Leeroo open-sources Kapso, an iterative learning engine for enterprise data
What happened
On November 13, 2026, Leeroo's open-source Kapso reached the Hacker News front page. It runs iterative experiments against enterprise data tasks, accumulates experience, and adapts the chosen approach for deployment on the target stack. Users give the task goal and success criteria; the system screens candidates using past experience and a budget, then an independent validation module checks results and updates the confidence and applicability bounds of the relevant experience in the library. The report says Kapso is not tied to a specific model or coding agent, and its pipeline covers candidate screening, result validation, experience updates and deployment adaptation.
Written by AI from the coverage · updated 4 days ago
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pageShow HN: Kapso – Iterative learning from enterprise data
Leeroo 开源 Kapso,面向企业数据任务运行实验、积累经验并将选出的方案适配部署到目标技术栈。用户提供目标和成功标准后,系统依据历史经验与预算筛选方案,由独立验证模块检验结果,再更新经验库的置信度与适用边界;系统不绑定特定模型或编码智能体。
Heat over time
Heat now 3·Comparable peak 10(Nov 13 03:00)·Comparable change over 24 hours -49%
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.