EnerOS
Rust · Power-Native · AgentOS

Converge Energy
Orchestrate Intelligence

EnerOS is a power-native Agent Operating System for the electric power and energy domain.
It embeds power system domain knowledge, physical constraints, and operational logic as OS kernel primitives,
enabling AI Agents with native understanding, safe decision-making, and autonomous action capabilities in energy scenarios.

0
Core Crate Modules
0
Roadmap Phases
0
Design Principles
0
Application Scenarios
Scroll Down

Why EnerOS?

General-purpose Agent frameworks face fundamental challenges in the power and energy domain. AI Agent technology is reshaping industries at an unprecedented pace, yet the power and energy domain faces unique challenges — safety constraints are degraded to prompt-level suggestions, and grid topology and electrical coupling relationships are ignored.

Physics Blindness

Agents don't understand physical quantities like power flow, voltage, and frequency, unable to judge the physical feasibility of decisions.

Missing Constraints

Safety constraints (N-1, thermal stability, voltage limits) are treated as "prompts" rather than system-level guarantees.

Topology Agnostic

Agents treat the grid as flat data, unable to perceive topology structure and electrical coupling.

Temporal Disconnect

Power systems are strongly time-coupled; general frameworks lack first-class support for the temporal dimension.

Device Heterogeneity

Transformers, circuit breakers, and inverters each have independent models and protocols, making unified scheduling difficult.

EnerOS's Answer

Don't "bolt on" power knowledge to general frameworks — build an OS power-natively from the ground up.

Design Philosophy

Six core design principles defining the foundational paradigm of a power-native Agent OS.

01

Power-Native First

电力原生优先

Power topology, power flow computation, and device models are not bolt-on plugins but native OS abstractions. Agents run on a physical world model of the grid from inception.

02

Agent-as-Grid-Node

智能体即电网节点

Each Agent corresponds to a functional node in the grid (substation, feeder, device), inherently possessing topology awareness and constraint compliance. Inter-Agent communication mirrors information exchange between grid nodes.

03

Constraint as Kernel Law

约束即内核法律

Safety constraints (N-1 verification, thermal stability, voltage limits) are enforced by the kernel — no Agent decision can exceed the physically feasible domain. Safety is not a prompt; it's an OS-level hard constraint.

04

Time-Series Native

时序原生

Power systems are strongly time-coupled. EnerOS treats the temporal dimension as a first-class citizen, supporting native operations for real-time data streams, historical lookback, and predictive inference.

05

Real-Time Determinism

实时确定性

Power systems have rigid real-time requirements. EnerOS adopts a dual-execution architecture: the general execution domain handles Agent orchestration and AI inference, while the real-time execution domain guarantees deterministic latency for protection logic and switching operations. The safety domain cannot be blocked by the general domain.

06

Open & Interoperable

开放与互操作

Standardized Agent communication protocols and device access specifications enable plug-and-play for heterogeneous energy devices and multi-vendor systems.

System Architecture

Dual-execution architecture: General Domain + Real-Time Domain. The system is partitioned into two execution domains, balancing complex AI inference computation with hard real-time guarantees for grid control.

General Execution Domain General Domain
Agent Runtime
AI Inference Engine
Planning & Optimization
Human-Machine Interaction
Non-deterministic · Latency: seconds to minutes
Real-Time Safety Gateway
RT Safety Gateway
Cross-domain communication · Command dispatch · State sync · Priority arbitration · Constraint verification
Real-Time Execution Domain Real-Time Domain
Relay Protection Logic
Switching Operation Execution
Fault Isolation
Frequency Regulation
Deterministic · Latency: microseconds to milliseconds
🛡️

Safety domain cannot be blocked by general domain

Real-time domain tasks have the highest priority; no general domain operation may affect real-time execution determinism.

➡️

One-Way Trust

The real-time domain can directly read decision commands from the general domain, but the general domain cannot directly interfere with real-time domain scheduling.

🔒

Cross-Domain via Gateway

All general→real-time domain commands must pass through the gateway's constraint verification and priority arbitration.

Fault Degradation

When the general domain fails, the real-time domain automatically switches to local protection logic, ensuring grid safety doesn't depend on AI.

Layered Architecture Overview

A five-layer architecture from application to infrastructure, clearly separating responsibilities and abstraction levels.

Application Layer Application Layer
Dispatch Agent Operation Agent Planning Agent Trading Agent Fault Diagnosis Load Forecasting Energy Efficiency
Agent Runtime Layer Agent Runtime
Lifecycle Management Memory Storage Tool Engine Multi-Agent Collaboration Reasoning Engine Safety Guard Grid-Aware Context Injection
Power-Native Kernel Power-Native Kernel
Topology Engine (Graph Model) Power Flow Engine (PF/OPF) Constraint Executor (N-1/Thermal/Voltage) Equipment Model Library (IEC/GB) Time-Series Engine Event Bus
RT Safety Gateway RT Safety Gateway
Cross-Domain Comm Command Dispatch State Sync Priority Arbitration Constraint Verification
Infrastructure Layer Infrastructure
Relay Protection Switching Ops Fault Isolation Freq Regulation GOOSE SCADA IEC 61850 IEC 104 MQTT Modbus OPC UA

Core Capabilities

Six core capabilities that make Agents natively "understand power".

