Open MEP building state that a language model can reason about and edit correctly — grounded in deterministic loads and duct sizing, graded by a deterministic checker.
The bet: the useful unit of AI-assisted HVAC design is not a Revit plugin but a small, inspectable data model (rooms, loads, terminals, ducts, connectivity, constraints) that deterministic engines compute over and agents edit. This repo is that model, the engines, and the harness that measures whether an agent can edit it without breaking it.
Workspace | What it does |
| Dependency-free equal-friction round-duct sizing, supply/return/exhaust network CFM propagation, port-coincidence connectivity, ASHRAE equivalent diameters, and actual-vs-recommended size grading. |
| MCP server ( |
| Sizes and checks HVAC in Pascal Editor scenes, live through Pascal's MCP ( |
| Agent skill (Pascal skills.sh format) that drives the adapter from an MCP-connected agent: gather CFM, set |
| Synthetic T1–T6 mechanical-plan editing benchmark (single + branching fixture sets), deterministic grader, |
| IFC ingestion (web-ifc): storeys, spaces, elements, space boundaries, geometric envelope recovery; 2D plan extraction (Clipper2 footprints); design-day cooling/heating loads (ASHRAE 62.1 ventilation, 90.1 assemblies); mechanical plan layers with CFM-grounded terminals and inferred duct connectivity; plan validator; headless eval runner. |
| Next.js 16 viewer: 3D (That Open / Three.js) and storey-driven 2D plan mode with the load dashboard. |
|
|
Real-model tests and evals run on public IFC fixtures (buildingSMART
Duplex and WBDG Office ARCH + MEP pairs, CC BY 4.0) fetched by
fixtures/fetch-public-ifc.sh; see fixtures/README.md for provenance and the
exporter quirks the pipeline handles. No IFC is committed to this repository.
Related MCP server: EPANET MCP Server
claude mcp add openmep -- npx -y -p @openmep/mcp openmep-mcpAny MCP client works ({"command": "npx", "args": ["-y", "-p", "@openmep/mcp", "openmep-mcp"]}).
Describe the system in plain language, with the CFM each terminal needs, and the
agent calls the engine; see packages/mcp/README.md.
npx -p @openmep/hvac-domain openmep-hvac size packages/hvac-domain/examples/furnace-two-registers.items.json --pretty
npx -p @openmep/hvac-domain openmep-hvac duct --cfm 250 --role main --diameter-in 6From a checkout: npm ci && npm run build --workspace @openmep/hvac-domain, then
node packages/hvac-domain/bin/openmep-hvac.js ....
The network is a list of equipment, fittings, terminals with engineer-supplied
requiredCfm, and segments linked by connectedItemRefs. The result lists each
run's system, CFM, role, recommended standard round diameter, velocity and friction
rate, grades any existing section as ok/undersized/oversized, and reports
terminals with no airflow or no path to equipment. Any host that can produce this
document gets the same engine; openmep-pascal items produces it from a Pascal
scene.
cd examples/manual-d-demo && npm install && node demo.mjsTakes blower external static, device losses, and one line per run (CFM,
length, fitting equivalent length) and prints available static, total effective
length, the Manual D friction rate, and a round size per run, graded against the
size you already have. Ships with the ACCA worksheet example; see
examples/manual-d-demo/README.md for what it does and does not do.
Change a room's supply airflow, preview the connected duct sizes on the plan, apply or undo the change, and export the edited plan JSON.
npm ci
npm run dev:design
# Open http://localhost:3001/designRequires Node.js 24+. The first launch fetches the public Office IFC pair and
prepares Level 1; no database, .env, or model credentials are needed. Pass
-- --refresh to rebuild the example, or -- --port 3002 to use another port.
