PumasAI

What is PumasAI?

PumasAI makes Pumas, a software suite for quantitative work in drug development. It covers nonlinear mixed-effects modeling, optimal design, Bayesian methods, clinical trial simulation, non-compartmental analysis and bioequivalence testing in one environment based on the Julia language. PumasCP is the point-and-click product for NCA and BE projects, with built-in study workflows, automated reports and options for FDA or EMA requirements. DeepPumas adds neural networks to mechanistic models so scientists can find relationships in small or sparse datasets. The AI features include AskPumas, a retrieval-based assistant that answers pharmacometrics questions with links to documentation, and PumasAide, which lets whichever coding agent you prefer work against a running Pumas session. It is used by pharma and biotech teams, CROs and academics. Pricing is not published: the site mentions volume discounts and tailored plans for CROs and consultants, and says desktop versions of Pumas and PumasCP are free for academic research and training.

Use cases

• Run non-compartmental analysis on PK data
• Test bioequivalence under FDA or EMA rules
• Build NLME and PK/PD models
• Combine neural networks with mechanistic models
• Generate automated clinical pharmacology reports
• Ask pharmacometrics questions with cited answers
• Simulate clinical trials

Who it's for

• Pharmacometricians
• Clinical pharmacologists
• Contract research organizations
• Academic researchers

Why use PumasAI

• Several analysis types live in one tool, which cuts the cost of maintaining separate packages.
• PumasCP guides users from data formatting to report generation, which reduces training and QC effort.
• AskPumas answers link back to documentation so claims can be checked.
• PumasAide keeps data and prompts local while letting your own coding agent run analyses.
• Desktop versions are free for academic research and training.

PumasAI features

• NCA workflow that reads standard file formats and produces customized TLFs and reports
• BE workflow with standard and reference-scaled testing
• Built-in study workflows for studies such as SAD, food-effect and drug-drug interaction
• DeepPumas hybrid modeling that mixes NLME structure with neural networks
• AskPumas assistant with answers linked to the Pumas documentation
• PumasAide connection between a coding agent and a live Pumas session
• Point-and-click data formatting for XLSX, CSV, XPT and SAS7BDAT files
• Desktop and cloud versions, with the cloud version on JuliaHub
• Built to CFR Part 11 and SOC-2 standards

PumasAI integrations

• JuliaHub
• OpenAI
• Anthropic
• Google

How to get started with PumasAI

1. Request a call or a customized plan from the PumasAI team.
2. Choose the desktop version for Windows or Mac, or the cloud version on JuliaHub.
3. Load study data from files such as XLSX, CSV or XPT and set up the analysis.
4. Run an NCA, BE or modeling workflow and generate tables, figures and listings.
5. Use AskPumas for questions or PumasAide to run live analyses from your coding agent.

PumasAI limitations

• Pricing is quoted on request rather than published
• Some of the built-in study workflows are marked as in development
• Desktop users handle their own regulatory compliance setup, while the cloud version covers it

PumasAI pricing

PumasAI is sold on custom quotes, so its prices aren't published.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

PumasAI alternatives

The main PumasAI alternatives listed on Debuly are TensorFlow, BAML, Exa, Firemetrics, Guardrails AI and MLX. The table compares pricing and platforms; order is A–Z.

1. 

   BAML

   Open-source, TypeScript-like programming language for agents, with typed LLM functions, built-in tests and SDK generation.

   Developer platformsCoding
   Open sourceVisit BAML (official site)
2. 

   Exa

   Web search API for AI agents and apps that returns relevant passages with citations, billed pay-as-you-go from a free monthly credit.

   Developer platformsResearch and searchAutomation and agents
   FreemiumVisit Exa (official site)
3. 

   Firemetrics

   FHIR-native clinical data repository for hospitals with SQL access, an MCP server and a local AI assistant.

   Developer platformsResearch and search
   Contact salesVisit Firemetrics (official site)
4. 

   Guardrails AI

   Open-source framework that wraps LLM apps with validators for PII, hallucination and policy checks, plus Snowglobe simulation testing.

   Developer platformsCodingAutomation and agents
   Open sourceVisit Guardrails AI (official site)
5. 

   MLX

   Open-source array framework from Apple machine learning research for training and running models on Apple silicon.

   Developer platformsCoding
   Open sourceVisit MLX (official site)
6. 

   TensorFlow

   Open-source machine learning framework with Keras, TensorFlow.js, LiteRT and TFX for building and deploying models.

   Developer platformsCoding
   Open sourceVisit TensorFlow (official site)

PumasAI FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: none collected yet, so a monogram is shown.
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.