Grid Topology as First-Class Citizen

The grid topology graph is EnerOS's core data structure. Agents automatically acquire electrical relationships, upstream/downstream devices, and operational status of their node through topology-aware context — no explicit queries needed.

Physics-Constrained Decisions

All Agent decision outputs undergo constraint verification by the power-native kernel — whether power flow converges, voltage exceeds limits, or lines are overloaded. Decisions failing physical constraints are rejected at the kernel level.

Equipment Model Library

Built-in equipment parameter library compliant with Chinese national standards (GB) and IEC standards, covering transformers, lines, switches, inverters, and other core equipment types, with pandapower-compatible format support.

Multi-Agent Collaboration

Grid topology-based Agent organization model: Agents within the same substation automatically form collaboration groups; cross-substation Agents communicate structurally via topology paths, avoiding global broadcast chaos.

Time-Series Native Operations

Real-time data streams, historical lookback, predictive inference — three temporal modes unified at the kernel level. Agents seamlessly switch between "review-perceive-predict" temporal perspectives.

Safety Guard

Kernel-level safety guard: N-1 security verification, thermal stability check, voltage limit detection. Safety constraints cannot be bypassed or degraded by Agents — they are the "hard laws" of the operating system.

Crate Index

A modular system of 12 Rust Crates, each with clear responsibilities, loosely coupled and highly cohesive. Built on Rust for memory safety and high performance.

eneros-corecrates/eneros-core/

Unified types, errors, config

EnerOSErrorPowerSystemStateElementId
eneros-topologycrates/eneros-topology/

Grid topology graph modeling & analysis

NetworkGraphTopologyEngineBusBranch
eneros-powerflowcrates/eneros-powerflow/

Newton-Raphson power flow solver

PowerFlowSolverYBusMatrixJacobianMatrix
eneros-constraintcrates/eneros-constraint/

Safety constraint verification & enforcement

ConstraintEngineViolationResponseStrategy
eneros-equipmentcrates/eneros-equipment/

Equipment parameter model library

EquipmentModelTransmissionLineTwoWindingTransformer
eneros-timeseriescrates/eneros-timeseries/

Time-series data storage & query

TimeSeriesEngineTimeSeriesQueryAggregation
eneros-eventbuscrates/eneros-eventbus/

Event-driven communication bus

EventBusEventEventHandler
eneros-gatewaycrates/eneros-gateway/

Safety gateway & command control

SafetyGatewayCommandSafetyCheckCommandPriority
eneros-devicecrates/eneros-device/

Device communication & protocol adaptation

ProtocolAdapterDeviceManagerHealthMonitor
eneros-apicrates/eneros-api/

CLI / HTTP API service

ApiServerApiClientApiResponse
eneros-bridgecrates/eneros-bridge/

Python bridge (cnpower/pandapower)

PythonBridgeCnpowerEquipmentLoader
eneros-networkcrates/eneros-network/

Topology-powerflow unified pipeline (planned)

coming soon

Application Scenarios

Intelligent application scenarios covering the full lifecycle of power and energy.

Intelligent Dispatch Dispatch Agent

Day-ahead / intra-day / real-time dispatch based on load forecasting and renewable generation, achieving optimal balance between economics and safety.

🔧

Intelligent Operations Operation Agent

Equipment condition monitoring, fault diagnosis, and maintenance decisions — shifting from reactive repair to predictive maintenance.

📐

Distribution Planning Planning Agent

Network expansion and equipment selection under load growth forecasting, supporting new power system construction.

💹

Power Trading Trading Agent

Spot market bidding strategies and settlement analysis, adapting to the wave of power market reform.

🛡️

Self-Healing Self-Healing Agent

Fault location, isolation, and non-fault area power restoration — millisecond-level response improving supply reliability.

🌱

Energy Efficiency Energy Agent

Energy optimization and demand response for commercial and industrial users, supporting dual carbon goals.

Uniquely Positioned

EnerOS leads simultaneously across three dimensions: power physics modeling, AI nativeness, and safety constraints.

