Show HN: Aitori – open-source tool to inspect Claude and ChatGPT traffic
Aitori is an open-source tool that lets users inspect and analyze traffic between their applications and AI models like Claude and ChatGPT, providing visibility into API interactions.
Background
- Aitori is an open-source, self-hosted proxy tool that sits between a user and AI services (like ChatGPT, Claude, or any OpenAI-compatible API) to inspect, log, and modify the requests and responses going in and out.
- It allows developers to see exactly what data is being sent to and from large language models (LLMs), which is useful for debugging, auditing, compliance, or understanding how an AI application behaves under the hood.
- The tool is built by TrueFoundry, a company that provides infrastructure for deploying and managing machine learning models — this fits their existing focus on observability and control over AI workloads.
- For users of AI APIs, traffic is typically invisible unless you build custom logging. Aitori fills that gap with a transparent, inspectable proxy — similar in spirit to tools like mitmproxy, but tailored for LLM API formats.
- Being open-source and self-hosted means no third party handles the traffic; this matters for organizations with data privacy or compliance requirements who still want deep visibility into their AI usage.