← All projects
jevals
openlayer-ai/jevals MIT Python Eval & Align
rank#155
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
- 112
- Forks
- 12
- Open issues
- 4
- Last push
- today
44 days · 48 → 112
agentsevalsguardrailsjevllmllm-evaluationragastypesafe