Langfuse
Trace agent runs, manage prompts and evaluate outputs in an AI engineering platform.
When to consider it
Consider it when you need to connect an agent's output to the model calls, tools and prompt versions behind it.
Before you choose
Our selection notes: use these checks for your own trial. These are recommendations, not results of a hands-on benchmark.
- Decide what sensitive content to redact before recording traces.
- Attach a stable run identifier to tool and model calls.
- Use a small, representative evaluation dataset before comparing changes.
Sources & project links
About this listing
Official documentation reviewed 2026-10-26. The overview is based on the linked official source. Selection advice is our interpretation.
Pricing, licensing, supported models and hosting requirements may change. Check the original project before installing or paying. Inclusion is not an endorsement or a performance rating.
Historical repository popularity
The old directory displayed 35.4k GitHub stars. Its original observation date is unknown. This is retained as historical context, not a live count or quality score.