jihe520/MathModelAgentPublic

🤖📐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.

AI summary: An automated AI agent specifically designed to complete mathematical modeling competitions and generate submission-ready papers.

Stars
6.2K
+-1 today
Forks
449
Watchers
26
Open issues
33
Open PRs
11
Contributors
~11
Commits
101
Branches
7

TeXNo licenseCreated Jan 30, 2025Last push 2d agoLatest release v0.0.22+61 stars this week+1.3K this month

Quick answers

What is MathModelAgent?
An automated AI agent specifically designed to complete mathematical modeling competitions and generate submission-ready papers.
What does MathModelAgent do?
MathModelAgent streamlines the grueling process of mathematical modeling competitions by automating the end-to-end workflow. It leverages built-in Claude Code and specialized skills to transform a multi-day competition effort into a task completing in mere hours. The system is distributed as a standalone desktop application, removing the need for complex Python or Node.js environment setups. It handles everything from initial problem analysis to generating a complete, formatted research paper ready for submission. By integrating various scientific computing and formatting tools, it drastically reduces the manual labor traditionally required in these academic contests.
Who is MathModelAgent for?
Students, academic researchers, and participants in mathematical modeling competitions looking to drastically accelerate their workflow. No advanced programming or environment setup skills are required to use the desktop version.
How do I get started with MathModelAgent?
https://github.com/jihe520/MathModelAgent/releases/latest
How popular is MathModelAgent on GitHub?
jihe520/MathModelAgent has 6,163 stars and 449 forks on GitHub, and gained 61 stars in the last 7 days.

Star history

since Sep 11, 2026
02K4K6KSep 2026Sep 2026Sep 2026Oct 2026
6.2K stars as of Oct 2, 2026. Measured daily since Sep 11, 2026; GitHub no longer exposes earlier star timestamps.

Contribution activity

commits per day, last 52 weeks
OctNovDecJanFebMarAprMayJunJulAugSepMonWedFri2025-10-05: 0 commits2025-10-06: 0 commits2025-10-07: 0 commits2025-10-08: 0 commits2025-10-09: 0 commits2025-10-10: 0 commits2025-10-11: 0 commits2025-10-12: 0 commits2025-10-13: 0 commits2025-10-14: 0 commits2025-10-15: 0 commits2025-10-16: 0 commits2025-10-17: 0 commits2025-10-18: 0 commits2025-10-19: 0 commits2025-10-20: 0 commits2025-10-21: 0 commits2025-10-22: 0 commits2025-10-23: 0 commits2025-10-24: 0 commits2025-10-25: 0 commits2025-10-26: 0 commits2025-10-27: 0 commits2025-10-28: 0 commits2025-10-29: 0 commits2025-10-30: 0 commits2025-10-31: 0 commits2025-11-01: 0 commits2025-11-02: 0 commits2025-11-03: 0 commits2025-11-04: 0 commits2025-11-05: 0 commits2025-11-06: 0 commits2025-11-07: 0 commits2025-11-08: 0 commits2025-11-09: 0 commits2025-11-10: 0 commits2025-11-11: 0 commits2025-11-12: 0 commits2025-11-13: 0 commits2025-11-14: 0 commits2025-11-15: 0 commits2025-11-16: 0 commits2025-11-17: 0 commits2025-11-18: 0 commits2025-11-19: 0 commits2025-11-20: 0 commits2025-11-21: 0 commits2025-11-22: 0 commits2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 1 commit2026-02-21: 0 commits2026-02-22: 1 commit2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 0 commits2026-02-26: 0 commits2026-02-27: 0 commits2026-02-28: 0 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 0 commits2026-03-05: 0 commits2026-03-06: 0 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 0 commits2026-03-10: 0 commits2026-03-11: 0 commits2026-03-12: 0 commits2026-03-13: 0 commits2026-03-14: 0 commits2026-03-15: 0 commits2026-03-16: 0 commits2026-03-17: 0 commits2026-03-18: 1 commit2026-03-19: 0 commits2026-03-20: 0 commits2026-03-21: 0 commits2026-03-22: 0 commits2026-03-23: 0 commits2026-03-24: 0 commits2026-03-25: 0 commits2026-03-26: 0 commits2026-03-27: 0 commits2026-03-28: 0 commits2026-03-29: 0 commits2026-03-30: 0 commits2026-03-31: 0 commits2026-04-01: 0 commits2026-04-02: 0 commits2026-04-03: 0 commits2026-04-04: 0 commits2026-04-05: 0 commits2026-04-06: 0 commits2026-04-07: 0 commits2026-04-08: 0 commits2026-04-09: 0 commits2026-04-10: 0 commits2026-04-11: 0 commits2026-04-12: 0 commits2026-04-13: 0 commits2026-04-14: 0 commits2026-04-15: 0 commits2026-04-16: 0 commits2026-04-17: 0 commits2026-04-18: 0 commits2026-04-19: 0 commits2026-04-20: 0 commits2026-04-21: 0 commits2026-04-22: 0 commits2026-04-23: 0 commits2026-04-24: 2 commits2026-04-25: 0 commits2026-04-26: 0 commits2026-04-27: 0 commits2026-04-28: 0 commits2026-04-29: 0 commits2026-04-30: 1 commit2026-05-01: 2 commits2026-05-02: 0 commits2026-05-03: 0 commits2026-05-04: 0 commits2026-05-05: 0 commits2026-05-06: 0 commits2026-05-07: 0 commits2026-05-08: 0 commits2026-05-09: 0 commits2026-05-10: 0 commits2026-05-11: 1 commit2026-05-12: 0 commits2026-05-13: 1 commit2026-05-14: 1 commit2026-05-15: 2 commits2026-05-16: 3 commits2026-05-17: 0 commits2026-05-18: 1 commit2026-05-19: 2 commits2026-05-20: 0 commits2026-05-21: 0 commits2026-05-22: 0 commits2026-05-23: 0 commits2026-05-24: 0 commits2026-05-25: 0 commits2026-05-26: 0 commits2026-05-27: 0 commits2026-05-28: 0 commits2026-05-29: 0 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 0 commits2026-06-02: 0 commits2026-06-03: 0 commits2026-06-04: 0 commits2026-06-05: 2 commits2026-06-06: 0 commits2026-06-07: 1 commit2026-06-08: 0 commits2026-06-09: 0 commits2026-06-10: 0 commits2026-06-11: 0 commits2026-06-12: 0 commits2026-06-13: 0 commits2026-06-14: 0 commits2026-06-15: 0 commits2026-06-16: 0 commits2026-06-17: 0 commits2026-06-18: 0 commits2026-06-19: 1 commit2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 0 commits2026-06-23: 0 commits2026-06-24: 0 commits2026-06-25: 0 commits2026-06-26: 0 commits2026-06-27: 0 commits2026-06-28: 0 commits2026-06-29: 0 commits2026-06-30: 1 commit2026-07-01: 0 commits2026-07-02: 0 commits2026-07-03: 0 commits2026-07-04: 0 commits2026-07-05: 0 commits2026-07-06: 0 commits2026-07-07: 0 commits2026-07-08: 0 commits2026-07-09: 0 commits2026-07-10: 0 commits2026-07-11: 0 commits2026-07-12: 0 commits2026-07-13: 0 commits2026-07-14: 0 commits2026-07-15: 0 commits2026-07-16: 0 commits2026-07-17: 0 commits2026-07-18: 0 commits2026-07-19: 0 commits2026-07-20: 1 commit2026-07-21: 0 commits2026-07-22: 0 commits2026-07-23: 0 commits2026-07-24: 0 commits2026-07-25: 0 commits2026-07-26: 0 commits2026-07-27: 0 commits2026-07-28: 0 commits2026-07-29: 0 commits2026-07-30: 0 commits2026-07-31: 0 commits2026-08-01: 0 commits2026-08-02: 0 commits2026-08-03: 0 commits2026-08-04: 0 commits2026-08-05: 0 commits2026-08-06: 0 commits2026-08-07: 0 commits2026-08-08: 0 commits2026-08-09: 1 commit2026-08-10: 0 commits2026-08-11: 0 commits2026-08-12: 0 commits2026-08-13: 0 commits2026-08-14: 0 commits2026-08-15: 0 commits2026-08-16: 0 commits2026-08-17: 1 commit2026-08-18: 0 commits2026-08-19: 0 commits2026-08-20: 0 commits2026-08-21: 0 commits2026-08-22: 0 commits2026-08-23: 0 commits2026-08-24: 0 commits2026-08-25: 0 commits2026-08-26: 0 commits2026-08-27: 0 commits2026-08-28: 0 commits2026-08-29: 0 commits2026-08-30: 0 commits2026-08-31: 0 commits2026-09-01: 0 commits2026-09-02: 0 commits2026-09-03: 0 commits2026-09-04: 0 commits2026-09-05: 0 commits2026-09-06: 0 commits2026-09-07: 0 commits2026-09-08: 0 commits2026-09-09: 0 commits2026-09-10: 0 commits2026-09-11: 0 commits2026-09-12: 0 commits2026-09-13: 1 commit2026-09-14: 0 commits2026-09-15: 0 commits2026-09-16: 0 commits2026-09-17: 0 commits2026-09-18: 0 commits2026-09-19: 0 commits2026-09-20: 0 commits2026-09-21: 0 commits2026-09-22: 0 commits2026-09-23: 0 commits2026-09-24: 0 commits2026-09-25: 0 commits2026-09-26: 0 commits2026-09-27: 0 commits2026-09-28: 0 commits2026-09-29: 0 commits2026-09-30: 0 commits2026-10-01: 0 commits2026-10-02: 2 commits2026-10-03: 0 commits
30 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Continuous integration

