Ask HN: Has anyone used Phoenix, Langfuse, or OpenObserve?
What worked well, and what issues or limitations did you run into?
If you only want observability then it is save and easy to switch to/from LangFuse. Other features (if you care about) are more lock-in.
Also, it take some times for LangFuse to process spans and traces from the agents, so if you want to have visibility in milliseconds then that is not the option for you. But if few minute gap before code execution and traces being available to explore is not a problem, then Langfuse is good. Other than that I did not observe problems with it.
The delay in Langfuse only happens if you are ingesting via outdated SDKs/endpoints. If you use the new ones there's no delay
OpenObserve is much simpler and lighter to run with all the features, including prompt management and evals.
Thanks a lot for your perspective. I needed a comparison cause I only used Phoenix. Its architecture is extremely simple. Tracing is nice, I didn't have any complaints. All other features like evaluations, datasets, prompts - I'd use a separate tool for this.
I used both Langfuse and Logfire. Imo both very similar, and at the same time limited when you want to customize graphs. Langfuse in general has broder feature set (however I used Logfire long time ago so it might have changed) like evaluation and prompt management
Also MLFlow since version 3.0 has nice features for agent observability. Worth investigating too as it is well established solution