Built for R&D Teams

Research & Development.

Name: Micantis Battery Analytics Platform
Author: Micantis

From prototype to production. Spend your time on the science, not the spreadsheets.

University Labs Battery Startups Corporate R&D National Labs

Request a demo Explore Pricing

10x faster

Stop wrestling with Excel.

Bring your own

Python SDK for your models.

Unlimited data

No GB limits on cycle data.

Read R&D insights

Features

Everything your research team needs.

Comprehensive tools to take your battery research from raw cycler data to publication ready insights.

Quick Graphing

One click data analysis.

Stop wrestling with Excel and complex Python scripts. Get instant, professional visualizations of your battery data with one click.

One click visualizations for voltage, capacity fade, dQ/dV, EIS Nyquist, DRT
Multi cell comparisons across unlimited datasets
Interactive exploration with zoom, pan, and inspect
Presentation ready styling and smart annotations

Cycle life graphing in the Micantis Web App

Dashboards

Custom research dashboards.

Build personalized views that show exactly what matters for your specific research goals. Monitor live experiments and share insights with your team.

Drag and drop builder. No coding required.
Real time updates from running experiments
Multi experiment views across test campaigns
Shareable templates standardize team views
Mobile responsive monitoring from anywhere

Electrochemistry

Advanced electrochemical analysis.

Skip the manual data processing. Micantis automatically extracts key parameters from EIS, HPPC, and other electrochemical tests, surfacing performance and degradation insights.

EIS analysis with automatic Nyquist/Bode plots and circuit fitting
DRT analysis in one click from EIS data
HPPC processing for resistance and power capability
Feature extraction with automated parameter trending
Multi condition analysis across temperature and SOC
Mechanism identification via pattern recognition

Auto Features

Every feature, extracted automatically.

When test data lands in Micantis, every relevant battery metric is computed automatically. No scripts to maintain, no manual data wrangling, no chasing edge cases when firmware changes.

Capacity, energy, Coulombic efficiency per cycle
dQ/dV peaks detected and tracked over life
HPPC resistance and power maps from current pulses
EIS Nyquist/Bode with automatic circuit fitting
DRT analysis derived from EIS data
DCIR computed from cycle pulses

Automatic feature extraction across HPPC and cycling data

Data Cleaning

Clean test data without writing scripts.

Remove bad cycles, trim restart artifacts, drop sensor glitches, and stitch interrupted runs together. Click through it visually, or describe what to remove and let MOOSE handle it. Cleaning rules save as templates you can apply to every future run.

Visual cleaning. Select bad cycles or regions on the chart and remove them
Stitch interrupted runs. Combine multi part tests into one continuous record
Auto detect anomalies. Flag sensor dropouts and spikes for review
Reusable templates. Save a cleaning recipe and apply it to new data
Non destructive. Raw data preserved, cleaned views layered on top

Cloud Python

Run Python where your data lives.

Skip local environment setup, file downloads, and dependency wrangling. Run scripts directly in the cloud against your Micantis data, save them as templates, and schedule recurring analysis.

Cloud execution in secure containers, no local setup
Save scripts as reusable templates for the team
Schedule recurring analysis to run on a cadence
Pandas native. Results land as DataFrames
MOOSE in the editor. Describe what you want, MOOSE writes the code

Cloud Script · scheduled daily

# Runs in the cloud against your Micantis data
from micantis import MicantisAPI
import pandas as pd

api = MicantisAPI()

# Pull yesterday's NMC formation data
data = api.get_data_table(
    search="NMC and Formation",
    since="yesterday",
)

# Your model. Your IP. Our compute.
scores = your_model(data)
api.push_results(scores, tag="daily-formation")

Developer APIs

Developer APIs and integration.

Integrate Micantis into your research ecosystem with comprehensive APIs and SDKs. Whether you're using Jupyter notebooks, custom scripts, or automated pipelines, Micantis fits your workflow.