    Automated checks passing

  • Repeat trending

    4 trending appearances

What MathModelAgent does

MathModelAgent streamlines the grueling process of mathematical modeling competitions by automating the end-to-end workflow. It leverages built-in Claude Code and specialized skills to transform a multi-day competition effort into a task completing in mere hours. The system is distributed as a standalone desktop application, removing the need for complex Python or Node.js environment setups. It handles everything from initial problem analysis to generating a complete, formatted research paper ready for submission. By integrating various scientific computing and formatting tools, it drastically reduces the manual labor traditionally required in these academic contests.

Students, academic researchers, and participants in mathematical modeling competitions looking to drastically accelerate their workflow. No advanced programming or environment setup skills are required to use the desktop version.

  • Desktop application bundle: Packaged as a standalone application for macOS and Windows, requiring no prior environment configuration.
  • Integrated Claude Code: Comes pre-configured with the Claude AI engine to drive the core analytical reasoning.
  • Automated paper generation: Synthesizes the mathematical models and results into a completely formatted, submission-ready document.
  • Pre-configured skill set: Includes a comprehensive suite of mathematical and modeling skills out of the box.
  • Cross-platform compatibility: Provides native installers for Apple Silicon, Intel Macs, and Windows 64-bit systems.

Where teams use it

Competing in modeling contests

Utilize the agent to rapidly analyze problems and draft comprehensive solutions during time-constrained academic competitions.

Automating academic writing

Generate structured, submission-ready research papers directly from raw mathematical models and data.

Simplifying environment setup

Deploy the modeling agent immediately using the standalone installers without dealing with Python dependencies or Redis servers.

Accelerating scientific modeling

Reduce the time taken to construct and document mathematical models from several days to just a few hours.

