OpenCTI is rebuilding its connector layer into a marketplace and wiring the platform to XTM Hub
modeltime alternatives
The best modeltime alternatives in analytics tools, ranked by Sparkpulse's velocity_score.
Updated Aug 12, 2026
Looking for the best alternatives to modeltime? Sparkpulse tracks and ranks 12 alternatives in analytics tools by shipping velocity — how frequently each ships meaningful updates, verified from official changelogs. For reference, modeltime shipped 0 meaningful updates in the last 30 days and carries a velocity score of 0.0 out of 10 in 2026. The alternatives below are ranked the same way, so you're comparing real release momentum, not marketing claims.
About modeltime
modeltime built conformal intervals in, then went quiet on features.
modeltime is at 1.3.3, a single change making the package robust to xgboost version shifts. The feature weight sits in 1.3.2, which added a future-based parallel backend, the maape() accuracy metric and dials helpers for ADAM engine tuning, and further back in the 1.2.8 and 1.3.0 pair that introduced conformal prediction intervals and then carried them through the nested forecasting workflow.
Velocity 0.0 · Last update 1h ago
Top 12 alternatives to modeltime
Ranked by recent ship velocity. Tap any card for the full editorial breakdown, or pivot to a head-to-head.
Fulcrum is consolidating on Esri, with Google Maps gone September 1
Omni ships weekly, and almost every week the headline item is an AI feature
OpenHouse is hardening the seams where table policies and jobs quietly fail.
silx 3.0 moved its default Qt binding to PySide6 — a migration for everyone embedding it.
Iris ships steadily on a two-a-year cadence, but its feed publishes only pointers.
Julia's distribution library grinds forward one distribution at a time
Quantum chemistry package adding whole method families every release.
OpenMC's random ray solver has gone from new arrival to the centre of every release
TsFile is quietly rebuilding itself as an Arrow-speaking interchange format
tidyr replaced separate() with a family that says what it does.
performance keeps adding ways to check a model you have already fitted.
modeltime vs alternatives — shipping velocity at a glance
Velocity score (0–10) and meaningful releases shipped in the last 30 days, from official changelogs. Higher = shipping faster.
| Product | Velocity | Sparks · 30d | Focus areas | Latest release |
|---|---|---|---|---|
| modeltime (baseline) | 0.0 | 0 | forecastingconformal-predictiontidymodels | — |
| OpenCTI | 6.3 | 1 | threat-intelligenceconnector-marketplacextm-hub | Connector catalog is rebuilt as a faceted marketplace |
| Fulcrum | 6.3 | 0 | field-data-collectionesri-arcgisoffline-maps | — |
| Omni | 6.3 | 1 | business-intelligencesemantic-modelai-routines | AI semantic model generation goes generally available in Omni |
| OpenHouse | 5.0 | 0 | icebergdata governancetable policies | — |
| silx | 2.5 | 0 | synchrotronqthdf5 | 3.0.0: PySide6 becomes the default Qt binding, Python 3.10 required |
| iris | 2.5 | 0 | earth sciencerelease cadencepython | — |
| Distributions.jl | 2.5 | 0 | juliastatisticsdistributions | — |
| PySCF | 2.5 | 0 | quantum-chemistryperiodic-systemscoupled-cluster | — |
| OpenMC | 2.5 | 0 | monte-carlo-transportrandom-raydepletion | OpenMC 0.15.0 introduces a random ray transport solver |
| Apache TsFile | 2.5 | 0 | time-seriescolumnar-formatapache-arrow | — |
| tidyr | 0.0 | 0 | tidyversedata-reshapingpivoting | — |
| performance | 0.0 | 0 | r-languagemodel-diagnosticsbayesian | — |
The 12 best modeltime alternatives, in depth
1. OpenCTI · velocity 6.3
OpenCTI is rebuilding its connector layer into a marketplace and wiring the platform to XTM Hub.
Over the last 30 days OpenCTI shipped 1 meaningful update vs modeltime's 0, most recently “Connector catalog is rebuilt as a faceted marketplace”. Its velocity score of 6.3/10 blends that with longer-term release cadence.
Where modeltime leans on forecasting, conformal prediction and tidymodels, OpenCTI focuses on threat intelligence, connector marketplace and xtm hub.
Over the last 30 days OpenCTI has been shipping faster than modeltime — a point in its favour if release momentum matters to you.
2. Fulcrum · velocity 6.3
Fulcrum is consolidating on Esri, with Google Maps gone September 1.
Its velocity score of 6.3/10 reflects longer-term release cadence.
Where modeltime leans on forecasting, conformal prediction and tidymodels, Fulcrum focuses on field data collection, esri arcgis and offline maps.
Fulcrum and modeltime have shipped at a similar pace over the last 30 days, so the decision comes down to fit and feature depth.
3. Omni · velocity 6.3
Omni ships weekly, and almost every week the headline item is an AI feature.
Over the last 30 days Omni shipped 1 meaningful update vs modeltime's 0, most recently “AI semantic model generation goes generally available in Omni”. Its velocity score of 6.3/10 blends that with longer-term release cadence.
