Beta These tools are in active development. Try them out and share your feedback.
Open Source · MIT License

Modern tools for building energy simulation

A suite of open-source tools for EnergyPlus — from a Python library to a visual web editor to AI integration. Everything you need to model, simulate, and optimize building energy performance.

4000x Faster lookups
55k+ Weather stations
25 AI tools via MCP

Three layers.
One mission.

From Python scripting to visual editing to AI-powered workflows — choose the layer that fits your needs.

Core Library

idfkit

A fast, modern Python toolkit for EnergyPlus with O(1) lookups, automatic reference tracking, and zero dependencies.

  • O(1) dictionary-based object indexing
  • Live cross-object reference graph
  • IDF + epJSON dual format support
  • 3D geometry & thermal calculations
  • Sync, async & batch simulation
  • EnergyPlus 8.9 through 25.2
pip install idfkit
View on GitHub
AI Integration

idfkit-mcp

An MCP server that exposes building energy modeling to AI agents. Let Claude author, validate, and simulate EnergyPlus models.

  • 25 MCP tools for full workflow
  • Schema discovery & validation
  • Model authoring & modification
  • Weather station integration
  • Simulation execution & results
  • stdio & HTTP transport modes
uvx idfkit-mcp
View on GitHub

Built for performance.
Designed for humans.

Legacy tools hold you back. idfkit is built from the ground up for speed, correctness, and developer experience.

4,000x faster

O(1) dictionary-based lookups vs linear scans. On a 1,700-object IDF, idfkit is 4,000x faster than eppy.

Reference tracking

Automatic live graph of cross-object relationships. Rename a zone and every reference updates instantly.

Zero dependencies

Core library uses only the Python standard library. Optional extras for pandas, plotting, and cloud storage.

3D geometry

Built-in Vector3D and Polygon3D classes. Calculate surface areas, zone volumes, and coordinate transforms natively.

55,000+ weather stations

Search by location or coordinates. Download EPW and DDY files. Inject design days automatically.

AI-native

MCP server with 25 tools lets AI agents author, validate, and run energy simulations autonomously.

Up and running
in seconds.

quickstart.py
# Install
pip install idfkit

# Load a model
from idfkit import load

model = load("building.idf")

# O(1) lookup by name
zone = model["Zone"]["Office_Floor_1"]

# Automatic reference tracking
zone.name = "Main_Office"
# ^ All referencing objects update automatically

# Run simulation
results = model.simulate()
print(results.summary())
claude_desktop_config.json
// Add to your Claude MCP config
{
  "mcpServers": {
    "idfkit": {
      "command": "uvx",
      "args": ["idfkit-mcp"]
    }
  }
}

// Then ask Claude:
// "Create an office building model
//  with 3 zones and run an annual
//  simulation for Denver, CO"
No installation needed
# Envelop runs entirely in your browser

1. Open Envelop in any modern browser
2. Import an IDF or start from scratch
3. Design HVAC systems visually
4. Edit schedules with intuitive UI
5. View 3D geometry in real-time
6. Simulate with in-browser EnergyPlus

# Powered by WebAssembly
# No server required
# Works offline

Help shape the future
of energy modeling.

All three tools are in active beta. We'd love for you to try them and let us know what's working and what isn't.

idfkit

Core Python library

Report an Issue

Envelop

Web-based visual editor

Report an Issue

idfkit-mcp

AI integration via MCP

Report an Issue

Have a feature request or general feedback?