Kapso
by Community
Kapso by Leeroo: Long-running agents that optimize AI and Data systems, and learn from every experience. #1 open-source on MLE-Bench; ALE-Bench; RelBench
OSS
Kapso
Added 1 Oct 2026
Overview
Kapso is an open-source Python project from Leeroo that provides long-running agents for optimizing AI and data systems, with a focus on learning from each experience. It is ranked #1 open-source on MLE-Bench, ALE-Bench, and RelBench benchmarks.
Best for
Best for
Teams building long-running AI/data optimization agents that want a benchmark-proven open-source starting point.
Use cases
- Automate optimization of machine learning pipelines
- Monitor and improve data system performance over time
- Benchmark agent performance on MLE-Bench, ALE-Bench, and RelBench
Notes
118 stars on GitHub. Last updated 2026-09-29. Licensed MIT.
Pros
- Open-source with a Python codebase
- Proven performance on multiple benchmarks
- Designed for long-running autonomous operation
Cons
- Small user base (118 stars)
- Focused on benchmark performance, not general-purpose observability
- Limited information available beyond benchmark claims
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.