AI4Math-Optimization

KO | EN

gitlite — search

#pytorch #claude #chatgpt #framework #cloud-native #pdf #gpt #editor #deep-learning #python

AI4Math-Optimization

(★ 9)

AI4Math skills for optimization modeling, solver routing, convex quadratic programming with OSQP, and manifold-constrained optimization with CDOpt.

File Explorer

ZIP Download

- - validate.yml
- - README.md
  - README.zh-CN.md
  - SKILL.md
- - comparison_mip_academic.png
  - examples.md
  - mip_academic_summary.png
  - README.md
  - SKILL.md
- - assignment-problem-example.md
  - assignment-problem-example.zh-CN.md
  - LICENSE
  - README.md
  - README.zh-CN.md
  - SKILL.md
  - SOURCES.md
  - UPDATE.md
- - examples.md
  - README.md
  - SKILL.md
- - README.md
  - README.zh-CN.md
  - requirements-test.txt
  - SKILL.md
- - comparison_socp_academic.png
  - examples.md
  - README.md
  - SKILL.md
  - socp_academic_summary.png
- test_cdopt_skill_shape.py
- test_osqp_solver_skill.py
CONTRIBUTORS.md
LICENSE
pyproject.toml
README.md
README.zh-CN.md
SKILL.md

# Use via CDN

jsDelivr

jsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.

Version

File

Link

Example

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

Skill packages for mathematical optimization modeling, solver setup,
LP/MIP/SOCP workflows, continuous convex QP/OSQP, and
manifold-constrained optimization.

[中文说明](README.zh-CN.md) · [Contributors](CONTRIBUTORS.md) · [Skill packages](#skill-packages) · [Installation](#installation) · [Quick start](#quick-start) · [Security model](#security-and-scope)

![version](https://img.shields.io/badge/version-0.1.0-blue)
![skills](https://img.shields.io/badge/skills-6-2ea44f)
![license](https://img.shields.io/badge/license-MIT-green)

</div>

<p align="center">
  If this project helps your work, please consider giving the repository a Star ⭐
  <a href="https://github.com/VeryMath/AI4Math-Optimization"><img alt="GitHub stars" src="https://img.shields.io/github/stars/VeryMath/AI4Math-Optimization?style=social"></a>
</p>

## What This Repository Is

This repository is the AI4Math home for optimization skills. It collects
packages for modeling mathematical programs, selecting solvers, checking solver
environments, adapting examples, and reporting evidence from optimization runs.

Use the root page as the public map. For concrete modeling or solving, open the
package that matches the problem class.

## Skill Packages

| Package | Use it for | Start here |
| --- | --- | --- |
| [`cdopt-optimization`](skills/cdopt-optimization/) | CDOpt and manifold-constrained optimization modeling, validation, runner generation, and evidence reports. | [`README`](skills/cdopt-optimization/README.md) · [`SKILL`](skills/cdopt-optimization/SKILL.md) |
| [`mixed-integer-programming`](skills/mixed-integer-programming/) | MILP/MIP modeling with binary, integer, and continuous decision variables. | [`README`](skills/mixed-integer-programming/README.md) · [`SKILL`](skills/mixed-integer-programming/SKILL.md) |
| [`second-order-cone-programming`](skills/second-order-cone-programming/) | SOCP modeling and cvxpy-based conic solver workflows. | [`README`](skills/second-order-cone-programming/README.md) · [`SKILL`](skills/second-order-cone-programming/SKILL.md) |
| [`or-solver`](skills/or-solver/) | Python dependencies, installation, licenses, environment variables, and setup troubleshooting for a specified solver. | [`README`](skills/or-solver/README.md) · [`SKILL`](skills/or-solver/SKILL.md) |
| [`osqp-solver`](skills/osqp-solver/) | OSQP modeling, repeated solves, status gates, and independent verification for continuous convex QPs. | [`README`](skills/osqp-solver/README.md) · [`SKILL`](skills/osqp-solver/SKILL.md) |
| [`optskills`](skills/optskills/) | Standalone selection and use of 103 released OptSkills problem-archetype cards, with explicit upstream updates. | [`README`](skills/optskills/README.md) · [`SKILL`](skills/optskills/SKILL.md) |

`optskills` can be used on its own for modeling and solving with an available
solver. The user or modeling skill chooses the solver; `or-solver` configures
that specified solver when dependency installation or license setup is needed.

