Batch state API
Fused PAT and telemetry state, streamed or polled, with unit-operation context.
Learn moreDevelopers
An API for the physical batch.
Subscribe to fused PAT state, read predictions with the evidence behind them, and submit bounded control proposals — all through the same interface the console uses.
3client SDKs
1edge runtime
100%actions audited
Quickstart
Connect to a train in ten lines
Point the SDK at a plant-edge node, pick a train, and read the live state of the batch that is running right now.
from polymorra import Plant
plant = Plant.connect("edge://site-04", verify_tls=True)
for batch in plant.train("CR-2").stream():
print(batch.step) # "antisolvent-addition"
print(batch.state.supersaturation)
print(batch.state.d50_um)
print(batch.state.polymorph) # ("Form II", 0.97)
if batch.state.risk("oiling-out") > 0.2:
batch.alert("oiling-out risk", severity="high")Control
Proposals, not commands
The API never lets you write a raw setpoint. You submit a proposal; it is checked against the validated window for that train and routed for approval according to the configured autonomy level.
import { Plant } from "@polymorra/sdk";
const plant = await Plant.connect("edge://site-04");
const train = plant.train("CR-2");
const proposal = await train.propose({
parameter: "jacket_ramp_c_per_min",
target: 0.18,
rationale: "FBRM counts rising above metastable limit",
evidence: ["fbrm:2024-06-11T09:41Z", "raman:2024-06-11T09:41Z"],
});
// SHADOW -> logged only | ASSIST -> queued for chemist
// BOUNDED -> applied if inside validated window
console.log(proposal.disposition, proposal.auditId);Edge runtime
Signed images, pinned models
The runtime is a signed container with a pinned, validated model bundle. Version changes are explicit, logged, and reversible — because in a GMP plant, silent updates are a finding.
$ polymorra edge status --train CR-2
runtime 1.8.3 (signed, verified)
models crystallize-v4.2.1 [VALIDATED · locked]
polymorph-v3.9.0 [VALIDATED · locked]
autonomy ASSIST
streams raman ✓ fbrm ✓ pvm ✓ nir ✓ dcs ✓
audit append-only · 1,284,902 events · sealed
uptime 61d 04h (last failover: none)Surfaces
What you can build on
Everything is designed to be traceable: no output without evidence, no action without an audit id.
Prediction API
Polymorph, particle size, impurity, and endpoint predictions with confidence and cited evidence.
Learn moreControl proposals
Bounded setpoint proposals routed by autonomy level, always audited.
Learn moreRecord & evidence
Query the Part 11 trail and export evidence packages for review or inspection.
Learn moreTwin API
Run profile simulations and scale-up predictions programmatically.
Learn moreWebhooks
Subscribe to deviations, form-transition risk, and autonomy changes.
Learn morePlant-edge console
One screen for the batch that is running right now
Supersaturation, particle size distribution, predicted polymorph, impurity trajectory, and the next control move — with the evidence behind each number.
Polymorra plant-edge console showing live supersaturation, particle size distribution, predicted polymorphic form, and impurity trajectory for a running crystallization, with the recommended next control move.
Testing
A simulator so you never debug on a real batch
The twin doubles as a development target: replay historical campaigns, inject faults, and validate your integration long before it touches a qualified train.
- Replay any recorded campaign deterministically
- Inject oiling-out, fouling, seed drift, and sensor dropout
- Assert on predictions and proposals in CI
Integrations
Connects to the systems already running your plant
Polymorra reads and writes through the reactor DCS, PAT instruments, crystallizer and isolation skids, historians, and MES you already validated.
Reactor control & DCS
Emerson DeltaVSiemens PCS 7Honeywell ExperionOPC UAModbus/TCP
PAT & analytics
Mettler-Toledo FBRMPVM in-situ imagingReactIREndress+Hauser RamanNIRHPLC / XRPD imports
Isolation & drying
Nutsche filter-dryersCentrifugesAgitated dryersConical millsMicronizers
MES, historian & quality
Körber PAS-XEmerson SyncadeOSIsoft PILIMSeBR / QMS exports
Trust & compliance
Validated for GMP manufacturing
Polymorra is engineered for regulated drug-substance production: grounded outputs, immutable audit trails, graduated autonomy, and validation documentation from day one.
