Optim-AgentOptim-AgentCommunityยท1 Agent Skills Included

optim-agent

Automate parameter tuning for models, systems, and experiments

Automates the iterative parameter-tuning work of an algorithm engineer using coding agents. Reads your code to understand what each parameter means, proposes trial configurations, and records measured objective results. Eliminates manual guess-and-check tuning for model training, inference serving, quant strategies, and scientific workflows. Keeps every trial auditable with JSON or SQLite studies that resume after interruptions.
npx skills add Optim-Agent/optim-agent --all -g -y

All Skills in This Repository (1)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install optim-agent?โ–ผ

Run `npx skills add Optim-Agent/optim-agent --all -g -y` in your terminal to install the skill globally for your AI agent.

What does optim-agent actually do?โ–ผ

It lets coding agents like Claude Code or Codex tune real system parameters by reading your code, proposing trial values, and recording measured results until the objective is optimized.

Which AI agents work with optim-agent?โ–ผ

It works with Claude Code, Codex, and OpenCode/OpenClaw. You need one authenticated agent CLI available on your PATH.

What kinds of systems can optim-agent tune?โ–ผ

It tunes model training hyperparameters, inference and serving settings, quant trading rules, reinforcement learning configurations, and any black-box system with a measurable scalar objective.

Do I need optimization expertise to use optim-agent?โ–ผ

No. You define the parameter ranges and objective in plain Python, and the agent reasons over parameter meanings and trial history to propose the next configuration.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’