Getting started: https://github.com/jihe520/MathModelAgent/releases/latest

README

main branch

🤖 MathModelAgent 📐

专为数学建模设计的 Agent
自动完成数学建模,生成一份完整的可以直接提交的论文。
简体中文 | English

⬇️ 下载最新桌面版(推荐)

🎨 姊妹项目:sci-box —— 科研图表 & 流程图 SKILL 合集


🖥️ 桌面版(推荐使用方式)

不想折腾环境?直接下载桌面版,开箱即用。

👉 前往 Releases 下载最新版本

桌面版已内置 Claude Code 与全套 MathModelAgent SKILLS,无需安装 Python / Node.js / Redis,也无需手动配置 SKILL,装好填一个模型 API Key 即可开始建模。

系统 下载文件
macOS(Apple 芯片 M 系列) mathmodel-<version>-arm64.dmg
macOS(Intel 芯片) mathmodel-<version>-x64.dmg
Windows 64 位 mathmodel-<version>-x64.exe

macOS 安装包已 Developer ID 签名并通过 Apple 公证。

Tip

不确定自己的 Mac 是哪种芯片?点击左上角 → 关于本机,看「芯片」一栏:显示 Apple M 系列选 arm64,显示 Intel 选 x64。

Warning

Windows 安装包当前未签名,首次安装或运行时可能出现 Microsoft Defender SmartScreen 提示,请选择「更多信息」→「仍要运行」,并务必从官方 Releases 页面 下载。

安装后应用会自动检查更新(macOS 支持自动更新,Windows 待代码签名证书配置完成后启用)。

如果你是开发者,想自行部署或参与贡献,请继续阅读下方的 SKILLS 与 使用教程。


🌟 愿景:

3 天的比赛时间变为 1 小时 自动完整一份可以获奖级别的建模论文

✨ 功能特性

  • 🔍 自动分析问题,数学建模,编写代码,纠正错误,撰写论文
  • 💻 Code Interpreter
    • local Interpreter: 基于 jupyter , 代码保存为 notebook 方便再编辑
    • 云端 code interpreter: E2B 和 daytona
  • 📝 生成一份编排好格式的论文
  • 🤝 multi-agents: 建模手,代码手,论文手等
  • 🔄 multi-llms: 每个 agent 设置不同的、合适的模型
  • 🤖 支持所有模型: litellm
  • 💰 成本低:workflow agentless,不依赖 agent 框架
  • 🧩 自定义模板:prompt inject 为每个 subtask 单独设置需求
  • 🌐 Web Search: Agent 自主搜索互联网获取真实数据(Tavily API)
  • 📚 RAG 知识库: 从本地知识库检索建模方法、代码模板、论文写作参考(ChromaDB + Rerank)
  • 🤝 HIL 人机协作: 关键节点暂停等待用户审批,支持 6 种决策动作(confirm / edit / regenerate / ask / skip / abort)
  • 🛡️ 四层容错: 有限重试 → Fallback Hand Off → Evaluator Shadow Mode → Feedback Rerun


我在平台中托管了一个在线版本,方便使用,欢迎体验:

https://mathmodel.top/home

SKILLS

项目蒸馏成完全由 SKILLS 驱动 不再做 Harness 层

Intro

MathModelAgent SKILL —— 直接在 Harness 中驱动的数学建模自动化方案.

💰 开源免费,接入任意模型 完全开源免费,可接入任何模型。

🧠 端到端自动化 从问题分析、建模、编码、绘图到论文排版和验收,一条 /1start-mathmodel 命令全自动完成,中间阶段自动串联,无需人工干预。

📄 17 套 Typst 论文模板 内置中英文主流赛事模板(国赛、华数杯、华为杯、MCM/ICM 等),自动匹配赛事类型,生成排版精良、可直接提交的 PDF 论文。

📐 内置建模知识库 包含完整的建模规范、模型选择决策树(AHP、TOPSIS、ARIMA、GA 等)、常见易错模式和 MCM/ICM 评分标准,每个阶段自动参考,降低模型幻觉。

✅ 9 步自动验收 文本泄漏检测 → 数值一致性校验 → Typst 编译 → PDF 可视化检查,确保论文零低级错误。

🔧 可组合、可扩展 每个阶段是独立 Skill,可单独调用(如只跑分析、只写论文);模板和知识库可自由扩展;支持 Typst 生态排版。

Skills 一览

工作流 Skills 按 1–6 阶段串联,也可以按需单独调用。

Skill 用途 主要交付
1start-mathmodel 启动完整数学建模流程,安排各阶段任务 建模计划与任务清单
2analysis-modeling 分析赛题与数据,设计模型和求解策略 建模报告、假设、公式与约束
3coding-visual 编写并运行求解代码,生成数据图表 可复现代码、结果报告与图表 PDF
4drawio 绘制技术路线、求解流程与模型结构图 可编辑的 DrawIO 图与 PDF
5writing 选择比赛模板,组织和排版论文 Typst / LaTeX 论文源码与 PDF
6verity 核对数值、引用、图表、编译与提交要求 验收报告与待修复问题
mathmodel-to-ei 将完整数模论文改写为英文会议论文 IEEE LaTeX 源码、PDF 与改稿说明
doctor 检查工作流依赖,指导补齐环境 环境检查结果与安装指引
typst-author 编写、修改和排查 Typst 文档 Typst 源码与排版修复
mathmodel-figure-templates 使用内置科研绘图模板,按需调整样式 绘图脚本与 PNG / PDF / SVG
_references 提供各阶段共用的建模、写作与图表规范 共享参考知识库,由其他 Skills 按需读取

数模论文转 EI 会议论文

已有完整的数学建模竞赛论文,可以使用 mathmodel-to-ei 提炼研究主线、重组章节、改写英文正文并整理图表。内置 IEEE conference LaTeX 模板,交付论文源码、编译成功的 PDF 和改稿说明;目标会议有指定模板时优先使用指定模板。

使用 $mathmodel-to-ei,将这篇完整数模论文改写为英文会议论文,交付源码、PDF 和改稿说明。

下图展示了研赛 2025 A 题论文改写为英文会议初稿的示例,包含论文预览与交付清单。初稿仍需补齐作者信息并确认目标会议要求,不代表已录用或被 EI 收录。

数模论文转英文会议论文示例:改稿交付清单与 IEEE 双栏论文预览

🎨 姊妹项目:sci-box(科研图表 & 流程图)

科研绘图和流程图模板已独立成仓库 jihe520/sci-box,可单独安装、单独使用:

SKILL 内容
scibox-figure SHAP / ROC / Taylor / 云雨图 / 和弦图 / 环形热图等科研图表复刻模板(Python + Matplotlib,导出 PNG / PDF / SVG)
scibox-diagram 可编辑的 draw.io 模板:五层技术路线图、三栏研究框架、三栏流程图、横向任务流水线
npx skills add jihe520/sci-box

figure

Install & Usage

安装 SKILL

npx skills add jihe520/MathModelAgent --all

运行

// claude
claude --dangerously-skip-permissions
claude: /1start-mathmodel 完成这个数学建模任务

// codex
codex --yolo
codex: $start-mathmodel 完成这个数学建模任务

其他命令

/doctor:  检查环境配置
/typst-author: typst 知识

What Can You Contribute?