21 CFR Part 11
Immutable, validated audit log for every agent perception, recommendation, and control action, with e-signature-ready review flows.
GMP / ICH Q7
Change control, validated model versioning, and deployment documentation designed for drug-substance manufacturing.
SOC 2
SOC 2 Type I in progress, Type II on the roadmap; SSO/RBAC, encryption in transit and at rest. [ASPIRATIONAL]
Route & IP protection
Per-tenant isolation of routes, recipes, spectra, and crystal images. No cross-tenant training. On-prem option.
Graduated autonomy
Shadow → assist → bounded auto-control. Every autonomy level is explicitly configured, bounded, and revocable.
Grounded outputs
Every recommendation cites the spectra, images, telemetry, SOP, or specification it was derived from.
Plant-edge first
Inference runs on-site so control loops survive network loss; cloud is for training, fleet, and analytics.
Human-in-the-loop
Chemist and QA checkpoints are first-class: approve, correct, or reject — and every correction trains the models.
Accelerated computing
An NVIDIA-accelerated stack, from the train to the fleet
Perception at the edge, reasoning in the cloud, and a reactor-and-crystallizer twin in between.
Stack
Jetson at the train
Plant-edge inference per reactor or crystallizer train: PVM crystal-image models, FBRM feature extraction, Raman and NIR soft sensors, anomaly and safety classifiers. [ASPIRATIONAL]
Stack
TensorRT + Holoscan
Low-latency perception and sensor-stream preprocessing for in-situ imaging and PAT spectra inside validated control windows.
Stack
Triton + NIM
Route-specific polymorph, impurity, particle-size, endpoint, and batch-reasoning models served with validated version locks and rollback.
Stack
Omniverse + Cosmos
Reactor-and-crystallizer twin plus synthesis of rare crystallization faults — oiling-out, fouling, seed drift, wrong-polymorph nucleation. [ASPIRATIONAL]
Stack
RAPIDS + cuOpt
Telemetry ETL at campaign scale, plus scheduling, solvent recovery, and crystallization-profile optimization.
Stack
NeMo + DGX
Fine-tuned chemistry-process and batch-record reasoning trained on de-identified design-partner data and chemist corrections. [ASPIRATIONAL]
FAQ
Frequently asked questions
Both — in a deliberate order. Polymorra starts in shadow mode (perceive only), moves to assist (recommend, chemist approves), then to bounded auto-control on qualified trains where setpoint moves stay inside validated control windows. Every level is configured per train and revocable.
Polymorra is built for GMP (ICH Q7) and 21 CFR Part 11: immutable audit trail, validated model version locks with rollback, change control, grounded and citable outputs, and human-in-the-loop checkpoints. We ship a validation package and support IQ/OQ/PQ activities with your quality unit.
API or OPC access to your reactor DCS, PAT instruments (Raman, FBRM, PVM, NIR), crystallizer and isolation skids, and MES or historian — plus a train with enough campaign volume for clear ROI.
No. Per-tenant isolation of routes, recipes, spectra, and crystal images is enforced at the data and model layer. Cross-site benchmarks are opt-in and de-identified.
A typical wedge pilot instruments one train, runs shadow mode over a baseline campaign, then moves to assist mode with a defined polymorph, yield, or reprocessing success metric agreed up front.
Perception and control inference run at the plant edge. Cloud handles training, fleet management, and analytics — losing it degrades reporting, not the batch.
Start in shadow mode. Break nothing.
Start with one crystallizer or reactor train. Prove polymorph, yield, and reprocessing ROI in a validation-friendly pilot. Then expand across the plant.