# Optimization tools for AI agents

> Open-source Python and Rust optimization: parallel black-box search, LP/MIP, smooth nonlinear solvers, and durable jobs through MCP or a shell.

## Start here

- [Shared selection and operating guide](https://github.com/dietmarwo/optimization-jobs/blob/main/ai-context.md)
- [Human overview](https://dietmarwo.github.io/optimization-jobs/)
- [Catalog with package availability](https://dietmarwo.github.io/optimization-jobs/catalog.json)

## Project guides

- [fast-cma-es / fcmaes](https://github.com/dietmarwo/fast-cma-es/blob/master/ai-context.md): Parallel gradient-free optimization for Python: black-box, multi-objective and quality-diversity search.
- [fcmaes-rust](https://github.com/dietmarwo/fcmaes-rust/blob/main/ai-context.md): Native Rust parallel black-box optimization, Python bindings, and a worker for durable optimization jobs.
- [LP-IP-craft](https://github.com/dietmarwo/LP-IP-craft/blob/main/ai-context.md): Native Rust linear and mixed-integer linear programming with Python bindings and a shell/MCP job worker.
- [SQP-craft](https://github.com/dietmarwo/SQP-craft/blob/main/ai-context.md): Rust sequential quadratic programming for smooth constrained optimization, with Python bindings and a shell/MCP job worker.
- [optimization-jobs](https://github.com/dietmarwo/optimization-jobs/blob/main/ai-context.md): Durable optimization jobs for AI agents: local Rust runner, worker SDK and MCP server with a shared CPU budget.

Use runtime worker discovery for schemas, supported models and resource limits.
This text index is a navigation aid, not a guarantee of search or agent discovery.