项目以后只会做 SKLLS 层的迭代和优化,不会再做其他部分。

如果你希望寻找 Agent 开发岗位,你可以研究该项目 Agent 设计并贡献,我会尽量合并.

你能做什么:

  • 优化贡献比赛 typst Template , 你可以找一些 LaTeX 转成 typst
  • 优化 SKILL Workflow
  • 在不同的 Harness 上测试 不同的 LLM, 提供反馈和案例放在 example 仓库

Harness SKILL 的优化需要大量黑盒测试和调优.

Thinking

  • 两年前,我做了一个 Mulit-Agent 的数学建模项目并开源出来,收到了社区的欢迎和很多 star, 感谢大家支持。
  • 感谢开源的 latex 模板,我在此基础上转化为 typst 模板
  • 此 SKILL 是一个基础模板,你可以基于此构建更适合你自己的 MathModel SKILL
  • For Agent DEVs : 两年前,我都是自己实现一套 Agent 框架,现在和以后更多的 Agent 产品直接基于 Harness 如 Codex / Claude Code / Pi + SKILLS 来构建


🚀 后期计划

  • 添加并完成 webui、cli
  • 完善的教程、文档
  • 提供 web 服务
  • 英文支持(美赛)
  • 集成 latex 模板
  • 接入视觉模型
  • 添加正确文献引用
  • 更多测试案例
  • docker 部署
  • human in loop ( HIL ): 关键节点暂停等待用户审批,支持 6 种决策动作(confirm/edit/regenerate/ask/skip/abort)
  • feedback: 评估器评分 + 反馈注入重跑,先 Writer 后 Coder
  • codeinterpreter 接入云端 如 e2b 等供应商..
  • 多语言: R 语言, matlab
  • 绘图 napki,draw.io,plantuml,svg, mermaid.js
  • 添加 benchmark
  • web search tool: Tavily API 搜索互联网获取真实数据
  • RAG 知识库: ChromaDB + Rerank 检索建模方法、代码模板、论文写作参考
  • A2A hand off: Fallback 自动切换备用模型 + 有限重试 + Evaluator Shadow Mode
  • chat / agent mode

视频demo

mathmodelagent.mp4

Caution

项目处于实验探索迭代demo阶段,有许多需要改进优化改进地方,我(项目作者)很忙,有时间会优化更新 欢迎贡献

📖 使用教程

提供三种部署方式,请选择最适合你的方案:

  1. docker(最简单)
  2. 本地部署
  3. 脚本本地部署(社区)

下载项目

git clone https://github.com/jihe520/MathModelAgent.git # 克隆项目

如果你想运行 命令行版本 cli 切换到 master 分支,部署更简单,但未来不会更新

🐳 方案一:Docker 部署(推荐:安全简单)

确保电脑安装了 docker 环境

  1. 启动服务

在项目文件夹下运行:

docker-compose up
  1. 访问

现在你可以访问:

  1. 配置

侧边栏 -> 头像 -> API Key

💻 方案二: 本地部署(推荐项目开发者部署)

确保电脑中安装好 Python, Nodejs, Redis 环境

step1:安装依赖
  1. 下载Redis(记得设置环境变量redis_path)
  1. 安装后端依赖
# ============ 安装依赖 ============
# 1. 切换到 backend 目录
cd backend
# 2. 安装 uv 包管理器(推荐)
pip install uv
# 3. 同步项目依赖
uv sync
# ============ MacOS / Linux 安装命令 ============
# 1. 设置环境变量
export ENV=DEV
export REDIS_URL=redis://localhost:6379/0
# ============ Windows PowerShell 安装命令 ============
# 1. 设置环境变量
$env:ENV="DEV"
$env:REDIS_URL="redis://localhost:6379/0"
# 2. 设置 PowerShell 执行策略策略为 RemoteSigned
Set-ExecutionPolicy RemoteSigned -Scope CurrentUser
# 3. 创建虚拟环境
python -m venv venv

3.安装前端依赖

cd frontend # 切换到 frontend 目录下
npm install -g pnpm
pnpm i
step2:启动项目

windows用户直接双击运行项目中的win_start.bat 即可启动项目

1.启动 Redis

redis-server

2.启动后端

# ============ MacOS / Linux 安装命令 ============
# 1. 激活虚拟环境
source .venv/bin/activate
# 2. 启动后端服务(激活后可直接使用 uvicorn 命令)
uvicorn app.main:app --host 0.0.0.0 --port 8000 --ws-ping-interval 60 --ws-ping-timeout 120 --reload
# ============ Windows PowerShell 安装命令 ============
# 1. 切换到 backend 目录
cd .\backend\
# 2. 激活虚拟环境
.\venv\Scripts\Activate.ps1
# 3. 启动后端服务
uvicorn app.main:app --host 0.0.0.0 --port 8000 --ws-ping-interval 60 --ws-ping-timeout 120 --reload

3.启动前端

cd .\frontend\
pnpm run dev

修改 backend/.env.dev 的环境变量 REDIS_URL

配置API Key

  1. 使用 WebUI  侧边栏 -> 头像 -> API Key
  2. 修改 backend/.env.dev 文件  先将.env.example文件 改为.env.dev  然后在.env.dev中 修改各 Agent API 配置

🚀 方案三:自动脚本部署(来自社区)

