- Video — coming soon
For AI model companies and agent platforms
Physical AI infrastructure for AI model companies and agent platforms
Kilo gives teams building general-purpose intelligence a mature physical-world control layer they can integrate instead of rebuilding: one professional platform for heterogeneous IoT devices, safe execution, and enterprise operations.
01
Add real-world capabilities to AI agents
Let models observe and operate sensors, machines, buildings, fleets, and future robotic systems through one integration.
02
Abstract years of IoT platform complexity
Kilo already handles protocols, device models, multi-tenancy, deployment, monitoring, failure states, and real-world command delivery.
03
Protect trust at the device-control boundary
Simulation, approvals, typed commands, verification, execution history, and rollback turn AI intent into governable physical operations.
Safe AI device control
Safe AI device control from request to recorded outcome
Kilo governs the complete Physical AI control loop. The AI agent does not connect around your operational controls.
01
Observe IoT data
Read normalized telemetry and live device state.
02
Reason with context
Ground the AI decision in real operations.
03
Simulate automation
Test logic and capture side effects safely.
04
Approve the action
Apply permissions and human confirmation.
05
Control the device
Run typed commands or deployed IoT rules.
06
Track delivery state
Follow the command lifecycle and keep the record.
07
Record and roll back
Keep execution history and restore known-good logic.
Physical AI example
Physical AI example: safe cold storage automation
“Keep this cold room below 4°C without creating a false alarm.”
The AI agent request is accepted inside the operator’s organization and permission scope.
Consistent IoT data. Controlled device action. Verifiable physical result.
01
Live IoT context loaded
Temperature, door state, command definitions, and recent history
02
IoT automation simulated
Trigger and non-trigger readings tested; side effects captured
03
AI-proposed change approved and deployed
Versioned build enters production after confirmation
04
Device command verified
Controller response and outcome retained in execution history
Production controls
Enterprise AI device control with simulation, audit trails, and rollback
Physical actions need more than a clever model. Kilo supplies the controls between a request and a real device.
01
Permission inheritance
An agent can never see or change more than the signed-in user is allowed to.
02
Human confirmation
Consequential and destructive changes pause for explicit approval.
03
Test before deploy
Rules are validated and simulated before they touch live infrastructure.
04
Version and rollback
Every automation change is versioned and a known-good build is one click away.
05
Typed, verified commands
Parameter bounds constrain actions; optional verification confirms the device responded.
06
Forensic history
Commands, deployments, permission changes, and outcomes remain auditable.
MCP and IoT APIs
Connect AI agents to IoT devices through MCP, REST, and gRPC
Use Kilo with OpenAI, Anthropic, another MCP-capable AI agent, the built-in assistant, or your own services. Every integration works against the same digital device models, IoT data, permissions, and organization boundary.
INSIDE KILO
The built-in AI Assistant
Ask about live and historical telemetry, provision devices, build and simulate rules, and configure alarms in plain language.
- ✓Grounded in your live deployment
- ✓Confirms consequential changes
- ✓Bring OpenAI, Anthropic, Ollama, or a compatible model
YOUR AI CLIENT
Any MCP-capable agent
Connect ChatGPT, Claude, Codex, Cursor, or another MCP client. Sign in with your Kilo account; the agent inherits exactly your permissions.
- ✓OAuth sign-in — no token copying
- ✓Organization-scoped access
- ✓Open Streamable HTTP endpoint
Proof, not a mock-up
What connecting your own AI client actually looks like
A Claude Code session signed in to a live Kilo organization over MCP. It is asked to configure a LoRaWAN distance sensor, recommends provisioning through the platform rather than driving the browser, calls a real Kilo tool, and stops for permission before continuing.
Enterprise Physical AI platform
Scalable enterprise IoT infrastructure for Physical AI
Production AI device control needs durable, secure IoT infrastructure—not a collection of fragile demo integrations.
GO
Go-based IoT server core
A deliberately designed service architecture built for concurrent, real-time IoT operations.
HA
Scalable Physical AI operations
Fault-tolerant cloud operation, durable data, and deployment from pilot to multi-site device fleets.
ABAC
Enterprise AI agent isolation
Fine-grained permissions and strict organization boundaries govern every connected AI client.
CLOUD / ON-PREM
Cloud or on-premise IoT platform
Use managed Kilo Cloud or retain infrastructure control with an on-premise IoT Server.
MULTI-PROTOCOL
One model for heterogeneous IoT devices
LoRaWAN, mioty, MQTT, cellular, APIs, and gateways converge into consistent device state.
NO LOCK-IN
AI model and IoT hardware choice
Bring your devices, connectivity, and preferred AI provider without rebuilding the control layer.
Built for operations
Physical AI use cases across buildings, industry, fleets, and agriculture
CO₂ · LEAKS · ENERGY · ACCESS
Facilities and buildings
Understand conditions across sites, coordinate alarms, and command connected HVAC, valves, gates, and controls.
VIBRATION · POWER · UPTIME
Factories and infrastructure
Reason across vibration, temperature, power, and machine state before a rule or operator takes action.
GPS · CAN · TEMPERATURE
Fleets and mobile assets
Combine position, vehicle telemetry, geofences, and alerts across thousands of tracker models.
WATER · SOIL · WEATHER · TANKS
Environment and agriculture
Operate remote sites where batteries last for years and there is no Wi-Fi or mains power.
The next input layer · Coming soon
Physical AI video monitoring with Kilo Lens
Organize supported RTSP and ONVIF cameras across sites, recordings, motion zones, videowalls, and scoped access — next to the sensors and device state Kilo already understands.
Preview Kilo Lens→Physical AI platform
Physical AI platform and AI device control FAQ
What is a Physical AI platform?+
A Physical AI platform connects AI reasoning to sensors, machines, and connected infrastructure. Kilo supplies normalized IoT data, digital device models, governed commands, automation, verification, and audit history so AI agents can observe and act in the real world.
How can AI agents control IoT devices safely?+
Kilo applies the signed-in user’s permissions, typed command parameters, approval gates, tested and versioned rules, execution history, device-response verification, and rollback before or after an AI-proposed physical action.
How does an IoT MCP server connect AI to physical devices?+
Kilo’s MCP server exposes authorized IoT data and device tools to compatible AI clients through OAuth. The client works with consistent device models and remains inside the user’s organization and permission scope.
Can ChatGPT or Claude control devices through Kilo?+
Yes. ChatGPT, Claude, Codex, Cursor, or another MCP-capable client can connect to Kilo, subject to client support and your Kilo permissions. OpenAI, Anthropic, Ollama, and compatible models can also power the built-in assistant.
Is Kilo a robotics platform?+
Kilo is the governed Physical AI and IoT execution layer behind connected systems. Robots and controllers can integrate through supported protocols and APIs while Kilo handles telemetry, permissions, automation, commands, verification, and auditability.
Connect AI agents to real-world devices with Kilo.
Connect through MCP, evaluate the Physical AI platform with five IoT devices, or design an enterprise architecture with us.
Read the developer docs →