Skip to main content

OpenStudio AI harness with MCP runtime, host adapters, skills, and knowledge.

Project description

OpenStudio AI Harness

OpenStudio AI Harness packages a local MCP runtime, host adapters, skills, knowledge, and workflow-state tools for AI-assisted building-energy modeling.

Current Capabilities

  • OpenStudio MCP server for model lifecycle, simulation, results, SDK lookup, runtime storage, and MCP-backed blackboard workflow state.
  • Claude Code plugin export.
  • Codex plugin export.
  • Runtime learning schemas and candidate folders.
  • HVAC workflow skills and generated child skills.
  • Reviewed OpenStudio SDK knowledge packs.
  • Packaging north-star plan for stable pip install and marketplace agentic installation paths.

Development Setup

From this repository root:

python -m pip install -e ".[dev]"

Install the runtime package after it is published:

python -m pip install openstudio-ai
openstudio-ai doctor
openstudio-ai-mcp --transport stdio

Run focused tests:

python -m pytest -q \
  tests/test_mcp_openstudio_smoke.py \
  tests/test_openstudio_sdk_docs.py \
  tests/test_openstudio_learning_pipeline.py \
  tests/test_openstudio_codex_adapter.py \
  tests/test_openstudio_claude_code_adapter.py

Start the MCP server in stdio mode:

openstudio-ai-mcp --transport stdio

Export local development plugins:

python -m adapters.claude_code_adapter export-plugin \
  --output-dir /tmp/openstudio-ai-claude-plugin

python -m adapters.codex_adapter export-plugin \
  --output-dir /tmp/openstudio-ai-codex-plugin

Export marketplace-oriented plugins that expect an installed runtime command:

python -m adapters.claude_code_adapter export-plugin \
  --output-dir /tmp/openstudio-ai-claude-plugin \
  --runtime-mode marketplace

python -m adapters.codex_adapter export-plugin \
  --output-dir /tmp/openstudio-ai-codex-plugin \
  --runtime-mode marketplace

Key Docs

Runtime State

Local runtime state is intentionally ignored by Git:

  • .openstudio_mcp_workspace/
  • .openstudio_ai_blackboards/
  • logs/
  • outputs/

The MCP runtime uses local SQLite metadata and filesystem workspaces for large OSM, SQL, and log artifacts.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

openstudio_ai-0.1.0.tar.gz (1.1 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

openstudio_ai-0.1.0-py3-none-any.whl (1.1 MB view details)

Uploaded Python 3

File details

Details for the file openstudio_ai-0.1.0.tar.gz.

File metadata

  • Download URL: openstudio_ai-0.1.0.tar.gz
  • Upload date:
  • Size: 1.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for openstudio_ai-0.1.0.tar.gz
Algorithm Hash digest
SHA256 d2b27b6d53f7d2842f25fc97fc4b5a889b005f9a167f83d4adaf29b0dbb8119d
MD5 5556141102ee963caea51fab2472d72b
BLAKE2b-256 7bb629b050facfc401407cc174c726ab556ec4f33534b6f4d6254795dc088d3b

See more details on using hashes here.

File details

Details for the file openstudio_ai-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: openstudio_ai-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 1.1 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for openstudio_ai-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 79fd68dc7d7341279bf7a202fd583aeba5ba13946c8ea01c119880018e76ae93
MD5 964c052f1d008031d1e371904b05bc8f
BLAKE2b-256 a9810051a6d4fe0a693973d9105b947d0919ca4de21465189eca6004d6d384f7

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page