## Installation

The recommended path is AI-assisted installation: ask your coding agent to clone or update this repository, read the Skill instructions, install the entrypoints, and verify discovery.

```text
Please install these AI4Math Skills for me.

Repository: https://github.com/VeryMath/AI4Math-Optimization.git
Branch: main
Skill paths:
- skills/cdopt-optimization
- skills/mixed-integer-programming
- skills/second-order-cone-programming
- skills/or-solver
- skills/osqp-solver
- skills/optskills

Steps:
1. Clone or update the repository locally.
2. Read README.md, SKILL.md, AGENTS.md if present, and each target Skill entrypoint.
3. If this environment supports local Skill discovery, link each directory that contains SKILL.md into the local skills directory.
4. Keep shared sibling support directories in place when a Skill depends on them.
5. Verify that the installed Skills are discoverable.
6. Tell me the installed paths, whether a restart is needed, and give me one test prompt.
```

Manual fallback for Codex-style local discovery:

```bash
git clone https://github.com/VeryMath/AI4Math-Optimization.git
cd AI4Math-Optimization
mkdir -p ~/.codex/skills
ln -s "$PWD/skills/cdopt-optimization" ~/.codex/skills/cdopt-optimization
ln -s "$PWD/skills/mixed-integer-programming" ~/.codex/skills/mixed-integer-programming
ln -s "$PWD/skills/second-order-cone-programming" ~/.codex/skills/second-order-cone-programming
ln -s "$PWD/skills/or-solver" ~/.codex/skills/or-solver
ln -s "$PWD/skills/osqp-solver" ~/.codex/skills/osqp-solver
ln -s "$PWD/skills/optskills" ~/.codex/skills/optskills
```

If your agent uses a different local Skill directory, replace `~/.codex/skills` with that configured path.

## Quick Start

Clone the repository and choose a package:

```bash
git clone https://github.com/VeryMath/AI4Math-Optimization.git
cd AI4Math-Optimization
```

To configure a solver already chosen by the user or modeling skill, start with:

```text
skills/or-solver/SKILL.md
```

For LP modeling, start with `skills/optskills/SKILL.md`. For dedicated MIP or
SOCP workflows, use the matching package under `skills/`. For CDOpt or
manifold-constrained tasks, start with:

```text
skills/cdopt-optimization/SKILL.md
```

For continuous convex QPs solved with OSQP, start with:

```text
skills/osqp-solver/SKILL.md
```

For natural-language operations-research archetypes, start with:

```text
skills/optskills/SKILL.md
```

## Repository Layout

```text
AI4Math-Optimization/
├── README.md
├── README.zh-CN.md
├── SKILL.md
└── skills/
    ├── cdopt-optimization/
    ├── mixed-integer-programming/
    ├── or-solver/
    ├── osqp-solver/
    ├── optskills/
    └── second-order-cone-programming/
```

Keep solver examples, scripts, references, and generated run evidence inside
the package that owns them.

## Validation

There is no root build step. When changing a package, validate its `SKILL.md`,
README links, scripts, and package-local examples. If you use Codex's local
skill validator, run it against every changed standard skill package.

## Security and Scope

Do not commit solver licenses, API keys, private datasets, `.env` files,
generated solver logs with sensitive data, or local run outputs. Public examples
should include source notes for benchmark data and be safe to redistribute.

AI4Math-Optimization

Owner Repos

File Explorer

# Use via CDN

Was this content helpful?

Recent Feedback

AI4Math-Optimization

Owner Repos

File Explorer

# Use via CDN

Was this content helpful?

Recent Feedback

Download README