Show HN: A better way to inspect and test AI Agents traces(github.com)
github.com
Show HN: A better way to inspect and test AI Agents traces
https://github.com/invariantlabs-ai/explorer
Hi everyone! My team and I just open-sourced a bunch of cool agent dev tools: Invariant Explorer to visually inspect and understand AI traces and a testing framework, building on pytest.
2 comments
What’s better/different/same from many tools in this space like langfuse etc
This is specifically directed at agent traces and not necessarily other LLM use cases. We work on a lot of automated analysis and error detection mechanisms (see https://github.com/invariantlabs-ai/invariant/tree/main/anal...) on such agent traces, which can be nicely shown and highlighted in line with the trace in Explorer. Also, agent builders value collaboration a lot. They send around traces like pastebins to point out specific issues and failure modes of their agents. Explorer makes it easy to point to specific points in long traces and annotate them.
One of the authors here. Let us know what you think :)