有没有自动部署的脚本 ? mmaAutoSetupRun

教程

运行的结果和产生在backend/project/work_dir/xxx/*目录下

  • notebook.ipynb: 保存运行过程中产生的代码
  • res.md: 保存最后运行产生的结果为 markdown 格式

需要自定义自定义提示词模板 template ? Prompt Inject : prompt

网络状况太差难以配置Docker等设置? 网络不畅时的配置过程示例:网络环境极差时的MathModelAgent配置过程

⚙️ 新功能配置

MathModelAgent 支持以下可选功能,默认已关闭,开启后未配置外部依赖时自动降级跳过。详见 升级说明。

功能 配置开关 说明
Web Search SEARCH_ENABLED + TAVILY_API_KEY Agent 自主联网搜索真实数据(Tavily API)
RAG 知识库 RAG_ENABLED 从本地知识库检索建模方法和代码模板(ChromaDB + Rerank)
HIL 人机协作 HIL_ENABLED 关键节点暂停等待用户审批,支持 6 种决策动作
Fallback Hand Off FALLBACK_* 系列 主模型故障自动切换备用模型
Evaluator + Feedback EVALUATOR_* 系列 输出质量评估 + 反馈重跑

快速启用 Web Search:注册 Tavily 获取 API Key,在 backend/.env.dev 中设置 TAVILY_API_KEY=tvly-xxx。

🤝 贡献和开发

DeepWiki | Zread

Tip

如果你有跑出来好的案例可以提交 PR 在该仓库下: MathModelAgent-Example

  • 项目处于开发实验阶段(我有时间就会更新),变更较多,还存在许多 Bug,我正着手修复。
  • 希望大家一起参与,让这个项目变得更好
  • 非常欢迎使用和提交 PRs 和 issues
  • 需求参考 后期计划

clone 项目后,下载 Todo Tree 插件,可以查看代码中所有具体位置的 todo

.cursor/* 有项目整体架构、rules、mcp 可以方便开发使用

📄 版权License

个人免费使用,请勿商业用途,商业用途联系我(作者)

License

🙏 Reference

Thanks to the following projects:

其他

💖 Sponsor

☕️ 给作者买一杯咖啡

https://linux.do/

企业

302.AI 是一个按用量付费的企业级AI资源平台,提供市场上最新、最全面的AI模型和API,以及多种开箱即用的在线AI应用

用户

danmo-tyc

👥 GROUP

有问题可以进群问

点击链接加入腾讯频道【MathModelAgent】:https://pd.qq.com/s/7rfbai3au

点击链接加入群聊 779159301【MathModelAgent】:https://qm.qq.com/q/Fw2cCJPoki

Discord

Caution

免责声明: 注意,AI 生成仅供参考,目前水平直接参加国赛获奖是不可能的,但我相信 AI 和 该项目未来的成长。

View on GitHub

Recent activity

commits and pull requests

Recent open issues

view all

Releases and announcements

25 total
  1. mathmodel v0.0.22v0.0.22Sep 22, 202698K downloads

    ## mathmodel v0.0.22 ### 🐞 修复问题 - 修复文件引用后的文字显示不完整、切换页面后草稿丢失的问题。 - 修复关闭预览弹窗后界面无法操作的问题。 <details> <summary><strong>🚀 优化改进</strong></summary> - 更新华为杯 2026 论文模板,调整封面、页码和正文排版。 - 优化登录与对话启动失败提示。 - 统一下拉菜单样式,改善模型选择和技能信息展示。 </details> ## 下载地址 ### macOS - DMG 安装包:[Apple 芯片(M 系列)](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.22/mathmodel-0.0.22-arm64.dmg) | [Intel 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.22/mathmodel-0.0.22-x64.dmg) - ZIP 压缩包:[Apple 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.22/mathmodel-0.0.22-arm64.zip) | [Intel 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.22/mathmodel-0.0.22-x64.zip) macOS 安装包已经过 Developer ID 签名和 Apple 公证。 ### Windows - [Windows 64 位安装包](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.22/mathmodel-0.0.22-x64.exe) > [!WARNING] > Windows 安装包当前未签名。首次安装或运行时可能出现 Microsoft Defender SmartScreen 提示,请从本 Release 页面下载安装。Windows 自动更新将在配置代码签名证书后启用。 <details> <summary><strong>📦 其他文件说明</strong></summary> - `latest.yml`、`latest-mac.yml`、`beta.yml`、`beta-mac.yml` 和 `.blockmap` 文件用于应用自动更新,一般无需手动下载。 - 遇到安装问题时,请在本 Release 页面提交反馈并注明系统版本与设备架构。 </de

  2. mathmodel v0.0.21v0.0.21Sep 20, 202620.5K downloads

    ## mathmodel v0.0.21 ### 🐞 修复问题 - 修复部分情况下无法启动、重新打开窗口后未保留原有页面的问题。 - 修复模型配置变更后旧对话无法继续发送、部分模型设置丢失的问题。 - 修复删除模板后仍有相关内容残留的问题。 - 修复更新下载异常的问题。 <details> <summary><strong>🚀 优化改进</strong></summary> - 改善长对话的响应体验。 - 打开工作文件夹时,直接定位到当前对话。 - 优化 PDF 预览、新手引导和托盘图标。 </details> ## 下载地址 ### macOS - DMG 安装包:[Apple 芯片(M 系列)](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21/mathmodel-0.0.21-arm64.dmg) | [Intel 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21/mathmodel-0.0.21-x64.dmg) - ZIP 压缩包:[Apple 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21/mathmodel-0.0.21-arm64.zip) | [Intel 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21/mathmodel-0.0.21-x64.zip) macOS 安装包已经过 Developer ID 签名和 Apple 公证。 ### Windows - [Windows 64 位安装包](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21/mathmodel-0.0.21-x64.exe) > [!WARNING] > Windows 安装包当前未签名。首次安装或运行时可能出现 Microsoft Defender SmartScreen 提示,请从本 Release 页面下载安装。Windows 自动更新将在配置代码签名证书后启用。 <details> <summary><strong>📦 其他文件说明</strong></summary> - `latest.yml`、`latest-mac.yml`、`beta.yml`、`beta-mac.yml` 和 `.blockmap` 文件用于应用自动更新,一般无需手动下载。 - 遇到安装问题时,请在本

