We built an open-source LLM observability tool. Would love your feedback!

Hey Product Hunt community!

I'm Haeseong, the solo founder behind Spanlens. I built it because I kept seeing the same problem around me. Developers shipping AI products had no clear picture of what was actually happening with their LLM calls in production. Costs were invisible, errors were silent, and when something broke, there was no trace.

Spanlens fixes that with two lines of code. You point your existing OpenAI, Anthropic, or Gemini SDK at our proxy URL, swap in a Spanlens API key, and from that point every request is logged, costs are tracked, and agent traces are captured automatically.

What makes it different from other observability tools out there

It supports multiple providers in one place. OpenAI, Anthropic, Gemini, Azure OpenAI, Ollama, LangChain, LlamaIndex, and the Vercel AI SDK all work out of the box.

It is fully open-source under the MIT license and self-hostable via Docker. No vendor lock-in, no mandatory cloud plan.

The integration takes two lines of code. Most observability tools require a full integration project. Spanlens does not.

We are launching on Product Hunt on June 3 and are also looking for a hunter who is active in the dev tools or AI space. If that sounds like you or someone you know, I would love to connect. Feel free to drop a comment or DM me.

Would love honest feedback on

Does the two-line integration concept land clearly?

Is there anything missing that you would expect from an LLM observability tool?

Check it out at spanlens.io. Thanks for reading!