Skip to content
TopicTracker
来自 HackerNews查看原文
译文语言译文语言

Show HN: Aitori – 用于检查 Claude 和 ChatGPT 流量的开源工具

Aitori 是一款开源工具,可让用户检查和监控 Claude 与 ChatGPT 的 API 流量。它帮助开发者调试、审查和理解与这些 AI 模型之间的请求与响应数据,提升对 AI 交互的可观测性和透明度。

背景速读

- Aitori 是一个开源工具,由 TrueFoundry 开发,用于拦截和查看你与 Claude(Anthropic 出品)以及 ChatGPT(OpenAI 出品)之间的网络流量。它本质上是一个本地代理服务器,相当于在你和 AI 服务之间放了一个“监听器”,让你能看到实际往来的数据包内容。 - 这类工具的核心用途是调试、审计或理解 AI 聊天客户端到底向服务器发送了什么、接收了什么。对于开发者来说,这有助于排查提示词(prompt)构造问题、确认是否泄露了敏感信息、或者检验 API 调用的实际结构。 - 它的背景是:AI 对话服务的 API 调用往往被封装在官方客户端或 Web 界面之后,普通用户或开发者很难直接观察底层 HTTP 请求。开源代理工具填补了这个透明性缺口。 - 该项目在 GitHub 上以 Show HN 形式发布,属于“开发者工具/调试工具”类别,面向有一定技术背景、需要深入理解或调试 AI 交互流程的用户。

相关报道

  • Newer Claude models sometimes invent extra keys in tool call arguments, breaking validation in Pi's edit tool. The author suspects post-training for Claude Code's forgiving harness makes alternative schemas fail. This suggests closed RL training can degrade general tool-use reliability.

  • Simon Willison released llm-coding-agent 0.1a0, an experimental coding agent built on his LLM library. The agent provides tools for reading, editing, searching files and executing commands, and ships with a Python API and CLI. It was developed using Claude Code (Fable 5) via TDD with a spec-first approach, and is available as a slop-alpha on PyPI.

  • Truth Social remains an outlet primarily for Trump's own posts, while other administration officials continue using X. The platform functions as a blog-like channel for Trump's messages rather than a genuine social network competitor.