  3. mathmodel v0.0.21-beta.2v0.0.21-beta.2Sep 17, 2026pre-release105 downloads

    ## mathmodel v0.0.21-beta.2 > [!WARNING] > 这是供自愿参与升级测试的测试版,可能不稳定。重要项目请先保留备份。 ## 本次测试内容 - 修复部分设备升级后无法打开应用的问题。 - 改善 Claude 和 Codex 启动失败时的提示,保留已发送的问题。 - 修复删除自定义模板后仍显示失效项目的问题。 - 修复自定义模型的思考强度设置和缓存用量显示不准确的问题。 - 再次打开应用时保留原来的页面、草稿和编辑状态。 ## 下载地址 ### macOS - DMG 安装包:[Apple 芯片(M 系列)](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21-beta.2/mathmodel-0.0.21-beta.2-arm64.dmg) | [Intel 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21-beta.2/mathmodel-0.0.21-beta.2-x64.dmg) - ZIP 压缩包:[Apple 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21-beta.2/mathmodel-0.0.21-beta.2-arm64.zip) | [Intel 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21-beta.2/mathmodel-0.0.21-beta.2-x64.zip) macOS 安装包已经过 Developer ID 签名和 Apple 公证。 ### Windows - [Windows 64 位安装包](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21-beta.2/mathmodel-0.0.21-beta.2-x64.exe) > [!WARNING] > Windows 安装包当前未签名。首次安装或运行时可能出现 Microsoft Defender SmartScreen 提示,请只从本 Release 页面下载安装。 <details> <summary><strong>📦 其他文件说明</strong></summary> - `beta.yml`、`beta-mac.yml` 和 `.blockmap` 文件用于测试版自动更新,一般无需手动下载。 - 遇到问题时,请反馈系统版本、设备架构和从哪个版本升级。

  4. mathmodel v0.0.21-beta.1v0.0.21-beta.1Sep 16, 2026pre-release94 downloads

    ## mathmodel v0.0.21-beta.1 > [!WARNING] > 这是供自愿参与升级测试的测试版,可能不稳定。重要项目请先保留备份。 ## 本次测试内容 - 修复部分 Windows 设备偶尔无法打开应用的问题。 - 改善 Claude 和 Codex 启动失败时的提示,保留已发送的问题。 - 修复删除自定义模板后仍显示失效项目的问题。 - 修复自定义模型的思考强度设置和缓存用量显示不准确的问题。 - 再次打开应用时保留原来的页面、草稿和编辑状态。 ## 下载地址 ### macOS - DMG 安装包:[Apple 芯片(M 系列)](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21-beta.1/mathmodel-0.0.21-beta.1-arm64.dmg) | [Intel 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21-beta.1/mathmodel-0.0.21-beta.1-x64.dmg) - ZIP 压缩包:[Apple 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21-beta.1/mathmodel-0.0.21-beta.1-arm64.zip) | [Intel 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21-beta.1/mathmodel-0.0.21-beta.1-x64.zip) macOS 安装包已经过 Developer ID 签名和 Apple 公证。 ### Windows - [Windows 64 位安装包](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.21-beta.1/mathmodel-0.0.21-beta.1-x64.exe) > [!WARNING] > Windows 安装包当前未签名。首次安装或运行时可能出现 Microsoft Defender SmartScreen 提示,请只从本 Release 页面下载安装。 <details> <summary><strong>📦 其他文件说明</strong></summary> - `beta.yml`、`beta-mac.yml` 和 `.blockmap` 文件用于测试版自动更新,一般无需手动下载。 - 遇到问题时,请反馈系统版本、设备架构和从哪

  5. mathmodel v0.0.20v0.0.20Sep 14, 202612.4K downloads

    ## mathmodel v0.0.20 ### ✨ 新增功能 - 新增竞赛日历,支持查看赛程、比赛详情、报名入口和收藏比赛。 ### 🐞 修复问题 - 修复部分 PDF 读取、Windows 文献搜索和绘图导出问题。 <details> <summary><strong>🚀 优化改进</strong></summary> - 每个对话分别记住模型选择,切换会话更方便。 - 优化报错提示,提供更清楚的处理建议。 </details> ## 下载地址 ### macOS - DMG 安装包:[Apple 芯片(M 系列)](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.20/mathmodel-0.0.20-arm64.dmg) | [Intel 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.20/mathmodel-0.0.20-x64.dmg) - ZIP 压缩包:[Apple 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.20/mathmodel-0.0.20-arm64.zip) | [Intel 芯片](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.20/mathmodel-0.0.20-x64.zip) macOS 安装包已经过 Developer ID 签名和 Apple 公证。 ### Windows - [Windows 64 位安装包](https://github.com/jihe520/MathModelAgent/releases/download/v0.0.20/mathmodel-0.0.20-x64.exe) > [!WARNING] > Windows 安装包当前未签名。首次安装或运行时可能出现 Microsoft Defender SmartScreen 提示,请从本 Release 页面下载安装。Windows 自动更新将在配置代码签名证书后启用。 <details> <summary><strong>📦 其他文件说明</strong></summary> - `latest.yml`、`latest-mac.yml`、`beta.yml`、`beta-mac.yml` 和 `.blockmap` 文件用于应用自动更新,一般无需手动下载。 - 遇到安装问题时,请在本 Release 页面提交反馈并注明系统版本与设备架构。 </detail

