GitHub Repository

CLI tool that makes it easy to connect raw ML experiments data to AI Agents for autonomous research loops.

3 starsPython

Cadenza – Connect Wandb logs to agents easily for autonomous research

Name: Cadenza – Connect Wandb logs to agents easily for autonomous research
Availability: InStock
Author: hgarud

by hgarud·Apr 4, 2026·3 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidSolve My ProblemNiche Gem

Evolutionary database organization cuts context rot for agent experiment analysis.

Strengths

•Genotypes, islands, and elites structure mirrors how researchers actually think about experiments.
•Returns only high-performing runs to reduce token usage and context rot.
•Exploration/exploitation tradeoff configurable for different research phases.

Weaknesses

•Extremely niche audience — only ML researchers doing autonomous loops.
•W&B native API exists, though admittedly clunky for agent workflows.

Post Description

Wandb CLI and MCP is atrocious to use with agents for full autonomous research loops. They are slow, clunky, and result in context rot.

So I built a CLI tool and a Python SDK to make it easy to connect your Wandb projects and runs to your agent (clawed or otherwise). The cli tool works by allowing you to import your wandb projects and structures your runs in a way that makes it easy for agents to get a sense of the solution space of your research project.

When projects are imported, only the configs and metrics are analyzed to index and store your runs. When an agent samples from this index, only the most high performing experiments are returned which reduces context rot. You can also change the behavior of the index and your agent to trade-off exploration with exploitation.

Open sourcing the cli along with the python sdk to make it easy to use it with any agent. Would love feedback and critique from the community!

Github: https://github.com/mylucaai/cadenza Docs: https://myluca.ai/docs Pypi: https://pypi.org/project/cadenza-cli