Steltic CFS

Free, open-source AI agent that designs cold-formed steel buildings to AISI S100-16 (R2020) w/S2, S3, S240-20 and S400-20 with ASCE 7-22 loads, on your own machine: wall-path buildings (WSP, steel-sheet, strap-braced and gypsum shear walls, podium and mixed systems, up to 8 storeys) and portal-frame buildings. Paste a design brief and get an OpenSees model, a calculation report and an interactive 3D viewer. Bring your own LLM API key (your API base URL and key are held in memory only, never written to disk).

• Easiest start: Steltic Hub installs this and the other modules in one window.
• See the output first: 25 worked buildings with reports and 3D models at stelticai.com.
• Video: Steltic Hub installation.
• Indian Standards edition: steltic_CFS_india.

browser ──▶ FastAPI app (localhost) ──▶ your LLM (key in app memory, never stored)
                 │  parses tool calls
                 ▼
           sandbox executor (run_python only) — Docker when available
                 │
           steel engine + OpenSees ─▶ report.html + viewer_3d.html

Not for construction. Every output is produced by your own AI model, may be incomplete or incorrect, and must be independently checked and sealed by a licensed professional engineer before any use for design, construction, or permitting. See DISCLAIMER.md.

Install & run

Most people should start with Steltic Hub, which clones and installs this module for you. To run this module on its own, install it from GitHub. It needs Python 3.10–3.12 (openseespy, the analysis engine, ships compiled binaries for those versions only); 3.12 is recommended.

Windows (PowerShell)

git clone https://github.com/Steltic/steltic_cfs
cd steltic_cfs
py -3.12 -m venv .venv
.venv\Scripts\Activate.ps1
pip install -e .
steltic-cfs                  # starts on http://127.0.0.1:8000 and opens your browser

macOS / Linux

git clone https://github.com/Steltic/steltic_cfs
cd steltic_cfs
python3.12 -m venv .venv
source .venv/bin/activate
pip install -e .
steltic-cfs                  # starts on http://127.0.0.1:8000 and opens your browser

The install brings the full engine (openseespy, numpy, scipy, matplotlib, about 400 MB), so designs run without Docker. To run with a .env file of settings, use ./run_local.sh or .\run_local.ps1 instead of steltic-cfs.

Update: in the repo folder, git pull, then pip install -e . again (needed only when pyproject.toml changed, harmless otherwise).

First run: open Settings, enter your provider's API base URL (any OpenAI-compatible endpoint — OpenRouter, vLLM, Together, Fireworks, OpenAI, Anthropic…), your API key, and a model id. Then paste a brief (stories, bays & spacings, loads, seismic, system) — or pick one of the 25 built-in example briefs (numbered Ex1-Ex30; Ex20-24 rack briefs are descoped -- EXAMPLE_BRIEFS in steltic/main.py is the source of truth) — and click Design building.

Offline smoke test: set Model to MOCK — it drives the whole pipeline (sandbox, engine, OpenSees, report) with no LLM.

Windows note: if starting fails with "Application Control policy has blocked this file" or "os error 4551", Windows Smart App Control is blocking an unsigned Python. Use the signed python.org build and recreate the environment:

winget install Python.Python.3.12       # then open a new terminal in the repo folder
Remove-Item -Recurse -Force .venv
py -3.12 -m venv .venv
.venv\Scripts\Activate.ps1
pip install -e .

Sandbox

The agent's Python only ever executes in a sandbox. EXECUTOR (env / .env) picks the mode:

value	isolation	notes
auto	Docker if available, else subprocess	default
docker	container per run: no network, read-only fs, non-root, cpu/mem caps	build once: ./sandbox_image/build.sh
subprocess	none (child process with rlimits)	needs pip install openseespy numpy scipy matplotlib; fine for local single-user use

Steltic binds to 127.0.0.1 and has no authentication — don't expose the port. Designs are saved under your OS user-data dir (e.g. %LOCALAPPDATA%\Steltic, ~/.local/share/Steltic); override with DATA_DIR.

Engineering-standards, OpenSees & design-examples RAG (highly recommended)

Steltic was validated with RAG vector databases of AISI S100-16(R2020)+S2/S3, S240-20 and S400-20, an examples database of validated OpenSees models, and two databases of the OpenSees documentation. The specifications and design examples ground the LLM in the current procedures; the OpenSees databases help it build the model — and when OpenSees throws errors, resolve them. Steltic's performance has been validated with these databases and will likely reduce without them.

For copyright reasons the vector databases of the AISI standards are not open-sourced in this project. The OpenSees databases are freely downloadable from the Steltic v0.1.1 release (shared with the AISC agent) as portable .jsonl.gz dumps (pre-embedded; see rag_v2/README.md for loading them into your own Qdrant): cfs_design_examples (original worked Q&A for the CFS scope; being authored), opensees_buildings_3d (40 validated 3D building models), opensees_building_templates, and the two OpenSees documentation sets.

Two options:

1. None (default — not recommended). Leave RAG_API_URL empty — the agent relies on its own cited AISI/CFS knowledge. Good models do respectably; grounded runs are better.
2. Bring your own server. Run any server exposing the small API described in rag_v2/README.md: load the downloadable OpenSees databases, and build the standards collections from your own licensed copies with the rag_v2/ chunking + ingestion starter kit. Then put the connection in the environment (or a .env next to where you launch): RAG_API_URL=http://your-server:8080/query and, if your server enforces one, RAG_API_TOKEN=....

A tool call the model never finished

A provider behind OpenRouter validates the whole conversation on every request. If a turn is cut off in the middle of a tool call's arguments ({ and nothing more), a provider such as Together refuses the next request with 400 Invalid JSON in tool call arguments — a 400 the retry net does not retry, so the run ended, and the cut-off turn saved in conversation.json broke every Continue after it. The agent now keeps every tool call in the history parseable ({} stands in for arguments that did not parse), never runs such a call, answers it with an error that asks the model to repeat it with complete arguments, and heals a conversation saved by an older version when it is resumed. tests/test_tool_call_healing.py.

Repo map

steltic/ FastAPI app + agent loop + sandbox executors · steel_engine/ OpenSees modelling, design pipeline, consistency checks, report + 3D viewer · contract/ the agent's working contract and references · frontend/ vanilla JS UI · sandbox_image/ Docker sandbox image · test_buildings/ the 25 CFS example briefs with assessment rubric · rag_v2/, rag_update/ build-your-own-RAG starter kit.

License

MIT — see LICENSE, NOTICE (third-party data notes) and DISCLAIMER.md (engineering disclaimer; also shown in-app at /terms).

Physical data export and legacy replay

New design jobs record a versioned physical-data package for Steltic openBIM. Completed jobs can be replayed without analysis or redesign. See the export contract and commands. The export reports unresolved legacy geometry explicitly and preserves the source calculations.