Code frequency

additions and deletions
+2.2M-2.2MWeek of 2025-09-28: +119 linesWeek of 2025-09-28: -130 linesWeek of 2025-10-05: +0 linesWeek of 2025-10-05: -0 linesWeek of 2025-10-12: +0 linesWeek of 2025-10-12: -0 linesWeek of 2025-10-19: +0 linesWeek of 2025-10-19: -0 linesWeek of 2025-10-26: +0 linesWeek of 2025-10-26: -0 linesWeek of 2025-11-02: +0 linesWeek of 2025-11-02: -0 linesWeek of 2025-11-09: +0 linesWeek of 2025-11-09: -0 linesWeek of 2025-11-16: +0 linesWeek of 2025-11-16: -0 linesWeek of 2025-11-23: +0 linesWeek of 2025-11-23: -0 linesWeek of 2025-11-30: +0 linesWeek of 2025-11-30: -0 linesWeek of 2025-12-07: +0 linesWeek of 2025-12-07: -0 linesWeek of 2025-12-14: +0 linesWeek of 2025-12-14: -0 linesWeek of 2025-12-21: +0 linesWeek of 2025-12-21: -0 linesWeek of 2025-12-28: +0 linesWeek of 2025-12-28: -0 linesWeek of 2026-01-04: +0 linesWeek of 2026-01-04: -0 linesWeek of 2026-01-11: +0 linesWeek of 2026-01-11: -0 linesWeek of 2026-01-18: +0 linesWeek of 2026-01-18: -0 linesWeek of 2026-01-25: +0 linesWeek of 2026-01-25: -0 linesWeek of 2026-02-01: +0 linesWeek of 2026-02-01: -0 linesWeek of 2026-02-08: +0 linesWeek of 2026-02-08: -0 linesWeek of 2026-02-15: +4 linesWeek of 2026-02-15: -0 linesWeek of 2026-02-22: +1 linesWeek of 2026-02-22: -7 linesWeek of 2026-03-01: +0 linesWeek of 2026-03-01: -0 linesWeek of 2026-03-08: +0 linesWeek of 2026-03-08: -0 linesWeek of 2026-03-15: +748 linesWeek of 2026-03-15: -256 linesWeek of 2026-03-22: +0 linesWeek of 2026-03-22: -0 linesWeek of 2026-03-29: +0 linesWeek of 2026-03-29: -0 linesWeek of 2026-04-05: +0 linesWeek of 2026-04-05: -0 linesWeek of 2026-04-12: +0 linesWeek of 2026-04-12: -0 linesWeek of 2026-04-19: +29 linesWeek of 2026-04-19: -54 linesWeek of 2026-04-26: +278 linesWeek of 2026-04-26: -49 linesWeek of 2026-05-03: +0 linesWeek of 2026-05-03: -0 linesWeek of 2026-05-10: +12,408 linesWeek of 2026-05-10: -8,767 linesWeek of 2026-05-17: +582 linesWeek of 2026-05-17: -357 linesWeek of 2026-05-24: +0 linesWeek of 2026-05-24: -0 linesWeek of 2026-05-31: +35,915 linesWeek of 2026-05-31: -2,211,311 linesWeek of 2026-06-07: +1 linesWeek of 2026-06-07: -1 linesWeek of 2026-06-14: +5,933 linesWeek of 2026-06-14: -130 linesWeek of 2026-06-21: +0 linesWeek of 2026-06-21: -0 linesWeek of 2026-06-28: +3,330 linesWeek of 2026-06-28: -0 linesWeek of 2026-07-05: +0 linesWeek of 2026-07-05: -0 linesWeek of 2026-07-12: +0 linesWeek of 2026-07-12: -0 linesWeek of 2026-07-19: +248 linesWeek of 2026-07-19: -89 linesWeek of 2026-07-26: +0 linesWeek of 2026-07-26: -0 linesWeek of 2026-08-02: +0 linesWeek of 2026-08-02: -0 linesWeek of 2026-08-09: +65 linesWeek of 2026-08-09: -0 linesWeek of 2026-08-16: +33 linesWeek of 2026-08-16: -1 linesWeek of 2026-08-23: +0 linesWeek of 2026-08-23: -0 linesWeek of 2026-08-30: +0 linesWeek of 2026-08-30: -0 linesWeek of 2026-09-06: +0 linesWeek of 2026-09-06: -0 linesWeek of 2026-09-13: +2 linesWeek of 2026-09-13: -2 linesWeek of 2026-09-20: +0 linesWeek of 2026-09-20: -0 linesSep 28, 2025Sep 20, 2026
+59.7K lines added, -2.2M removed over the last year.

