artoo
artoo makes any-to-any clinical dataset conversion lossless by construction.
Comparison · Infra & APIs
campsis vs mLLMCelltype
A side-by-side editorial comparison of campsis and mLLMCelltype — release velocity, themes, recent moves, and the top alternatives to consider.
campsis vs mLLMCelltype: at a glance
What is campsis?
Campsis breaks its API on purpose: snake_case throughout, RxODE compatibility cut loose.
Campsis runs clinical-trial simulations from pharmacometric models, sitting on mrgsolve and rxode2 as interchangeable engines, with the sibling package Campsismod supplying the model object layer. Version 1.9.0 is the release where the suite stops carrying its history: the whole API migrates to snake_case, backward compatibility with the old RxODE package is removed, and result processing is refactored into output functions that can be applied as a collection, with an NCA table the first substantial one. Campsismod made the same snake_case move a week earlier, so this is a suite-wide rename rather than one package's decision.
What is mLLMCelltype?
Consensus cell-type annotation that keeps adding LLM providers, and keeps fixing how they fail.
mLLMCelltype annotates scRNA-seq clusters by polling several LLMs and reconciling their answers into a consensus label, shipping as paired R and Python packages. The 2.0 line has settled into a rhythm: broaden the provider roster, then harden the parsing and retry paths that decide whether a given provider's answer survives into the consensus. Version 2.0.8 is pure reliability work, disabling DeepSeek V4's thinking mode because it exhausted the response budget before labels were returned, and raising non-streaming timeouts to 120 seconds.
campsis vs mLLMCelltype: editorial side-by-side
campsis
3.8INFRA · APIS
Campsis breaks its API on purpose: snake_case throughout, RxODE compatibility cut loose.
◆ Current state
Campsis runs clinical-trial simulations from pharmacometric models, sitting on mrgsolve and rxode2 as interchangeable engines, with the sibling package Campsismod supplying the model object layer. Version 1.9.0 is the release where the suite stops carrying its history: the whole API migrates to snake_case, backward compatibility with the old RxODE package is removed, and result processing is refactored into output functions that can be applied as a collection, with an NCA table the first substantial one. Campsismod made the same snake_case move a week earlier, so this is a suite-wide rename rather than one package's decision.
◆ Where it's heading
The 1.8 and 1.9 releases together describe a package being made drivable from outside R. JSON interfaces arrived first for models in Campsismod 1.3.0 and for datasets in Campsis 1.8.0, then extended to scenarios, settings and study replication; the output side has now been generalised the same way, from fixed result processing to a collection of output functions applied to simulated results. Renaming every function and cutting RxODE loose is the cost of that consolidation, paid in one deliberate breaking release rather than spread across several.
◆ Prediction
With the rename and the RxODE removal behind it, the next releases should restore the rxode2 engine to the test suite, which 1.9.0 removed temporarily, and continue filling out the output-function catalogue beyond NCA. The JSON surface looks like the intended entry point for driving Campsis from outside R, though the entries do not say what is meant to consume it.
mLLMCelltype
2.5INFRA · APIS
Consensus cell-type annotation that keeps adding LLM providers, and keeps fixing how they fail.
◆ Current state
mLLMCelltype annotates scRNA-seq clusters by polling several LLMs and reconciling their answers into a consensus label, shipping as paired R and Python packages. The 2.0 line has settled into a rhythm: broaden the provider roster, then harden the parsing and retry paths that decide whether a given provider's answer survives into the consensus. Version 2.0.8 is pure reliability work, disabling DeepSeek V4's thinking mode because it exhausted the response budget before labels were returned, and raising non-streaming timeouts to 120 seconds.
◆ Where it's heading
The centre of gravity has moved from adding models to defending against them. Recent notes read as a catalogue of ways an LLM response can be malformed: numbered lists, preamble headers, annotation-internal colons, a mid-list Unknown, thinking blocks that precede the answer, rate limits returned as HTTP 200 with an error buried in the body. Each of those could previously shift or drop a cluster's annotation, which for a consensus tool is the failure that matters most. Provider additions now land as routine catalogue growth rather than a change in what the package can do.
◆ Prediction
Expect the next release to continue the reliability arc with more provider-specific timeout and parsing guards, and a CRAN publication of 2.0.8 to close the gap the notes themselves flag. Whether return_reasoning grows from an option into the default per-cluster evidence record is the open question these entries do not yet answer.
Alternatives to campsis and mLLMCelltype
Other Infra & APIs products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either campsis or mLLMCelltype.
tabular
tabular went from clinical tables to complete TFL output in under two months.
usmapdata
usmapdata ships its 2025 shapefiles on the year-indexed model it adopted in 0.4.0.
glcdp
glcdp reaches 1.0.0 with a stable schema contract behind its data explorer.
prova
prova adds expected-utility calculation on top of its Bayesian inference core.
checkhelper
checkhelper grew from a check wrapper into a CRAN pre-submission auditor.
See all campsis alternatives → · See all mLLMCelltype alternatives →
Recent activity from campsis and mLLMCelltype
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 2d agomLLMCelltypeDeepSeek annotations stop timing out before a label returns
- 15d agocampsissnake_case across the API; RxODE compatibility removed ⚡
- 1mo agomLLMCelltypeKimi joins the provider panel; annotation parsing hardened
- 3mo agomLLMCelltypePackaging release rolling up parsing and Qwen cache fixes
- 3mo agomLLMCelltypeRelease archived on Zenodo for the accompanying paper
- 5mo agocampsisJSON arguments reach Dataset, Scenarios and Settings
- 6mo agomLLMCelltypeModel roster refreshed; logging unified and console output off
- 7mo agocampsisMaintenance release for future package warnings
- 7mo agocampsisJSON import for Campsis datasets
- 1y agomLLMCelltypemLLMCelltype v1.2.9: Cache System Fix and Improvements
- 1y agocampsisDosing gains vectorized compartments and cycle repetition
- 1y agocampsisParameter uncertainty from SIR and bootstrap output
Frequently asked questions
What is the difference between campsis and mLLMCelltype?
They serve adjacent needs but don't currently overlap on shipped themes. campsis is currently shipping more aggressively (velocity 3.8 vs 2.5), with 1 editorial sparks in the last 30 days against 0. See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Is campsis better than mLLMCelltype?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. campsis is currently shipping more aggressively (velocity 3.8 vs 2.5), with 1 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other Infra & APIs products to evaluate alongside.
What are the best alternatives to campsis?
Top campsis alternatives in Infra & APIs are ranked by recent ship velocity. Browse the "campsis alternatives" section above for the current picks, or visit /alternatives/campsis for the full list with editorial commentary on each.
What are the best alternatives to mLLMCelltype?
Top mLLMCelltype alternatives in Infra & APIs are ranked by recent ship velocity. Browse the "mLLMCelltype alternatives" section above for the current picks, or visit /alternatives/mllmcelltype for the full list with editorial commentary on each.