Skip to content

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

Commits on main

0ee8fbd
2e07e44
fix(media): preserve dataset upload errors (#17674)
Max Deichmann committed 1 month ago
6198f19
feat(mcp): support decision-model evaluators (#18166)
Tobias Wochinger committed 1 month ago
e59efe0
8ffa2cf
fix(evals): clarify evaluation rule reuse (#18162)
Tobias Wochinger committed 1 month ago
ebfac15
3faca12
f5967f3
chore: release v4.50.0
Nimar committed 1 month ago
ef10753
chore(deps): bump next to 16.3.8 (#18161)
Nimar committed 1 month ago
106c72a
d94fe62
c0e82da
fix(evals): reflect evaluator model availability (#18143)
Tobias Wochinger committed 1 month ago
d418eae