Commits per week

last 52 weeks
80Week of 2025-10-05: 0 commitsWeek of 2025-10-12: 0 commitsWeek of 2025-10-19: 0 commitsWeek of 2025-10-26: 0 commitsWeek of 2025-11-02: 0 commitsWeek of 2025-11-09: 0 commitsWeek of 2025-11-16: 0 commitsWeek of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 0 commitsWeek of 2026-02-01: 0 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 1 commitsWeek of 2026-02-22: 1 commitsWeek of 2026-03-01: 0 commitsWeek of 2026-03-08: 0 commitsWeek of 2026-03-15: 1 commitsWeek of 2026-03-22: 0 commitsWeek of 2026-03-29: 0 commitsWeek of 2026-04-05: 0 commitsWeek of 2026-04-12: 0 commitsWeek of 2026-04-19: 2 commitsWeek of 2026-04-26: 3 commitsWeek of 2026-05-03: 0 commitsWeek of 2026-05-10: 8 commitsWeek of 2026-05-17: 3 commitsWeek of 2026-05-24: 0 commitsWeek of 2026-05-31: 2 commitsWeek of 2026-06-07: 1 commitsWeek of 2026-06-14: 1 commitsWeek of 2026-06-21: 0 commitsWeek of 2026-06-28: 1 commitsWeek of 2026-07-05: 0 commitsWeek of 2026-07-12: 0 commitsWeek of 2026-07-19: 1 commitsWeek of 2026-07-26: 0 commitsWeek of 2026-08-02: 0 commitsWeek of 2026-08-09: 1 commitsWeek of 2026-08-16: 1 commitsWeek of 2026-08-23: 0 commitsWeek of 2026-08-30: 0 commitsWeek of 2026-09-06: 0 commitsWeek of 2026-09-13: 1 commitsWeek of 2026-09-20: 0 commitsWeek of 2026-09-27: 2 commitsOct 5, 2025Sep 27, 2026
30 commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 1 commitsSun 1:00 — 0 commitsSun 2:00 — 0 commitsSun 3:00 — 0 commitsSun 4:00 — 0 commitsSun 5:00 — 0 commitsSun 6:00 — 0 commitsSun 7:00 — 0 commitsSun 8:00 — 0 commitsSun 9:00 — 0 commitsSun 10:00 — 1 commitsSun 11:00 — 1 commitsSun 12:00 — 0 commitsSun 13:00 — 0 commitsSun 14:00 — 1 commitsSun 15:00 — 2 commitsSun 16:00 — 2 commitsSun 17:00 — 1 commitsSun 18:00 — 0 commitsSun 19:00 — 0 commitsSun 20:00 — 0 commitsSun 21:00 — 1 commitsSun 22:00 — 1 commitsSun 23:00 — 0 commitsMon 0:00 — 0 commitsMon 1:00 — 0 commitsMon 2:00 — 0 commitsMon 3:00 — 0 commitsMon 4:00 — 0 commitsMon 5:00 — 0 commitsMon 6:00 — 0 commitsMon 7:00 — 0 commitsMon 8:00 — 0 commitsMon 9:00 — 0 commitsMon 10:00 — 2 commitsMon 11:00 — 0 commitsMon 12:00 — 0 commitsMon 13:00 — 1 commitsMon 14:00 — 2 commitsMon 15:00 — 0 commitsMon 16:00 — 1 commitsMon 17:00 — 0 commitsMon 18:00 — 0 commitsMon 19:00 — 1 commitsMon 20:00 — 2 commitsMon 21:00 — 0 commitsMon 22:00 — 2 commitsMon 23:00 — 3 commitsTue 0:00 — 2 commitsTue 1:00 — 0 commitsTue 2:00 — 0 commitsTue 3:00 — 0 commitsTue 4:00 — 0 commitsTue 5:00 — 0 commitsTue 6:00 — 0 commitsTue 7:00 — 0 commitsTue 8:00 — 0 commitsTue 9:00 — 0 commitsTue 10:00 — 1 commitsTue 11:00 — 1 commitsTue 12:00 — 1 commitsTue 13:00 — 0 commitsTue 14:00 — 2 commitsTue 15:00 — 1 commitsTue 16:00 — 0 commitsTue 17:00 — 0 commitsTue 18:00 — 0 commitsTue 19:00 — 1 commitsTue 20:00 — 0 commitsTue 21:00 — 0 commitsTue 22:00 — 0 commitsTue 23:00 — 3 commitsWed 0:00 — 0 commitsWed 1:00 — 0 commitsWed 2:00 — 0 commitsWed 3:00 — 0 commitsWed 4:00 — 0 commitsWed 5:00 — 0 commitsWed 6:00 — 0 commitsWed 7:00 — 0 commitsWed 8:00 — 1 commitsWed 9:00 — 0 commitsWed 10:00 — 0 commitsWed 11:00 — 0 commitsWed 12:00 — 0 commitsWed 13:00 — 1 commitsWed 14:00 — 3 commitsWed 15:00 — 1 commitsWed 16:00 — 0 commitsWed 17:00 — 0 commitsWed 18:00 — 0 commitsWed 19:00 — 1 commitsWed 20:00 — 0 commitsWed 21:00 — 0 commitsWed 22:00 — 0 commitsWed 23:00 — 1 commitsThu 0:00 — 1 commitsThu 1:00 — 0 commitsThu 2:00 — 0 commitsThu 3:00 — 0 commitsThu 4:00 — 0 commitsThu 5:00 — 0 commitsThu 6:00 — 0 commitsThu 7:00 — 0 commitsThu 8:00 — 0 commitsThu 9:00 — 0 commitsThu 10:00 — 0 commitsThu 11:00 — 0 commitsThu 12:00 — 0 commitsThu 13:00 — 1 commitsThu 14:00 — 1 commitsThu 15:00 — 0 commitsThu 16:00 — 1 commitsThu 17:00 — 0 commitsThu 18:00 — 0 commitsThu 19:00 — 0 commitsThu 20:00 — 1 commitsThu 21:00 — 0 commitsThu 22:00 — 0 commitsThu 23:00 — 1 commitsFri 0:00 — 0 commitsFri 1:00 — 0 commitsFri 2:00 — 0 commitsFri 3:00 — 0 commitsFri 4:00 — 0 commitsFri 5:00 — 0 commitsFri 6:00 — 0 commitsFri 7:00 — 0 commitsFri 8:00 — 0 commitsFri 9:00 — 0 commitsFri 10:00 — 1 commitsFri 11:00 — 0 commitsFri 12:00 — 0 commitsFri 13:00 — 2 commitsFri 14:00 — 2 commitsFri 15:00 — 3 commitsFri 16:00 — 2 commitsFri 17:00 — 0 commitsFri 18:00 — 0 commitsFri 19:00 — 0 commitsFri 20:00 — 3 commitsFri 21:00 — 1 commitsFri 22:00 — 3 commitsFri 23:00 — 2 commitsSat 0:00 — 0 commitsSat 1:00 — 2 commitsSat 2:00 — 0 commitsSat 3:00 — 0 commitsSat 4:00 — 0 commitsSat 5:00 — 0 commitsSat 6:00 — 0 commitsSat 7:00 — 0 commitsSat 8:00 — 0 commitsSat 9:00 — 0 commitsSat 10:00 — 0 commitsSat 11:00 — 0 commitsSat 12:00 — 0 commitsSat 13:00 — 1 commitsSat 14:00 — 2 commitsSat 15:00 — 2 commitsSat 16:00 — 0 commitsSat 17:00 — 0 commitsSat 18:00 — 1 commitsSat 19:00 — 3 commitsSat 20:00 — 0 commitsSat 21:00 — 0 commitsSat 22:00 — 0 commitsSat 23:00 — 0 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.

Who is committing

last 52 weeks
Maintainer commits13 (43%)
Community commits17 (57%)

30 commits in total over the last year.

DateListRankStars gained
Sep 14, 2026daily#12+262
Sep 13, 2026daily#12+262
Sep 12, 2026daily#5+129
Sep 11, 2026daily#10+132
  • obra/superpowers

    An agentic skills framework & software development methodology that works.

    295.2K stars · Shell

  • affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    272.8K stars · JavaScript

  • NousResearch/hermes-agent

    The agent that grows with you

    251.2K stars · Python

  • firecrawl/firecrawl

    Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

    188.6K stars · TypeScript

  • Significant-Gravitas/AutoGPT

    AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

    187.7K stars · Python

  • f/prompts.chat

    f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

    172K stars · HTML