OpenGithubs / OpenGithubs/weekly

【开源自荐】whatbroke:给 AI Agent 两次运行做行为 diff 的命令行工具

Open
#132 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
No language data
Stars
1.7k
Forks
71
PR merge metrics
No merged PRs in 30d

Description

推荐我自己开发的开源项目 whatbroke,希望有机会入选周刊。

项目简介

给 AI Agent 的行为做类似 git diff 的对比。改了提示词或者换了模型之后,对比前后两次运行:哪些工具调用是新增的、哪些消失了、哪些换了顺序,参数改了什么,成本和延迟差了多少。支持多次采样运行,会给出每个差异的出现频率,并自动降低那些在基线里本来就不稳定的项,减少误报。

今天发布的 v0.3.0 新增了 whatbroke import 命令,可以直接导入 OTLP JSON(OTel GenAI 语义约定)、Langfuse 和 LangSmith 的导出数据,已经接入链路追踪的 Agent 不用改一行代码就能做对比。全部在本地运行,不上传任何数据。

谢谢!

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No repository file, test, entry point, or concrete change is identified. The linked whatbroke project and its v0.3.0 features are described, but the issue does not define what should be changed in OpenGithubs/weekly or how completion would be verified.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
content
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.