← All projects
jevals
openlayer-ai/jevals MIT Python Eval & Align
rank#133
Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.
- Stars
- 48
- Forks
- 2
- Open issues
- 0
- Last push
- today
Star history starts building from the first daily refresh.
agentsevalsguardrailsjevllmllm-evaluationragastypesafe