← All projects
evalr
alexnodeland/evalr MIT Python Eval & Align
rank#376
Typed evaluation for agent systems: DSPy judges optimized with GEPA, TypeSafe Jev decision models, datasets and experiments in Langfuse.
- Stars
- 0
- Forks
- 0
- Open issues
- 2
- Last push
- today
Star history starts building from the first daily refresh.