Edits are session-local manual airflow scenarios with round-duct proposals;
export saves the applied plan JSON, not a rewritten IFC. The public example
labels its inferred connections and assumed initial demands. Existing model
viewers also link to Airflow design for their selected storey.
npm ci
fixtures/fetch-public-ifc.sh # duplex + wbdg_office (~55 MB)
npm run build --workspace @openmep/hvac-domain --workspace @openmep/agent-benchmark
npm testMaterialize an editable HVAC plan from the public office model:
npm run eval:materialize -- \
--arch fixtures/public/wbdg_office/arc.ifc \
--mech fixtures/public/wbdg_office/mep.ifc \
--model-id wbdg_office
# eval-runs/wbdg_office/Level_1/{architecture,loads,mechanicalVisual2D,mechanicalEdit2D,baseline}.jsonRun the synthetic agent benchmark: npm run benchmark:verify, or see
packages/agent-benchmark/README.md for grading your own candidates.
Copy .env.example to .env; start PostgreSQL and create the database.
npm run db:init
npm run dev:web — seeds the Duplex pair as a stable dev fixture at
/models/00000000-0000-4000-8000-000000000001?mode=plan
(MEP_SKIP_DEV_FIXTURE=1 to skip; IFC_FIXTURE_DIR to relocate fixtures).
npm run dev:worker in a second terminal.
Loads are design-day, steady-state (no RTS/CTS lag, latent, or schedules) and not yet validated against a reference case; envelope U-values come from ASHRAE 90.1 prescriptive tables, climate from 15 city anchors. Treat outputs as preliminary sizing inputs, not a sealed design.
Roof loads are zero for Revit exports whose ceilings are room-bounding (all seen so far); plenum inference is open work.
Duct connectivity for exports without IfcRelConnectsPorts is inferred
geometrically and flagged as such on every item.
MIT — see LICENSE. Fixture data keeps its upstream licenses (fixtures/README.md).
Release and provenance rules for the npm packages: docs/public-artifact-release.md.
Recommend a standard round diameter for one duct run carrying a given CFM, with velocity and friction at that size. Optionally grade an existing round, rect, or oval section as ok, undersized, or oversized.
| Name | Required | Description | Default |
|---|---|---|---|
| cfm | Yes | Airflow the run carries, CFM. | |
| role | No | main (at equipment), branch (serves several terminals), or runout (one terminal). Default main. | |
| existing | No | Existing section to grade: { diameterIn } for round, or { shape: rect|oval, widthIn, heightIn }. | |
| airflowType | No | System, which sets the velocity cap. Default supply. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description still adds real value by disclosing output content — recommended diameter, velocity, friction, and the ok/undersized/oversized grade — which is not available elsewhere since there is no output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tightly written sentences with no filler. The primary recommend behavior is front-loaded, and the optional grading capability follows immediately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description carries the burden of explaining what comes back, and it does so (diameter, velocity, friction, grade verdict). Defaults for role and airflowType live in the schema, so nothing critical is missing, though the sizing standard/basis is left unstated.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all four parameters are already documented in the schema, including the role and airflowType enums and the existing-section shapes. The description adds the grading vocabulary (ok/undersized/oversized) but no syntax or format detail beyond the schema, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (recommend/grade) and resource (one duct run) with clear scope. The phrase 'one duct run' implicitly contrasts with the sibling size_duct_network, but the sibling is never named, so an agent must infer the boundary.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description signals two modes of use: recommend a size from CFM, or grade an existing section via the 'existing' input. This implies when the grading path applies, but there is no explicit when-not guidance or named alternative (e.g., use size_duct_network for a whole system).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Size every supply, return, exhaust, and outside-air segment of a connected duct network. Each terminal's requiredCfm is carried along its shortest same-system path to equipment and summed per segment; roles (main/branch/runout) are inferred. Sizes at the fixed default friction rate, or, when fan is given with segment lengthFt and fitting equivalentLengthFt, at the Manual D friction rate derived from available static pressure over the total effective length (returned as design: ASP, TEL, friction rate, longest paths). Returns per-segment recommendations, grades for segments with an existing section, and findings: missing-required-cfm, no-equipment-path, dangling-reference, mixed-system-segment, undersized, oversized, friction-rate-out-of-range, missing-equivalent-length.
