Skip to content

EpiSim

EpiSim transforms research papers into interactive simulators.

Core trick

Six agents extract ODE models and parameters from a paper, generate a simulator, and check its output against the paper's reported results.

Tags

Description

EpiSim transforms research papers into interactive simulators. Upload a PDF or paste an arxiv ID — a six-agent pipeline extracts the mathematical model (ODEs, parameters, initial conditions), generates a Streamlit simulator with parameter sliders, validates output against the paper's results, and produces a downloadable Python script. Opus 4.6 features: adaptive thinking at per-agent effort levels (Reader at max, Summarizer at medium, Builder at high — five agents, three effort levels). Real-time visible thinking streams into a typewriter console. 1M context window holds entire papers with zero RAG. 128K output generates complete apps in one API call. Parallel multi-agent execution via ThreadPoolExecutor (~40% faster) Tested across domains: COVID-19 (SIDARTHE, 8 compartments), Dengue, Ebola, and Ecology (Lotka-Volterra). The pipeline reads differential equations, not just epidemiology. 76 tests passing.
wpn10/episim★ 20 forksPythonMITCreated Feb 11, 2026 · last push Feb 16, 2026

README excerpt

# EpiSim

### Research papers in, interactive simulators out.

Drop a PDF or paste an arxiv ID. EpiSim reads the paper, extracts the complete mathematical model, generates an interactive simulator with parameter sliders, validates it against the paper's own results, and produces a downloadable standalone script. Six AI agents. One pipeline. Zero code written by the user.

Built for epidemiology. Works on any ODE paper.

![SEIQR Quarantine Model — Generated by EpiSim](seiqr_quarantine_simulation.png)
*Example output: SEIQR quarantine model extracted from a research paper and simulated automatically.*

<!-- TODO: Add demo video GIF/link -->

[![Built with Claude Opus 4.6](https://img.shields.io/badge/Built_with-Claude_Opus_4.6-f0b429?style=for-the-badge&logo=anthropic&logoColor=white)](https://www.anthropic.com/news/claude-opus-4-6)
[![Python 3.10+](https://img.shields.io/badge/Python-3.10+-3776AB?style=for-the-badge&logo=python&logoColor=white)]()
[![License: MIT](https://img.shields.io/badge/License-MIT-06d6a0?style=for-the-badge)]()
[![76 Tests Passing](https://img.shields.io/badge/Tests-76_passing-06d6a0?style=for-the-badge)]()

> **Problem Statement 2: Break the Barriers** -- Mathematical modeling is locked behind programming expertise. EpiSim puts it in everyone's hands.

---

## The Problem

During COVID-19, thousands of epidemic modeling papers were published. Each contained mathematical models that could inform public health decisions -- if anyone could run them. But r

Team