# jihe520/MathModelAgent

🤖📐专为数学建模设计的 Agent & skills ,自动完成数学建模，生成一份完整的可以直接提交的论文。 An Agent Designed for Mathematical Modeling ,Automatically complete mathmodel and generate a complete paper ready for submission.

Repository: https://github.com/jihe520/MathModelAgent
Canonical: https://ross.abutalabs.com/products/mathmodelagent
Homepage: https://mathmodel.top/home
Language: Python
License Family: other
Topics: agent, llm, mathmodel, skills
Last push: 2026-08-26T14:30:08+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 41
- inputs: {"age_days": 580, "days_push": 7, "days_rel": 7, "gap_med": 1.0, "n_releases_24m": 13}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3791, forks 354 (observed 2026-08-28T04:08:18.672072+00:00)

## What it is
MathModelAgent is a multi-agent LLM application that automates mathematical modeling competitions end-to-end: it analyzes a problem, builds models, writes and executes code via a Jupyter-based code interpreter, and generates a submission-ready paper using Typst templates. It is distributed as a desktop app, a hosted web service, and a set of Claude Code SKILLS, with multi-LLM support via LiteLLM and a RAG knowledge base built on ChromaDB.

## Use cases
- automatically solve a math modeling competition problem and write the paper
- generate a submission-ready MCM/ICM or CUMCM paper from a problem statement
- run modeling, coding, and paper writing with multiple LLM agents
- execute optimization or statistical model code and produce charts automatically
- use Typst templates to format a competition paper
- retrieve modeling methods and code templates from a knowledge base
- practice math modeling contests with an AI assistant

## When to choose
- you need an end-to-end automated pipeline from problem statement to formatted paper
- you want a desktop app or hosted service that works without setting up Python/Node/Redis
- you compete in contests like CUMCM, MCM/ICM, or Huashu Cup and want template-matched output
- you want per-agent model selection and low-cost workflow-agentless orchestration

## When to avoid
- you need a general-purpose agent framework or library to build your own agents
- your task is not mathematical modeling or competition-style paper writing
- you require an OSI-approved license for commercial redistribution (none is provided)
- you need fully offline operation without any LLM API key

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, rag, prompt-engineering, data-science, machine-learning, chat-interface, code-review
- domain: artificial-intelligence, large-language-models, data-science, mathematics, education, developer-tools
- platform: python, cross-platform, windows
- tags: mathematical-modeling, multi-agent, paper-generation, typst-templates, code-interpreter, competition, skills, claude-code, litellm, chromadb, ai-agents, automation, macos, desktop, web-server, docker

## Member repositories
- jihe520/MathModelAgent (main) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:18.672072+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:27:04.448346+00:00, confidence not recorded.
  - readme: https://github.com/jihe520/MathModelAgent (fetched 2026-08-28T04:08:18.672072+00:00, sha 5cbe72dc08fe)
  - homepage: https://mathmodel.top/home (fetched 2026-08-29T09:22:15.902849+00:00, sha 66abf6add4e1)
  - site_page: https://mathmodel.top/about (fetched 2026-08-29T09:22:15.913859+00:00, sha b480d9cba21e)
  - site_page: https://mathmodel.top/changelog (fetched 2026-08-29T09:22:15.911962+00:00, sha b9b376b819a4)
- Data as of 2026-08-30T08:39:29.467469+00:00.