Python SDK with native Jupyter integration
REST API for full platform access
Real time streaming over WebSockets
Batch processing for bulk operations
Custom algorithms deployed on our infrastructure

Python SDK Example

import pandas as pd
from micantis import MicantisAPI

# Connect to Micantis platform
api = MicantisAPI(service_url=SERVICE_URL,
                  username=USERNAME,
                  password=PASSWORD)
api.authenticate()

# Get cell data and metadata
cells = api.get_cells_list(search="*LFP*")
data_table = api.get_data_table(search="cycle_life", limit=100)

# Download test data
file_ids = data_table['id'].to_list()
test_data = []
for file_id in file_ids:
    df = api.download_csv_file(file_id)
    test_data.append(df)

# Combine and analyze
all_data = pd.concat(test_data)
print(f"Analyzed {len(test_data)} test files")

MOOSE AI

Ask questions in plain language.

MOOSE is the built in AI assistant that understands your battery test data. Ask for charts, summaries, spec checks, or scheduled reports. MOOSE writes the queries and brings back structured answers.

Plain language queries. Skip the SQL.
Auto generated charts with the right axes for the question
Scheduled reports delivered to your inbox
Writes Python in the cloud editor when you describe what you want
Pin and share findings, no login required

Explore MOOSE

Micantis in Practice

How research teams use Micantis.

Real customer engagements where Micantis turned manual data plumbing into automatic insight.

From two raw files to one continuous test.

A research lab runs formation on one tester and cycle life on another. Manually stitching the two records together used to take an engineer hours each week. Now it lands stitched automatically the moment the data hits Micantis.

The situation

Formation runs on a high precision channel, cycle life moves to a long duration channel. The two outputs land as separate raw files with different timestamps, different channel IDs, and slightly different export formats. Combining them into a single record meant matching cell IDs across systems by hand and gluing the cycles together in spreadsheets.

What they did

They tagged formation and cycle life programs in Micantis with the same cell IDs and program metadata. Micantis recognises the relationship at ingest and stitches the two records into one continuous test, automatically. No script, no nightly job, no engineer in the loop.

The result

Formation and cycling data appear as one continuous timeline in every view, every graph, every export. The engineers stopped spending mornings joining files and started spending them on actual analysis.

Before Hours per week stitching

After 0 manual joins

100% auto stitched on ingest, no engineer in the loop

Two databases, one view.

A battery R&D team kept material formulations in LIMS and cell test data in spreadsheets. Now Micantis is their cell data system of record and pulls LIMS in alongside, so they can see how a formulation change moves cell performance in one click.

The situation

Two systems, no overlap. LIMS held formulation lots, additive ratios, and process parameters. A separate spreadsheet held the cell test results. Every time R&D wanted to ask "did the new electrolyte help?" they had to export from both, paste them together, and pivot by hand.

What they did

Micantis became the system of record for cell test data and connected to LIMS through the integration layer. Cell metadata now pulls supplier lot, formulation revision, and process parameters automatically. They built a dashboard grouping cell performance by formulation rev.

The result

One click view of how each formulation change moves capacity, retention, and resistance. R&D iterates faster because the question they keep asking, "did this change help?", finally has a built in answer.

Before 2 disconnected systems

After 1 unified view

1 click from formulation change to performance impact

Integrations

Works with your lab equipment.

Seamless data import from cyclers, potentiostats, and LIMS platforms.

Battery Cyclers

Data import from any cycler. If we don't support yours yet, we'll add it.

Arbin Maccor Neware Bitrode BioLogic Basytec

Potentiostats & EIS

Import EIS data and electrochemical measurements from leading instruments.

Gamry Autolab Ivium Solartron Princeton Squidstat

LIMS Systems

Connect lab data with sample tracking and metadata pipelines.

LabWare STARLIMS LabVantage Benchling Uncountable LabVIEW

Accelerate your battery research.

Join leading research institutions and companies using Micantis.

Request a demo Try AI assistant demo