Where modeltime leans on forecasting, conformal prediction and tidymodels, Omni focuses on business intelligence, semantic model and ai routines.
Over the last 30 days Omni has been shipping faster than modeltime — a point in its favour if release momentum matters to you.
4. OpenHouse · velocity 5.0
OpenHouse is hardening the seams where table policies and jobs quietly fail.
Its velocity score of 5.0/10 reflects longer-term release cadence.
Where modeltime leans on forecasting, conformal prediction and tidymodels, OpenHouse focuses on iceberg, data governance and table policies.
OpenHouse and modeltime have shipped at a similar pace over the last 30 days, so the decision comes down to fit and feature depth.
Full OpenHouse trajectory → · Compare modeltime vs OpenHouse →
5. silx · velocity 2.5
Silx 3.0 moved its default Qt binding to PySide6 — a migration for everyone embedding it.
Its velocity score of 2.5/10 reflects longer-term release cadence; its most recent meaningful update was “3.0.0: PySide6 becomes the default Qt binding, Python 3.10 required”.
Where modeltime leans on forecasting, conformal prediction and tidymodels, silx focuses on synchrotron, qt and hdf5.
silx and modeltime have shipped at a similar pace over the last 30 days, so the decision comes down to fit and feature depth.
6. iris · velocity 2.5
Iris ships steadily on a two-a-year cadence, but its feed publishes only pointers.
Its velocity score of 2.5/10 reflects longer-term release cadence.
Where modeltime leans on forecasting, conformal prediction and tidymodels, iris focuses on earth science, release cadence and python.
iris and modeltime have shipped at a similar pace over the last 30 days, so the decision comes down to fit and feature depth.
7. Distributions.jl · velocity 2.5
Julia's distribution library grinds forward one distribution at a time.
Its velocity score of 2.5/10 reflects longer-term release cadence.
Where modeltime leans on forecasting, conformal prediction and tidymodels, Distributions.jl focuses on julia, statistics and distributions.
Distributions.jl and modeltime have shipped at a similar pace over the last 30 days, so the decision comes down to fit and feature depth.
Full Distributions.jl trajectory → · Compare modeltime vs Distributions.jl →
8. PySCF · velocity 2.5
Quantum chemistry package adding whole method families every release.
Its velocity score of 2.5/10 reflects longer-term release cadence.
Where modeltime leans on forecasting, conformal prediction and tidymodels, PySCF focuses on quantum chemistry, periodic systems and coupled cluster.
PySCF and modeltime have shipped at a similar pace over the last 30 days, so the decision comes down to fit and feature depth.
9. OpenMC · velocity 2.5
OpenMC's random ray solver has gone from new arrival to the centre of every release.
Its velocity score of 2.5/10 reflects longer-term release cadence; its most recent meaningful update was “OpenMC 0.15.0 introduces a random ray transport solver”.
Where modeltime leans on forecasting, conformal prediction and tidymodels, OpenMC focuses on monte carlo transport, random ray and depletion.
OpenMC and modeltime have shipped at a similar pace over the last 30 days, so the decision comes down to fit and feature depth.
10. Apache TsFile · velocity 2.5
TsFile is quietly rebuilding itself as an Arrow-speaking interchange format.
Its velocity score of 2.5/10 reflects longer-term release cadence.
Where modeltime leans on forecasting, conformal prediction and tidymodels, Apache TsFile focuses on time series, columnar format and apache arrow.
Apache TsFile and modeltime have shipped at a similar pace over the last 30 days, so the decision comes down to fit and feature depth.
Full Apache TsFile trajectory → · Compare modeltime vs Apache TsFile →
11. tidyr · velocity 0.0
Tidyr replaced separate() with a family that says what it does.
Its velocity score of 0.0/10 reflects longer-term release cadence.
Where modeltime leans on forecasting, conformal prediction and tidymodels, tidyr focuses on tidyverse, data reshaping and pivoting.
tidyr and modeltime have shipped at a similar pace over the last 30 days, so the decision comes down to fit and feature depth.
12. performance · velocity 0.0
Performance keeps adding ways to check a model you have already fitted.
Its velocity score of 0.0/10 reflects longer-term release cadence.
Where modeltime leans on forecasting, conformal prediction and tidymodels, performance focuses on r language, model diagnostics and bayesian.
performance and modeltime have shipped at a similar pace over the last 30 days, so the decision comes down to fit and feature depth.
Full performance trajectory → · Compare modeltime vs performance →
Frequently asked questions
What are the best alternatives to modeltime?
The top modeltime alternatives we currently track in analytics tools are OpenCTI, Fulcrum, Omni, OpenHouse, silx, ranked by recent ship velocity.
How is this list of modeltime alternatives ranked?
Alternatives are ranked by Sparkpulse's velocity_score — release cadence + 30-day spark count + sector-relative ship rate.
Can I compare modeltime directly with one of these alternatives?
Yes — every card has a "Compare with modeltime" link to a side-by-side /compare page.