optim-agent

optim-agent

Optimize hyperparameters using LLM agents.

Agent SkillDevOpen source
Type
Agent Skill
Open source
Yes
GitHub Stars
★ 1.0k
Source
skill-github

Overview

optim-agent is a system optimization tool based on coding agents that automates the iterative parameter tuning work of algorithm engineers. It optimizes system parameters by reading code, proposing experimental suggestions, and recording measurement results. Suitable for systems requiring parameter configuration and measurable objectives. It combines parameter semantics with historical experiment data to suggest the next configuration for evaluation. The tool supports various models and systems and can improve performance as the underlying coding agent evolves.

Capabilities

  • Semantic parameter suggestions
  • High leverage with limited budget
  • Agent CLI upgrade benefits
  • Auditable decisions
  • Bounded execution

Use cases

Model training parameter optimizationInference and service parameter optimizationScientific research parameter optimization

Setup

Requires: API KeyPython环境
python -m pip install optim-agent

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Which models does optim-agent support?

Supports models such as Claude Code, Codex, and OpenCode.

How to install optim-agent?

Install via pip: python -m pip install optim-agent.

Related skills