Dimension
General Agent Framework
SCADA / EMS
EnerOS
Power Physics Modeling
None / Bolt-on
Deep but Closed
Native Kernel
AI Agent Support
Native
None
Native
Safety Constraint Guarantee
Prompt-level
Hard-coded
Kernel-level Enforcement
Topology Awareness
None
Yes
Agent-Native Awareness
Multi-Agent Collaboration
General Protocol
None
Topology-Structured Collaboration
Openness
High
Low
High (Plugin Architecture)
Equipment Model Standards
None
Vendor Proprietary
IEC / GB Standards

Quick Start

Built on Rust, start in a few commands. Prerequisites: Rust 1.70+ and Cargo.

bash — EnerOS
$ # Clone repository
$ git clone https://github.com/Gawg-AI/EnerOS.git
$ cd EnerOS
$ # Build project
$ cargo build --release
Compiling eneros-core ...
Compiling eneros-powerflow ...
Finished release [optimized]
$ # Start API server
$ cargo run --bin eneros -- serve --host 0.0.0.0 --port 8080
EnerOS API listening on 0.0.0.0:8080
$ # Run power flow
$ cargo run --bin eneros -- power-flow --case ieee14
✓ Power flow converged in 4 iterations

Evolution Roadmap

14 phases of continuous evolution, from kernel foundation to deterministic decision loop.

01
Phase 1

Kernel Foundation

Topology engine, power flow kernel, equipment model library

02
Phase 2

Agent Runtime

Agent lifecycle management, memory system, tool engine

03
Phase 3

Grid-Aware Context

Topology-aware injection, constraint verification guard, event bus

04
Phase 4

Multi-Agent Collaboration

Multi-agent collaboration protocol, topology-structured communication

05
Phase 5

Infrastructure Adapters

SCADA / IEC 61850 / IEC 104 / MQTT protocol adapters

06
Phase 6

Domain Applications

Dispatch Agent, Operation Agent, Self-Healing Agent, domain collaboration protocol

07
Phase 7

Real-Time Loop & System Integration

SCADA data pipeline, DC-OPF, state estimation, web dashboard

08
Phase 8

Deep Integration & Production

E2E integration tests, ApiClient real HTTP, SQLite persistence

09
Phase 9

Real Bug Fixes & Shell Elimination

Deadlock fix, SelfHealingAgent interlock verification, clippy zero warnings

10
Phase 10

Accuracy Verification & LLM Integration

IEEE 14-bus accuracy verification, LlmReasoningEngine, degradation fallback

11
Phase 11

rig Tool Materialization & Unified Reasoning

rig-core 0.38 integration, 4 power system tools materialized, unified reasoning engine

12
Phase 12

Real-Time Execution Domain

Priority command queue, real-time executor, watchdog timeout protection

13
Phase 13

Constraint-Driven Deterministic Decision Pipeline

Structured action output, feasibility projection, 3-stage decision pipeline, feedback re-reasoning

14
Phase 14

Closing the Deterministic Decision Loop

Eliminate "phantom loops", FeedbackLoop integration, 5 end-to-end closed-loop integration tests

Future Trends

From energy internet to embodied agents, EnerOS defines the intelligent foundation for next-generation power systems.

Trend 01

New Power Systems

High penetration of renewables and power electronics brings fundamental grid transformation. Source-grid-load-storage coordinated control, virtual power plant aggregation, and microgrid autonomy will become the norm, urgently requiring agents that natively understand power physics to manage increasingly complex grids.

Trend 02

Energy × Large AI Models

Deep fusion of large language models and domain reasoning engines, evolving from "knowledge retrieval" to "autonomous decision-making". LLMs provide intent understanding and natural language interaction, while EnerOS kernel provides physically feasible domain guarantees — together realizing trustworthy energy agents.

Trend 03

Energy Internet

Multi-energy coupling of electricity, gas, heat, and transport — energy systems evolving toward internet architecture. EnerOS's graph-native architecture naturally fits multi-energy network topology modeling, providing a unified foundation for cross-energy-type intelligent scheduling.

Trend 04

Dual Carbon & Power Market

Dual carbon goals drive deep energy restructuring; national unified power market construction accelerates. EnerOS's Trading Agent and Planning Agent will become the most active intelligent participants in the new power market.

Trend 05

Embodied Agents

From "software Agents" to "embodied Agents" — inspection robots, smart switchgear, and autonomous maintenance equipment will become embodied agents in the grid. EnerOS's Agent-as-Grid-Node paradigm natively supports intelligent integration of physical entities.

Trend 06

OS-Level Intelligent Foundation

Just as Linux is to the internet and Android is to mobile, EnerOS aims to be the OS foundation of the energy intelligence era — a universal platform enabling thousands of energy agents to collaborate safely, efficiently, and natively.

Technical Principles

Five core principles at the engineering implementation level.

Kernel-User SeparationPhysical constraints execute in kernel layer, Agent logic in user layer, clear safety boundary
Graph-CentricGrid topology graph is the system's core index; all operations revolve around graph structure
Event-DrivenEvent bus-based async architecture, adapting to power system real-time response needs
Plugin ArchitectureDevice protocols, solvers, and Agent capabilities all plug in, extensible
Standards ComplianceCompliant with IEC 61850 / IEC 60870-5-104 / GB series standards

Make Agents Natively Understand Power

Build an OS power-natively from the ground up. Converge Energy, Orchestrate Intelligence.