| Name | Required | Description | Default |
|---|---|---|---|
| fan | No | Blower data. When given, friction rate = (externalStatic − Σ componentLosses) × 100 / total effective length (longest supply + longest return effective path). | |
| items | Yes | Every terminal, segment, fitting, and equipment item in the network. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With annotations already covering the safety profile (readOnly, idempotent, non-destructive, closed-world), the description still goes well beyond them: it explains the path-tracing rule ('requiredCfm carried along its shortest same-system path'), role inference, the friction-rate formula inputs, and enumerates every finding code emitted. That is unusually rich behavioral disclosure for a computation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the purpose and efficient overall, with each clause carrying information (network scope, algorithm, friction-rate modes, outputs, findings). The long trailing findings inventory is dense but earns its place by telling the caller what failure signals to expect.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description carries the return-value burden and does so fully: per-segment recommendations, grades for existing sections, design ASP/TEL/friction-rate/longest paths, and the complete findings taxonomy. For a nested, two-parameter computational tool this is complete enough to call correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3, but the description adds real meaning by tying parameters into modes: terminals' requiredCfm drives the flow sum, and 'fan' together with lengthFt/equivalentLengthFt switches on the Manual D calculation and returns design ASP/TEL. That joint requirement is more than the per-field schema docs convey.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource ('Size every supply, return, exhaust, and outside-air segment of a connected duct network') and adds the algorithm used, so the agent knows exactly what is produced. It does not, however, differentiate itself from the sibling 'size_duct', leaving the boundary between whole-network and single-run sizing to inference.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives a clear conditional on which sizing mode applies: fixed default friction rate by default, or Manual D friction rate when 'fan is given with segment lengthFt and fitting equivalentLengthFt'. That is actionable context, though it never names when to prefer this tool over 'size_duct' or when the tool is inappropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.1size_duct_network3 fields changedInput schema / properties / fanAdded value: +{
+ "description": "Blower data. When given, friction rate = (externalStatic − Σ componentLosses) × 100 / total effective length (longest supply + longest return effective path).",
+ "properties": {
+ "componentLossesInWg": {
+ "additionalProperties": {
+ "minimum": 0,
+ "type": "number"
+ },
+ "description": "Device pressure drops outside the duct runs by name (coil, filter, supply-outlet, return-grille, damper), in. w.g.",
+ "propertyNames": {
+ "type": "string"
+ },
+ "type": "object"
+ },
+ "externalStaticInWg": {
+ "description": "Blower external static pressure at design airflow, in. w.g.",
+ "exclusiveMinimum": 0,
+ "type": "number"
+ }
+ },
+ "required": [
+ "externalStaticInWg"
+ ],
+ "type": "object"
+}Input schema / properties / items / items / properties / equivalentLengthFtAdded value: +{
+ "description": "Fittings and terminals: equivalent length of straight duct for the fitting's loss, feet (Manual D style). Counted in effective length when fan is given.",
+ "minimum": 0,
+ "type": "number"
+}Input schema / properties / items / items / properties / lengthFtAdded value: +{
+ "description": "Segments only: measured length in feet. Required on sized segments when fan is given.",
+ "minimum": 0,
+ "type": "number"
+}v0.1.0size_ductsize_duct_networkScored across 2 tools
The tools operate at different scopes: size_duct handles a single duct run, while size_duct_network sizes an entire network with multiple segments. The names are similar but the descriptions clearly differentiate their purposes, making confusion unlikely for an agent.
Both tool names follow a consistent verb_noun pattern (size_duct, size_duct_network). The only minor issue is that the noun part is very similar, but the naming convention itself is consistent.
With only 2 tools, the server is quite thin for a duct sizing domain. While each tool is well-scoped, the limited count may force agents to rely on external knowledge for common tasks like equipment selection or duct material properties.
The surface covers core duct sizing operations but lacks obvious complementary tools such as equipment selection, pressure loss calculations for fittings beyond equivalent length, or output formatting. Notably, there is no tool to retrieve or list existing duct networks, which could be a gap for iterative design workflows.
Heating, ventilation and energy engineering calculations and diagnostics for AI agents.
Design, solve and simulate HVAC systems from real components, weather years and buildings.
Construction takeoff and estimating for AI agents. Measure a drawing PDF, export a priced estimate.
Solar, weatherization, EV charging, battery and heat-pump decision tools for AI agents.
